Rescue positioning data fusion analysis method and system based on time series update

By integrating multiple positioning technologies and data fusion analysis methods, monitoring and analyzing the movement changes of rescue targets, the problem of insufficient real-time and accuracy of positioning in the existing technology is solved, and high-precision real-time three-dimensional positioning is achieved.

CN118584523BActive Publication Date: 2024-11-01ZHEJIANG YISHI TONGLIAN INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411050274.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-01
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

The existing rescue positioning technology is difficult to adapt to the dynamic changes of rescue targets in real time, resulting in insufficient real-time and accuracy of positioning.

Method used

Using the rescue positioning data fusion analysis method based on timing update, the rescue positioning module is built by integrating satellite positioning system, UWB positioning device, wireless signal base station and lidar, data preprocessing, critical evaluation and multi-sensor fusion, monitoring and analysis of rescue The current timing motion change parameters of the target are constructed, and the target dynamic trend impact matrix is ​​carried out to perform positioning dynamic analysis to obtain real-time three-dimensional positioning data.

Benefits of technology

High-precision real-time three-dimensional positioning of rescue targets is achieved, real-time and accuracy of positioning are improved, and can dynamically adapt to changes in rescue targets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118584523B_ABST
    Figure CN118584523B_ABST
Patent Text Reader

Abstract

The present invention discloses a rescue positioning data fusion analysis method and system based on time series update, which relates to data processing related fields. The method includes: obtaining multiple three-dimensional positioning data sets of rescue targets; performing mapping preprocessing and time series arrangement integration on multiple three-dimensional positioning data sets; performing critical evaluation on multiple standard time series positioning data sets, obtaining multiple data critical factors, performing multi-sensor fusion, and collecting three-dimensional positioning fusion data of rescue targets; obtaining current time series motion change parameters, performing dynamic impact analysis on the three-dimensional positioning fusion data of rescue targets, and obtaining the target dynamic trend impact matrix; performing positioning dynamic analysis, and obtaining real-time three-dimensional positioning data of targets. The method solves the technical problem that it is difficult to adapt to the dynamic changes of rescue targets in real time in the existing rescue positioning data analysis, resulting in insufficient real-time and accuracy of positioning, and achieves the technical effect of real-time adaptation to the dynamic changes of rescue targets and improving the real-time and accuracy of positioning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a rescue positioning data fusion analysis method and system based on time series updating. Background Art

[0002] In emergency rescue scenarios, accurately locating the position of the rescue target is the key to rapid response and effective execution of rescue operations. With the continuous advancement of technology, a variety of positioning technologies have been widely used in the field of rescue positioning. At present, rescue positioning mostly only focuses on the static analysis of positioning data. However, the rescue target may experience dynamic changes such as rapid movement and direction change during the rescue process. The existing methods ignore the dynamic impact of the rescue target's motion state on the positioning results, resulting in poor real-time and accuracy of positioning.

[0003] In the current relevant technologies, rescue positioning data analysis has the technical problem of being difficult to adapt to the dynamic changes of rescue targets in real time, resulting in insufficient real-time and accuracy of positioning. Summary of the invention

[0004] The present application provides a rescue positioning data fusion analysis method and system based on time series updates, constructs a rescue positioning module by integrating multiple positioning technologies, ensures data standardization and consistency through data preprocessing, critical evaluation and data fusion, performs dynamic impact analysis on three-dimensional positioning fusion data through the current time series motion change parameters of the rescue target, and performs positioning dynamic analysis on the rescue target based on the three-dimensional positioning fusion data of the rescue target, the current time series motion change parameters and the target dynamic trend impact matrix, and other technical means to obtain high-precision real-time three-dimensional positioning data of the target, thereby achieving the technical effect of real-time adaptation to the dynamic changes of the rescue target and improving the real-time and accuracy of positioning.

[0005] This application provides a rescue positioning data fusion analysis method based on time series update, including:

[0006] A rescue positioning module is obtained, wherein the rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar, and multiple three-dimensional positioning data sets of the rescue target are collected through the rescue positioning module; a data processing multi-channel is constructed according to the rescue positioning module, and the multiple three-dimensional positioning data sets are mapped preprocessed and time-series arranged and integrated through the data processing multi-channel to obtain multiple standard time-series positioning data sets; a critical evaluation is performed on the multiple standard time-series positioning data sets to obtain multiple data critical factors, and the multiple standard time-series positioning data sets are multi-sensor fused based on the multiple data critical factors to collect three-dimensional positioning fusion data of the rescue target; the current time-series motion change parameters of the rescue target are monitored and obtained, and the three-dimensional positioning fusion data of the rescue target are dynamically analyzed based on the current time-series motion change parameters to obtain the target dynamic trend influence matrix; the positioning dynamic analysis of the rescue target is performed based on the three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend influence matrix to obtain the real-time three-dimensional positioning data of the target.

[0007] In a possible implementation, the construction data processing multiple channels performs the following processing:

[0008] The rescue positioning module is subjected to data source extraction to obtain multiple data source characteristic information, and the multiple data source characteristic information is structured and classified to obtain a data structured type; based on the data structured type, the multiple data source characteristic information is subjected to preprocessing program analysis to obtain multiple data preprocessing programs; the multiple data source characteristic information is subjected to timing standardization analysis and timing data filling to obtain multiple data timing filling programs; the multiple data preprocessing programs and the multiple data timing filling programs are channel mapped and configured to construct the data processing multi-channel.

[0009] In a possible implementation, the obtaining of multiple data timing filling programs performs the following processing:

[0010] Timestamps are extracted respectively for the characteristic information of the multiple data sources to obtain timestamp information of multiple data source collections; collection time period analysis is performed based on the timestamp information of the multiple data source collections to obtain multiple data source collection time periods; timing standardization is performed on the multiple data source collection time periods to determine the data collection timing standard; timing data filling and analysis is performed on the characteristic information of the multiple data sources based on the data collection timing standard to obtain the multiple data timing filling programs.

[0011] In a possible implementation, the obtaining of multiple data criticality factors includes performing the following processing:

[0012] Acquire data fusion strategy factor information, wherein the data fusion strategy factor information includes data accuracy, acquisition stability, acquisition real-time and scenario demand orientation; evaluate the multiple standard time series positioning data sets based on the data fusion strategy factor information to obtain multiple data fusion factor evaluation parameter sets; assign priorities to each strategy factor in the data fusion strategy factor information to obtain strategy factor priority coefficients; perform weighted fusion on the multiple data fusion factor evaluation parameter sets based on the strategy factor priority coefficients to obtain the multiple data criticality factors.

[0013] In a possible implementation, the target dynamic trend influence matrix is ​​obtained by performing the following processing:

[0014] Perform motion characteristic analysis on the three-dimensional positioning fusion data of the rescue target to obtain target motion characteristic information, wherein the target motion characteristic information includes motion trajectory, speed trend and motion direction pattern; based on the target motion characteristic information, train a target motion state prediction model, wherein the target motion state prediction model includes a motion trajectory prediction model, a speed trend prediction model and a motion direction pattern prediction model; perform offset dynamic update on the target motion state prediction model based on the current time series motion change parameters to obtain the target dynamic trend influence matrix.

[0015] In a possible implementation, the real-time three-dimensional positioning data of the target is obtained by performing the following processing:

[0016] Based on the target motion state prediction model, a target state transfer matrix is ​​determined; and a target three-dimensional positioning dynamic model is constructed. The target three-dimensional positioning dynamic model is specifically: is the three-dimensional positioning coordinate of the rescue target at time t, F is the target state transfer matrix, It is the three-dimensional positioning fusion data of the rescue target The three-dimensional positioning coordinates at the moment, B is the target dynamic trend influence matrix, is the current temporal motion change parameter, To measure the disturbance error; based on the target three-dimensional positioning dynamic model, the positioning data of the rescue target is calculated and updated to obtain the real-time three-dimensional positioning data of the target.

[0017] In a possible implementation, the following processing is performed:

[0018] The rescue positioning module is used to perform positioning data monitoring and multi-sensor fusion to obtain current time-series three-dimensional positioning fusion data; based on the deviation between the target real-time three-dimensional positioning data and the current time-series three-dimensional positioning fusion data, a particle swarm optimization direction is determined; the target three-dimensional positioning dynamic model is evaluated and iteratively updated according to the particle swarm optimization direction until a preset termination condition is met, and the particle with the largest fitness is determined by optimization as a model parameter solution; based on the model parameter solution, the target three-dimensional positioning dynamic model is parameter updated and configured to obtain a target three-dimensional positioning dynamic optimization model.

[0019] The present application also provides a rescue positioning data fusion analysis system based on time series update, including:

[0020] Multiple three-dimensional positioning data set acquisition modules, the multiple three-dimensional positioning data set acquisition modules are used to acquire a rescue positioning module, the rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar, and collects and acquires multiple three-dimensional positioning data sets of the rescue target through the rescue positioning module; multiple standard time series positioning data set acquisition modules, the multiple standard time series positioning data set acquisition modules are used to construct a data processing multi-channel according to the rescue positioning module, and the multiple three-dimensional positioning data sets are mapped preprocessed and time-series arranged and integrated through the data processing multi-channel to acquire multiple standard time series positioning data sets; rescue target three-dimensional positioning fusion data acquisition module, the rescue target three-dimensional positioning fusion data acquisition module is used to perform critical evaluation on the multiple standard time series positioning data sets, Acquire multiple data criticality factors, perform multi-sensor fusion on the multiple standard time-series positioning data sets based on the multiple data criticality factors, and collect three-dimensional positioning fusion data of the rescue target; a target dynamic trend influence matrix acquisition module, the target dynamic trend influence matrix acquisition module is used to monitor and acquire the current time-series motion change parameters of the rescue target, and perform dynamic impact analysis on the three-dimensional positioning fusion data of the rescue target based on the current time-series motion change parameters to obtain the target dynamic trend influence matrix; a target real-time three-dimensional positioning data acquisition module, the target real-time three-dimensional positioning data acquisition module is used to perform positioning dynamic analysis on the rescue target based on the three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend influence matrix to obtain the target real-time three-dimensional positioning data.

[0021] The rescue positioning data fusion analysis method and system based on time series update proposed in this application are proposed. First, a rescue positioning module is obtained. The rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar. Multiple three-dimensional positioning data sets of the rescue target are collected and obtained through the rescue positioning module. Then, according to the rescue positioning module, a data processing multi-channel is constructed. The multiple three-dimensional positioning data sets are mapped and pre-processed and time-series arranged and integrated through the data processing multi-channel to obtain multiple standard time series positioning data sets. Then, a critical evaluation is performed on the multiple standard time series positioning data sets to obtain multiple data critical factors. Based on the multiple data critical factors, multi-sensor fusion is performed on the multiple standard time series positioning data sets to collect the three-dimensional positioning fusion data of the rescue target. Then, the current time series motion change parameters of the rescue target are monitored and obtained, and the three-dimensional positioning fusion data of the rescue target is dynamically analyzed based on the current time series motion change parameters to obtain the target dynamic trend influence matrix. Finally, the rescue target is positioned dynamically based on the three-dimensional positioning fusion data of the rescue target, the current time series motion change parameters and the target dynamic trend influence matrix to obtain the real-time three-dimensional positioning data of the target, so as to achieve the technical effect of real-time adaptation to the dynamic changes of the rescue target and improving the real-time and accuracy of positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A flowchart of a rescue positioning data fusion analysis method based on time series updating provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of a rescue positioning data fusion and analysis system based on time series updating provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: multiple three-dimensional positioning data set acquisition module 10, multiple standard time series positioning data set acquisition module 20, rescue target three-dimensional positioning fusion data acquisition module 30, target dynamic trend influence matrix acquisition module 40, target real-time three-dimensional positioning data acquisition module 50. DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The embodiment of the present application provides a rescue positioning data fusion analysis method based on time series update, such as Figure 1 As shown, the method includes:

[0030] Step S100, obtaining a rescue positioning module, the rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar, and collects and obtains multiple three-dimensional positioning data sets of the rescue target through the rescue positioning module. Specifically, a satellite positioning system (such as GPS, Beidou, etc.), a UWB (ultra-wideband) positioning device, a wireless signal base station (such as Wi-Fi, Bluetooth, etc.) and a laser radar are selected and integrated as the core components of the rescue positioning module. Among them, the satellite positioning system is a system that uses satellite signals to locate the geographic location, and determines the position of the receiver by receiving signals from multiple satellites and calculating their propagation time difference; the UWB positioning device is a positioning device based on ultra-wideband technology, which measures the distance by transmitting and receiving nanosecond or shorter pulse signals to achieve high-precision positioning; the wireless signal base station is a facility for transmitting and receiving wireless signals, and assists in positioning by measuring parameters such as signal propagation time and signal strength; the laser radar is a sensor that uses laser beams for scanning and ranging, which can generate a high-precision three-dimensional environment model and provide environmental data support for positioning. Physically connect and integrate all the above components with software to ensure smooth communication and data exchange between components. Perform system tests, including functional tests, performance tests, and stability tests, to ensure that the rescue positioning module can work normally and meet the positioning accuracy requirements. Configure data acquisition parameters, such as sampling frequency, positioning accuracy, data transmission protocol, etc., and set the trigger conditions for data acquisition, such as timed acquisition, event-triggered acquisition, etc. Start the rescue positioning module, collect the three-dimensional positioning data of the rescue target in real time, and store the collected three-dimensional positioning data in chronological order to form multiple three-dimensional positioning data sets, which are composed of position data at multiple time points.

[0031] Step S200, according to the rescue positioning module, a data processing multi-channel is constructed, and the mapping preprocessing and time-series arrangement integration of the multiple three-dimensional positioning data sets are performed through the data processing multi-channel to obtain multiple standard time-series positioning data sets. Specifically, the data format, sampling frequency, accuracy and other characteristics of the three-dimensional positioning data obtained from the rescue positioning module (including satellite positioning system, UWB positioning device, wireless signal base station, laser radar) are clarified. An independent data processing channel is allocated to each data source to realize parallel processing and separate processing. These data processing channels are used to receive, parse and preliminarily process data from the corresponding data source. Since different positioning technologies use different coordinate systems (such as WGS-84, UTM, etc.), all three-dimensional positioning data are unified into the same coordinate system through coordinate conversion and calibration, and noise, outliers or duplicate points in the data are removed to improve the accuracy and reliability of the data. For data sources with missing data, interpolation methods such as linear interpolation and Lagrange interpolation are used to fill in the missing data points. According to the timestamp information provided by each data source, all three-dimensional positioning data are arranged in chronological order to ensure the consistency of each data set in the time dimension. The data after mapping preprocessing are integrated into multiple standard time series positioning data sets in chronological order. Each standard time series positioning data set contains data from different positioning technologies, but is synchronized in time.

[0032] In a possible implementation, the data processing multi-channel is constructed, and step S200 further includes step S210, extracting the data source of the rescue positioning module, obtaining multiple data source characteristic information, and structurally classifying the multiple data source characteristic information to obtain data structured types. Specifically, all available data sources in the rescue positioning module are identified, including satellite positioning systems, UWB positioning devices, wireless signal base stations, and laser radars. For each data source, its characteristic information is collected, such as the source of the data positioning device, the data structured type (such as text, numerical value, image, etc.), the data collection time, the collection quantity, etc. According to the collected characteristic information, the data source is structurally classified to obtain the data structured type, that is, the organizational form or format of the data, such as numerical type, text type, image type, etc. The data structured type determines the data processing method and the operations that can be performed. Step S220, based on the data structured type, the multiple data source characteristic information is analyzed by preprocessing procedures to obtain multiple data preprocessing procedures. Specifically, based on the data structured type, the preprocessing steps required for each type of data are analyzed, wherein the preprocessing is used to perform a series of operations on the data before data analysis or modeling to improve data quality, reduce noise, unify the format, etc. Design a corresponding preprocessing program for each data type. For example, for numerical data, denoising, normalization, etc. are required; for image data, image enhancement, feature extraction, etc. are required. Step S230, the multiple data source characteristic information is subjected to time series standardization analysis and time series data filling to obtain multiple data time series filling programs. Specifically, the timestamp and data frequency of each data source are analyzed so that all data sources can be aligned with each other in time or find a suitable time mapping relationship. For data sources with inconsistent timestamps or different data frequencies, time conversion rules or sampling strategies are designed to uniformly process time series data. According to the data source characteristic information, especially the information related to data integrity and missing mode, the severity of data missing in each data source, the missing mode (such as random missing, periodic missing, etc.) and the impact of missing data on the overall data analysis are evaluated. Based on the results of the data source characteristic assessment, determine the appropriate time series data filling method for each data source, which may include statistical filling methods (such as mean filling, median filling, mode filling), model-based prediction methods (such as linear regression, time series model prediction) or neighbor value-based interpolation methods (such as linear interpolation, polynomial interpolation), etc. Design corresponding programs or scripts for each data filling method, which are used as part of the subsequent data processing flow to fill the actual data.

[0033] Step S240, channel mapping configuration is performed on the multiple data preprocessing programs and the multiple data timing filling programs to construct the data processing multi-channel. Specifically, according to the source of each data positioning device in the rescue positioning module, a corresponding data processing channel is designed, and each data processing channel is responsible for processing data from a type of data source. The data preprocessing program obtained in step S220 and the data timing filling program obtained in step S230 are matched and mapped with each data processing channel, so that each data processing channel can process the data according to a predetermined program. All configured data processing channels are integrated together to form a data processing multi-channel system. This implementation method modularly designs data preprocessing programs and data timing filling programs based on data source characteristic information, and configures them according to the needs of each data processing channel, which reduces the complexity and coupling of the system. These programs can be flexibly combined and configured according to the needs of different data processing channels, achieving the technical effect of increasing the flexibility and adaptability of the system.

[0034] In a possible implementation, the procedure for obtaining multiple data time series filling is further comprised of step S230, which extracts timestamps from the characteristic information of the multiple data sources respectively to obtain timestamp information for the collection of multiple data sources. Specifically, all data sources are traversed to obtain data records in each data source, and timestamp information is extracted from each data record, that is, fields or attributes representing the data record time are extracted, and the extracted timestamp information is sorted into an ordered set. Step S232, based on the timestamp information collected from the multiple data sources, a collection time period analysis is performed to obtain multiple data source collection time periods. Specifically, based on the sorted timestamp set, the collection interval of each data source (that is, the time difference between two consecutive records) is calculated, and based on the collection interval, the collection time period mode of each data source is determined, such as once per minute or once per second. Step S233, the time series standardization selection is performed on the collection time periods of the multiple data sources to determine the data collection time series standard. Specifically, the collection time periods of all data sources are compared to find the minimum collection interval, and the minimum collection interval is used as the data collection timing standard, that is, the time series of data collected by all data sources are unified to a common collection standard for subsequent data processing and fusion. Step S234, based on the data collection timing standard, the time series data filling and parsing of the characteristic information of the multiple data sources are performed to obtain the multiple data time series filling programs. Specifically, based on the data collection timing standard, a time series data filling strategy is designed for each data source, including statistical filling (such as mean and median filling), model-based prediction filling (such as time series model, machine learning model), etc. According to the designed filling strategy, a corresponding data filling program is written to generate a filling value. This implementation method compares the collection time periods of different data sources and selects the minimum collection interval as the data collection timing standard. Since high-frequency data collection can more accurately reflect the changes in the actual situation, high-frequency data is used as the standard for filling, so that low-frequency data is closer to the actual situation in time, thereby achieving the technical effect of improving the precision and accuracy of the data.

[0035] Step S300, perform critical evaluation on the multiple standard time series positioning data sets, obtain multiple data critical factors, perform multi-sensor fusion on the multiple standard time series positioning data sets based on the multiple data critical factors, and collect three-dimensional positioning fusion data of the rescue target. Specifically, according to the characteristics of each positioning technology (such as accuracy, stability, coverage, etc.) and the characteristics of the current rescue environment, determine the evaluation criteria for data criticality. The data criticality refers to the importance and contribution of a certain data source or data set to the overall fusion result during the data fusion process. Data sources with high criticality have higher accuracy, stability and reliability. For each standard time series positioning data set, calculate its data criticality factor according to the evaluation criteria. The criticality factor is an indicator or parameter used to quantify the criticality of the data, which is evaluated and calculated based on multiple aspects of the data (such as accuracy, stability, coverage, etc.). According to the calculated data criticality factors, the standard time series positioning data sets are sorted, and according to the characteristics of each standard time series positioning data set (such as data distribution, noise level, time synchronization, etc.), the fusion algorithm is determined, such as weighted average method, Kalman filter, particle filter, Bayesian network, etc. According to the fusion algorithm, the corresponding parameters are configured, such as weight coefficient, filter parameter, number of iterations, etc. The standard time series positioning data set is used as input and input into the fusion algorithm. According to the configuration of the algorithm and the input data, the fusion algorithm is executed. The algorithm integrates the information of each data source to generate fused three-dimensional positioning data, that is, the rescue target three-dimensional positioning fusion data. The rescue target three-dimensional positioning fusion data has higher accuracy and reliability, and can more accurately reflect the location information of the rescue target.

[0036] In a possible implementation, the step of obtaining multiple data critical factors, step S300 further includes step S310, obtaining data fusion strategy factor information, the data fusion strategy factor information includes data accuracy, acquisition stability, acquisition real-time and scenario demand orientation. Specifically, information about data accuracy, acquisition stability, acquisition real-time and scenario demand orientation is collected from multiple channels such as data source, system configuration, user demand, etc., and each strategy factor is analyzed to determine its specific impact on data fusion quality. Among them, data accuracy refers to the accuracy and reliability of data, reflecting the quality of data; acquisition stability refers to the stability and continuity during the data acquisition process, reflecting the reliability of the data acquisition system and the stability of the data source; acquisition real-time refers to the time delay from data generation to data acquisition and processing, which is particularly important for scenarios that require rapid response; scenario demand orientation refers to analyzing the importance of different data types according to the needs of specific application scenarios. For example, in some application scenarios, certain specific types of data are more important than other types of data and should be given higher weights. Step S320, based on the data fusion strategy factor information, the multiple standard time series positioning data sets are evaluated to obtain multiple data fusion factor evaluation parameter sets. Specifically, according to the collected data fusion strategy factor information, an evaluation standard and index for each strategy factor are formulated, each standard time series positioning data set is evaluated according to the evaluation standard, the evaluation results are recorded, and the evaluation results are summarized into multiple data fusion factor evaluation parameter sets, each parameter set contains the evaluation values ​​of multiple strategy factors. Step S330, assigning priority to each strategy factor in the data fusion strategy factor information, and obtaining the strategy factor priority coefficient. Specifically, according to the specific requirements of the application scenario and the importance of each strategy factor, the priority of each strategy factor is analyzed and determined, and a priority coefficient is assigned to each strategy factor, and the size of the coefficient reflects the relative importance of the strategy factor in the data fusion strategy. Step S340, based on the strategy factor priority coefficient, the multiple data fusion factor evaluation parameter sets are weighted and fused to obtain the multiple data criticality factors. Specifically, the strategy factor priority coefficient is used as a weight to perform weighted calculation on multiple data fusion factor evaluation parameter sets, and according to the result of the weighted calculation, the criticality of each standard time series positioning data set is comprehensively evaluated, and multiple data criticality factors are obtained. This implementation method comprehensively analyzes multiple key factors in the data fusion strategy, ensures that the evaluation results of data criticality factors are more comprehensive, and achieves the technical effect of improving the accuracy and scientificity of data criticality factor evaluation.

[0037] Step S400, monitor and obtain the current time-series motion change parameters of the rescue target, and perform dynamic impact analysis on the three-dimensional positioning fusion data of the rescue target based on the current time-series motion change parameters to obtain the target dynamic trend impact matrix. Specifically, use sensors (such as accelerometers, gyroscopes, speed sensors, etc.) installed at the rescue site or the rescue target to monitor the motion state of the rescue target in real time, extract key motion change parameters, such as speed change (including linear speed and angular velocity), steering angle change, acceleration, etc., and record these parameters in chronological order to form the current time-series motion change data set of the rescue target. Clean the monitored motion change data to remove noise and outliers to ensure the accuracy and reliability of the data. Analyze how the motion change of the rescue target affects the accuracy and reliability of its three-dimensional positioning fusion data. Specifically, analyze the impact of speed change on positioning accuracy, such as satellite positioning will produce large errors when moving at high speed; analyze the impact of steering angle change on positioning direction. In complex environments, steering will cause sudden changes in positioning direction. Use statistical or machine learning methods to quantify these impacts and generate impact factors or impact weights. According to the results of dynamic impact analysis, a matrix is ​​constructed to represent the dynamic trend impact of the rescue target motion change on its 3D positioning fusion data. For example, the rows of the matrix can represent different motion change parameters (such as speed change, steering angle change, etc.), and the columns can represent different dimensions of 3D positioning data (such as X, Y, Z coordinates). The elements in the matrix represent the degree of influence of the corresponding motion change parameters on the 3D positioning data dimensions, which can be specific values ​​(such as impact weights) or probability distributions. Use historical data or simulation data to verify the constructed target dynamic trend impact matrix to ensure its accuracy and reliability.

[0038] In a possible implementation, the target dynamic trend influence matrix is ​​obtained, and step S400 further includes step S410, performing motion characteristic analysis on the three-dimensional positioning fusion data of the rescue target to obtain target motion characteristic information, and the target motion characteristic information includes motion trajectory, speed trend and motion direction mode. Specifically, key motion features such as position coordinates (x, y, z), timestamp, etc. are extracted from the three-dimensional positioning fusion data of the rescue target, and the motion trajectory of the rescue target is constructed using the extracted position coordinates and timestamp information. The velocity vector of the rescue target is obtained by calculating the change in the position coordinates of adjacent time points and combining the time interval, and the speed trend (such as acceleration, deceleration, and uniform speed) is further analyzed; the steering angle and frequency of the rescue target motion trajectory are analyzed to identify the motion direction mode of the rescue target (such as linear motion, curved motion, periodic round trip, etc.). Step S420, based on the target motion characteristic information, a target motion state prediction model is trained and obtained, and the target motion state prediction model includes a motion trajectory prediction model, a speed trend prediction model, and a motion direction mode prediction model. Specifically, the target motion characteristic information data set is divided into a training set and a test set. According to the characteristics of the target motion characteristic information, a machine learning or deep learning model is selected, such as a time series prediction model (ARIMA, LSTM, etc.) for trajectory and speed prediction, and a classification model (decision tree, random forest, etc.) for direction pattern prediction. The model is trained using the training set data, the model parameters are adjusted to optimize the prediction performance, and the prediction accuracy and generalization ability of the model are evaluated using the test set data to ensure the effectiveness and reliability of the model. The trained target motion state prediction model is used to predict the future motion state of the rescue target, including motion trajectory, speed trend, and motion direction pattern. Step S430, the target motion state prediction model is dynamically updated based on the current time series motion change parameters to obtain the target dynamic trend influence matrix. Specifically, according to the current time-series motion change parameters, the target motion state prediction model is dynamically adjusted to reflect the impact of the motion change of the rescue target on the motion state. The updated model is used for prediction to obtain the positioning state offset parameters of the rescue target at a certain moment in the future. The predicted positioning state offset parameters are organized into a matrix form, namely the target dynamic trend influence matrix, which reflects the positioning offset of the rescue target under different conditions. This implementation method extracts useful information to train the target motion state prediction model by analyzing the motion characteristics of the three-dimensional positioning fusion data of the rescue target. According to the target motion state prediction model and the current time-series motion change parameters, the three-dimensional positioning fusion data of the rescue target is dynamically analyzed, so that the target dynamic trend influence matrix can reflect the latest dynamics and change trends of the rescue target in real time, achieving the technical effect of improving the accuracy and practicality of the target dynamic trend influence matrix.

[0039] Step S500, based on the three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend influence matrix, the rescue target is dynamically analyzed for positioning, and the target real-time three-dimensional positioning data is obtained. Specifically, according to the motion characteristics of the rescue target and the characteristics of the positioning data, a dynamic model (which can be based on physical principles or statistical learning models) is constructed, and this dynamic model can reflect the motion state and positioning accuracy of the rescue target that change over time. The three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend influence matrix are used as input data and input into the dynamic model, and a dynamic analysis process is performed to analyze the impact of the current motion state (such as speed, acceleration, steering angle, etc.) of the rescue target on the positioning data, and how these impacts change over time, and the target dynamic trend influence matrix is ​​used to adjust and optimize the dynamic model to more accurately reflect the actual motion trajectory and position of the rescue target. On the basis of dynamic analysis, the real-time three-dimensional positioning data of the rescue target is calculated, and the target real-time three-dimensional positioning data accurately reflects the position and posture of the rescue target at the current moment, and is used to provide accurate positioning support for the rescue operation. The embodiment of the present application adopts the integration of multiple positioning technologies to construct a rescue positioning module, ensures data standardization and consistency through data preprocessing, critical evaluation and data fusion, performs dynamic impact analysis on the three-dimensional positioning fusion data through the current time-series motion change parameters of the rescue target, and performs positioning dynamic analysis on the rescue target based on the three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend impact matrix. The high-precision real-time three-dimensional positioning data of the target is obtained, and the technical effect of real-time adaptation to the dynamic changes of the rescue target and improving the real-time and accuracy of positioning is achieved.

[0040] In a possible implementation, the real-time three-dimensional positioning data of the target is obtained, and step S500 further includes step S510, determining the target state transfer matrix based on the target motion state prediction model. Specifically, according to the motion characteristics of the rescue target, a state space is defined, including state variables such as position, velocity, and acceleration. The output result of the target motion state prediction model is used to construct a state transfer equation. The state transfer equation describes how the state of the rescue target transfers from the current state to the next state over time. According to the state transfer equation, combined with the motion characteristics of the rescue target and the prediction results, the target state transfer matrix is ​​calculated. The target state transfer matrix is ​​a mathematical matrix used to describe how the state of the rescue target (such as position, velocity, acceleration, etc.) transfers from one state to another over time. Step S520, construct a target three-dimensional positioning dynamic model, and the target three-dimensional positioning dynamic model is specifically: is the three-dimensional positioning coordinate of the rescue target at time t, F is the target state transfer matrix, It is the three-dimensional positioning fusion data of the rescue target The three-dimensional positioning coordinates at the moment, B is the target dynamic trend influence matrix, is the current temporal motion change parameter, The invention relates to a measurement disturbance error. Specifically, according to the modeling principle of dynamic systems, the framework of the target three-dimensional positioning dynamic model is set. The target three-dimensional positioning dynamic model includes the current three-dimensional positioning coordinates of the rescue target, the target state transfer matrix, the target dynamic trend influence matrix, the current time series motion change parameters and the measurement disturbance error elements. The mathematical equation of the target three-dimensional positioning dynamic model reflects the real-time positioning of the rescue target in a dynamic environment, and at the same time integrates the changes in the motion state of the rescue target, the influence of environmental factors and the interference of measurement errors. Step S530, based on the target three-dimensional positioning dynamic model, the positioning data of the rescue target is calculated and updated to obtain the real-time three-dimensional positioning data of the target. Specifically, the current time series motion change parameters are substituted as input data into the target three-dimensional positioning dynamic model for mathematical operation. During the operation, the model integrates the changes in the motion state of the rescue target, the influence of environmental factors and the interference of measurement errors to obtain more accurate target three-dimensional positioning information and update the real-time three-dimensional positioning data of the rescue target for rescue action decision-making and command. This implementation method builds a dynamic model of target three-dimensional positioning, comprehensively considers the changes in the motion state of the rescue target, the influence of environmental factors, and the interference of measurement errors, and achieves the technical effect of improving the accuracy and reliability of real-time three-dimensional positioning of the rescue target.

[0041] In a possible implementation, step S520 further includes step S521, performing positioning data monitoring and multi-sensor fusion through the rescue positioning module to obtain current time series three-dimensional positioning fusion data. Specifically, the latest current time series three-dimensional positioning fusion data is obtained by the same method as steps S100-S300. Step S522, based on the deviation between the target real-time three-dimensional positioning data and the current time series three-dimensional positioning fusion data, determine the particle swarm optimization direction. Specifically, by comparing the coordinate values, the deviation between the target real-time three-dimensional positioning data and the current time series three-dimensional positioning fusion data is calculated, and the search direction of the particle swarm optimization is determined according to the size and direction of the deviation. Step S523, the target three-dimensional positioning dynamic model is evaluated and iteratively updated according to the particle swarm optimization direction until the preset termination condition is met, and the particle with the largest fitness is determined as the model parameter solution. Specifically, a certain number of particles are randomly generated, each particle represents a set of possible parameters of the target three-dimensional positioning dynamic model, and the fitness of each particle is calculated according to the objective function (which can be a comprehensive evaluation of indicators such as positioning accuracy and stability). According to the particle swarm optimization algorithm, the speed and position of each particle are updated to move it to a region with higher fitness. The above steps are repeated until the preset termination conditions (such as reaching the maximum number of iterations, the fitness improvement is less than the threshold, etc.) are met. After the iteration is completed, the particle with the largest fitness is selected as the optimal solution of the model parameters. Step S524, based on the model parameter solution, the parameter update configuration of the target three-dimensional positioning dynamic model is performed to obtain the target three-dimensional positioning dynamic optimization model. Specifically, the obtained optimal solution (i.e., the optimal value of the model parameter) is configured into the target three-dimensional positioning dynamic model, and the updated model is verified using a new data set to ensure its effectiveness and accuracy in practical applications. If the verification result meets expectations, the target three-dimensional positioning dynamic optimization model is output for subsequent rescue operations. This implementation method can timely discover and correct positioning deviations by iteratively updating and optimizing the target three-dimensional positioning dynamic model, thereby achieving the technical effect of improving the real-time and accuracy of positioning.

[0042] In the above, refer to Figure 1 The rescue positioning data fusion analysis method based on time series update according to an embodiment of the present invention is described in detail. Figure 2 A rescue positioning data fusion and analysis system based on time series updating according to an embodiment of the present invention is described.

[0043] The rescue positioning data fusion analysis system based on time series update according to the embodiment of the present invention is used to solve the technical problem that it is difficult to adapt to the dynamic changes of the rescue target in real time in the existing rescue positioning data analysis, resulting in insufficient real-time and accuracy of positioning, so as to achieve the technical effect of adapting to the dynamic changes of the rescue target in real time and improving the real-time and accuracy of positioning. The rescue positioning data fusion analysis system based on time series update includes: multiple three-dimensional positioning data set acquisition modules 10, multiple standard time series positioning data set acquisition modules 20, rescue target three-dimensional positioning fusion data acquisition module 30, target dynamic trend influence matrix acquisition module 40, and target real-time three-dimensional positioning data acquisition module 50.

[0044] The multiple three-dimensional positioning data set acquisition module 10 is used to acquire the rescue positioning module, which integrates the satellite positioning system, the UWB positioning device, the wireless signal base station and the laser radar, and acquires multiple three-dimensional positioning data sets of the rescue target through the rescue positioning module; the multiple standard time series positioning data set acquisition module 20 is used to construct a data processing multi-channel according to the rescue positioning module, and perform mapping preprocessing and time series arrangement integration on the multiple three-dimensional positioning data sets through the data processing multi-channel to acquire multiple standard time series positioning data sets; the rescue target three-dimensional positioning fusion data acquisition module 30 is used to perform critical evaluation on the multiple standard time series positioning data sets to acquire multiple data critical The target dynamic trend influence matrix acquisition module 40 is used to monitor and obtain the current time series motion change parameters of the rescue target, and perform dynamic impact analysis on the three-dimensional positioning fusion data of the rescue target based on the current time series motion change parameters to obtain the target dynamic trend influence matrix; the target real-time three-dimensional positioning data acquisition module 50 is used to perform positioning dynamic analysis on the rescue target based on the three-dimensional positioning fusion data of the rescue target, the current time series motion change parameters and the target dynamic trend influence matrix to obtain the target real-time three-dimensional positioning data.

[0045] The specific configuration of the multiple standard time series positioning data set acquisition module 20 will be described in detail below. As described above, to construct a data processing multi-channel, the multiple standard time series positioning data set acquisition module 20 may further include: a data structured type acquisition unit for extracting the data source of the rescue positioning module, obtaining multiple data source characteristic information, and performing structured classification on the multiple data source characteristic information to obtain a data structured type; multiple data preprocessing program acquisition units for performing preprocessing program analysis on the multiple data source characteristic information based on the data structured type to obtain multiple data preprocessing programs; multiple data timing filling program acquisition units for performing timing standardization analysis and timing data filling on the multiple data source characteristic information to obtain multiple data timing filling programs; a channel mapping configuration unit for channel mapping configuration of the multiple data preprocessing programs and the multiple data timing filling programs to construct the data processing multi-channel.

[0046] Among them, the obtaining of multiple data timing filling programs, the multiple data timing filling program acquisition unit may further include: a timestamp extraction subunit for respectively extracting timestamps from the multiple data source characteristic information to obtain multiple data source collection timestamp information; a collection time period analysis subunit for performing collection time period analysis based on the multiple data source collection timestamp information to obtain multiple data source collection time periods; a timing standardization selection subunit for performing timing standardization selection on the multiple data source collection time periods to determine the data collection timing standard; a timing data filling analysis subunit for performing timing data filling analysis on the multiple data source characteristic information based on the data collection timing standard to obtain the multiple data timing filling programs.

[0047] The specific configuration of the rescue target three-dimensional positioning fusion data acquisition module 30 will be described in detail below. As described above, multiple data criticality factors are acquired, and the rescue target three-dimensional positioning fusion data acquisition module 30 can further include: a data fusion strategy factor information acquisition unit is used to acquire data fusion strategy factor information, and the data fusion strategy factor information includes data accuracy, acquisition stability, acquisition real-time and scene demand orientation; an evaluation unit is used to evaluate the multiple standard time series positioning data sets based on the data fusion strategy factor information to obtain multiple data fusion factor evaluation parameter sets; a priority assignment unit is used to assign priorities to each strategy factor in the data fusion strategy factor information to obtain a strategy factor priority coefficient; a weighted fusion unit is used to weightedly fuse the multiple data fusion factor evaluation parameter sets based on the strategy factor priority coefficient to obtain the multiple data criticality factors.

[0048] The specific configuration of the target dynamic trend influence matrix acquisition module 40 will be described in detail below. As described above, the target dynamic trend influence matrix is ​​obtained, and the target dynamic trend influence matrix acquisition module 40 may further include: a motion characteristic analysis unit is used to perform motion characteristic analysis on the three-dimensional positioning fusion data of the rescue target, and obtain target motion characteristic information, and the target motion characteristic information includes motion trajectory, speed trend and motion direction mode; a target motion state prediction model training unit is used to train and obtain a target motion state prediction model based on the target motion characteristic information, and the target motion state prediction model includes a motion trajectory prediction model, a speed trend prediction model and a motion direction mode prediction model; an offset dynamic update unit is used to perform an offset dynamic update on the target motion state prediction model based on the current temporal motion change parameter, and obtain the target dynamic trend influence matrix.

[0049] The specific configuration of the target real-time three-dimensional positioning data acquisition module 50 will be described in detail below. As described above, the target real-time three-dimensional positioning data is obtained, and the target real-time three-dimensional positioning data acquisition module 50 may further include: a target state transfer matrix determination unit is used to determine the target state transfer matrix based on the target motion state prediction model; a target three-dimensional positioning dynamic model construction unit is used to construct a target three-dimensional positioning dynamic model, and the target three-dimensional positioning dynamic model is specifically: is the three-dimensional positioning coordinate of the rescue target at time t, F is the target state transfer matrix, It is the three-dimensional positioning fusion data of the rescue target The three-dimensional positioning coordinates at the moment, B is the target dynamic trend influence matrix, is the current temporal motion change parameter, To measure the disturbance error; the positioning data calculation and updating unit is used to calculate and update the positioning data of the rescue target based on the target three-dimensional positioning dynamic model to obtain real-time three-dimensional positioning data of the target.

[0050] Among them, the target three-dimensional positioning dynamic model construction unit can further include: a current time series three-dimensional positioning fusion data acquisition subunit is used to perform positioning data monitoring and multi-sensor fusion through the rescue positioning module to obtain current time series three-dimensional positioning fusion data; a particle swarm optimization direction determination subunit is used to determine the particle swarm optimization direction based on the deviation between the target real-time three-dimensional positioning data and the current time series three-dimensional positioning fusion data; a model evaluation iterative update subunit is used to evaluate and iteratively update the target three-dimensional positioning dynamic model according to the particle swarm optimization direction until the preset termination condition is met, and optimize and determine the particle with the largest fitness as the model parameter solution; a model parameter update configuration subunit is used to perform parameter update configuration on the target three-dimensional positioning dynamic model based on the model parameter solution to obtain the target three-dimensional positioning dynamic optimization model.

[0051] The rescue positioning data fusion and analysis system based on time series updating provided in the embodiment of the present invention can execute the rescue positioning data fusion and analysis method based on time series updating provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0052] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0053] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A rescue positioning data fusion analysis method based on time series update, characterized in that: The method comprises: Acquire a rescue positioning module, wherein the rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar, and acquires multiple three-dimensional positioning data sets of the rescue target through the rescue positioning module; According to the rescue positioning module, a data processing multi-channel is constructed, and mapping preprocessing and time sequence arrangement integration are performed on the multiple three-dimensional positioning data sets through the data processing multi-channel to obtain multiple standard time sequence positioning data sets; Performing criticality evaluation on the multiple standard time series positioning data sets to obtain multiple data criticality factors, performing multi-sensor fusion on the multiple standard time series positioning data sets based on the multiple data criticality factors, and collecting three-dimensional positioning fusion data of the rescue target; Monitor and obtain the current time-series motion change parameters of the rescue target, and perform dynamic impact analysis on the three-dimensional positioning fusion data of the rescue target based on the current time-series motion change parameters to obtain the target dynamic trend impact matrix; Based on the three-dimensional positioning fusion data of the rescue target, the current time-series motion change parameters and the target dynamic trend influence matrix, the rescue target is dynamically analyzed for positioning to obtain real-time three-dimensional positioning data of the target; The step of obtaining multiple data criticality factors includes: Acquire data fusion strategy factor information, wherein the data fusion strategy factor information includes data accuracy, acquisition stability, acquisition real-time performance, and scenario demand orientation; Evaluate the plurality of standard time series positioning data sets based on the data fusion strategy factor information to obtain a plurality of data fusion factor evaluation parameter sets; Assigning priorities to each strategy factor in the data fusion strategy factor information to obtain a strategy factor priority coefficient; Performing weighted fusion on the multiple data fusion factor evaluation parameter sets based on the strategic factor priority coefficients to obtain the multiple data criticality factors; The obtaining of the target dynamic trend impact matrix includes: Performing motion characteristic analysis on the three-dimensional positioning fusion data of the rescue target to obtain target motion characteristic information, wherein the target motion characteristic information includes motion trajectory, speed trend and motion direction mode; Based on the target motion characteristic information, a target motion state prediction model is obtained by training, wherein the target motion state prediction model includes a motion trajectory prediction model, a speed trend prediction model, and a motion direction pattern prediction model; Based on the current time-series motion change parameters, the target motion state prediction model is dynamically updated to obtain the target dynamic trend influence matrix; The obtaining of real-time three-dimensional positioning data of the target includes: Based on the target motion state prediction model, determining a target state transfer matrix; Construct a target three-dimensional positioning dynamic model, wherein the target three-dimensional positioning dynamic model is specifically: , is the three-dimensional positioning coordinate of the rescue target at time t, F is the target state transfer matrix, It is the three-dimensional positioning fusion data of the rescue target The three-dimensional positioning coordinates at the moment, B is the target dynamic trend influence matrix, is the current temporal motion change parameter, is the measurement disturbance error; The positioning data of the rescue target is calculated and updated based on the target three-dimensional positioning dynamic model to obtain real-time three-dimensional positioning data of the target.

2. The rescue positioning data fusion analysis method based on time series update according to claim 1 is characterized in that: The construction of data processing multiple channels includes: Extracting data sources from the rescue positioning module to obtain multiple data source characteristic information, and structurally classifying the multiple data source characteristic information to obtain data structured types; Performing a preprocessing program analysis on the plurality of data source characteristic information based on the data structured type to obtain a plurality of data preprocessing programs; Performing time series standardization analysis and time series data filling on the plurality of data source characteristic information to obtain a plurality of data time series filling programs; The multiple data preprocessing programs and the multiple data timing filling programs are configured for channel mapping to construct the data processing multi-channel.

3. The rescue positioning data fusion analysis method based on time series update according to claim 2 is characterized in that: The method of obtaining multiple data timing filling procedures includes: Extracting timestamps from the characteristic information of the multiple data sources respectively to obtain timestamp information of collection of multiple data sources; Performing collection time period analysis based on the collection timestamp information of the multiple data sources to obtain multiple data source collection time periods; Performing time series standardization selection on the multiple data source collection time periods to determine the data collection time series standard; Based on the data collection timing standard, the timing data filling and analysis are performed on the plurality of data source characteristic information to obtain the plurality of data timing filling programs.

4. The rescue positioning data fusion analysis method based on time series update according to claim 1, characterized in that: The method comprises: The rescue positioning module is used to monitor positioning data and fuse multiple sensors to obtain current time series three-dimensional positioning fusion data; Determining a particle swarm optimization direction based on a deviation between the target real-time three-dimensional positioning data and the current time series three-dimensional positioning fusion data; The target three-dimensional positioning dynamic model is evaluated and iteratively updated according to the particle swarm optimization direction until a preset termination condition is met, and the particle with the largest fitness is determined as the model parameter solution; The target three-dimensional positioning dynamic model is updated and configured with parameters based on the model parameter solution to obtain a target three-dimensional positioning dynamic optimization model.

5. The rescue positioning data fusion analysis system based on time series update is characterized by: The system is used to implement the rescue positioning data fusion analysis method based on time series update according to any one of claims 1 to 4, and the system includes: Multiple three-dimensional positioning data set acquisition modules, the multiple three-dimensional positioning data set acquisition modules are used to acquire a rescue positioning module, the rescue positioning module integrates a satellite positioning system, a UWB positioning device, a wireless signal base station and a laser radar, and acquires multiple three-dimensional positioning data sets of the rescue target through the rescue positioning module; A plurality of standard time-series positioning data set acquisition modules, wherein the plurality of standard time-series positioning data set acquisition modules are used to construct a data processing multi-channel according to the rescue positioning module, and to perform mapping preprocessing and time-series arrangement integration on the plurality of three-dimensional positioning data sets through the data processing multi-channel to acquire a plurality of standard time-series positioning data sets; A rescue target three-dimensional positioning fusion data acquisition module, the rescue target three-dimensional positioning fusion data acquisition module is used to perform criticality evaluation on the multiple standard time series positioning data sets, obtain multiple data criticality factors, perform multi-sensor fusion on the multiple standard time series positioning data sets based on the multiple data criticality factors, and collect rescue target three-dimensional positioning fusion data; A target dynamic trend influence matrix acquisition module, which is used to monitor and obtain the current time-series motion change parameters of the rescue target, and perform dynamic impact analysis on the three-dimensional positioning fusion data of the rescue target based on the current time-series motion change parameters to obtain the target dynamic trend influence matrix; The target real-time three-dimensional positioning data acquisition module is used to perform positioning dynamic analysis on the rescue target based on the rescue target three-dimensional positioning fusion data, the current time-series motion change parameters and the target dynamic trend influence matrix to obtain the target real-time three-dimensional positioning data.