Multi-source Data Fusion and Situation Generation Method and System

Abstract

The present invention relates to a multi-source data fusion and situation generation method and system, the method comprising: obtaining original target data of multiple intelligence sources, parsing and preprocessing, and establishing an original target library; adopting a fuzzy decision association strategy to perform data association; adopting a D-S evidence theory algorithm to perform data fusion processing, and establishing a fusion database; generating a target track according to the data fusion processing result, and establishing a target track library; performing target situation estimation and target threat assessment according to the target track generation result, and outputting the situation result, and establishing an intelligence situation library; managing and displaying the original target data, fused data, target track data, and situation data. The present invention adopts a fuzzy decision association strategy to perform data association, and performs data fusion processing through a D-S evidence theory algorithm, realizes the reorganization and processing of multi-source data, improves the comprehensiveness and accuracy of the data, and provides an efficient and reliable information reference for decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of situation generation, and particularly to a multi-source data fusion and situation generation method and system. Background Art

[0002] Situation generation is an information processing technology that mainly obtains and presents the current environment and situation by analyzing and integrating multi-source data. When applied to the military field, it can help combatants quickly, comprehensively, and accurately master battlefield situation information.

[0003] With the development of the application fields and objects of multi-source data fusion and situation generation, multi-source data fusion and situation display analysis, as a new technology for multi-dimensional information processing, also plays an important role in geodetic surveying. In the application scenario based on three-dimensional high-tech space-based information acquisition, with the continuous increase in the types and quantities of sensors such as radar, infrared, laser, ESM, and communication, a large amount of geodetic surveying information can be obtained in real time. These geodetic surveying information not only includes traditional structured data but also a large amount of unstructured data. How to transform these real-time, discrete, and complex-changing information data into valuable information that can be intuitively understood has become an important problem to be solved when multi-source data fusion and situation generation are applied in fields such as geodetic surveying.

[0004] Currently, there are problems in the processing of multi-source data such as difficult correlation processing, insufficient collaborative positioning and fusion verification capabilities. At the same time, the large amount of data and slow fusion speed during the data fusion process are also problems that need to be urgently solved in the process of multi-source data fusion and situation display analysis. Summary of the Invention

[0005] To solve the above technical problems existing in the prior art, the purpose of the present invention is to provide a multi-source data fusion and situation generation method and system, which can realize the correlation and collaborative processing of multi-source data, discover unknown target information with regularity, or update the new feature information of known targets according to established rules, so that multi-dimensional information data processing plays an important role in actual battlefield applications.

[0006] To achieve the above invention purpose, the present invention provides a multi-source data fusion and situation generation method, including the following steps:

[0007] Step S1, obtain the original target data of multiple intelligence sources, parse and preprocess the original target data, and establish an original target database;

[0008] Step S2, adopt a fuzzy decision-making correlation strategy to perform data correlation on the preprocessed target data; adopt the D-S evidence theory algorithm to perform data fusion processing on the correlated target data, and establish a fusion database;

[0009] Step S3: Generate target tracks based on the data fusion processing results and establish a target track library;

[0010] Step S4: Perform target situation estimation and target threat assessment based on the generation results of the target tracks, output the situation results, and establish an intelligence situation library;

[0011] Step S5: Manage and display the original target data in the original target library, the fusion data in the fusion database, the target track data in the target track library, and the situation data in the intelligence situation library.

[0012] According to a technical solution of the present invention, in the step S1, the preprocessing includes unified alignment processing of the time system, space coordinate system, and target feature parameter measurement unit of the original target data.

[0013] According to a technical solution of the present invention, in the step S2, when using the fuzzy decision-making association strategy to perform data association on the preprocessed target data, it specifically includes:

[0014] Step S211: Screen the preprocessed target data;

[0015] Step S212: Determine whether the screened target data satisfies the Euclidean distance membership degree between targets; if so, execute step S213; otherwise, execute step 217;

[0016] Step S213: Determine whether the screened target data satisfies the Euclidean distance membership degree between azimuths; if so, execute step S214; otherwise, execute step 217;

[0017] Step S214: Determine whether the screened target data satisfies the Euclidean distance membership degree between speeds; if so, execute step S215; otherwise, execute step 217;

[0018] Step S215: Determine whether the screened target data satisfies the Euclidean distance membership degree between headings; if so, execute step S216; otherwise, execute step 217;

[0019] Step S216: The screened target data is associated information;

[0020] Step S217: The association of the screened target data fails.

[0021] According to a technical solution of the present invention, in the step S2, when using the D-S evidence theory algorithm to perform data fusion processing on the associated target data, it specifically includes:

[0022] Step S221: Input the associated target data according to the target task;

[0023] Step S222: Probability distribution is performed on the basic original data according to the attribute characteristics of the target data;

[0024] Step S223: Set the inference rules according to the DS fusion principle: Finite number of mass functions m on Θ 1 ,m 2 ,…,m n The DS synthesis is:

[0025]

[0026] in,

[0027]

[0028] Step S224, according to the DS principle, reasoning network uncertainty transfer;

[0029] Step S225, adjusting the basic probability by comparing the probability after DS synthesis with the original probability;

[0030] Step S226: fusion of different path decisions based on the association processing results of different data sources;

[0031] Step S227, calculate the fusion result and output the fusion information.

[0032] According to a technical solution of the present invention, in step S2, before establishing the fusion result library, it also includes automatically batching the fused target points to obtain several batches of fused data, each batch of fused data has a unique target batch number.

[0033] According to a technical solution of the present invention, the target track generation includes:

[0034] Step S31, according to the batches of fused data, using a track generation regression algorithm, generating tracks for each batch of fused data in turn, to generate one or more initial target track data;

[0035] Step S32, according to the track generation result obtained in step S31, the target data outside the initial target track is eliminated;

[0036] Step S33, performing same-target point track aggregation on a plurality of initial target track data generated based on the same batch of fused data;

[0037] Step S34, performing track aggregation on several batches of initial target track data after the same target point track aggregation, generating target track data, and performing storage processing on the target track data.

[0038] According to one aspect of the present invention, there is provided a multi-source data fusion and situation generation management system for implementing the above method, including:

[0039] An access and display unit for acquiring and parsing target data and situation data of multiple intelligence sources, and displaying and managing the target data and situation data;

[0040] A data fusion unit for performing data association and data fusion on the target data, and generating target track data according to the fused data;

[0041] A situation generation unit for performing situation analysis according to the target track data, and generating and outputting situation data.

[0042] According to a technical solution of the present invention, the access and display unit includes:

[0043] A data input module for acquiring and parsing target data of multiple intelligence sources to form original target data;

[0044] A data preprocessing module for performing unified alignment processing on the original target data in terms of time system, space coordinate system, and measurement unit of target feature parameters;

[0045] A data management module for generating an original target library, a fusion database, a target track library, and an intelligence situation library, and performing data management operations through the original target data in the original target library, the fusion data in the fusion database, the target track data in the target track library, and the situation data in the intelligence situation library;

[0046] A two-dimensional and three-dimensional display module for displaying the original target data, the fusion data, the target track data, and the situation data according to the original target library, the fusion database, the target track library, and the intelligence situation library, and editing the target track data and the situation data.

[0047] According to a technical solution of the present invention, the data fusion includes:

[0048] A data fusion module for associating the original target data by adopting a fuzzy decision-making association strategy based on a spatial coordinate distance threshold, speed and heading features, target identity information, and relative position relationship features of a unified target at several moments, and performing data fusion processing on the associated target data according to the D-S evidence theory algorithm to generate the fusion data;

[0049] A track generation module for generating a track for the target according to the fusion data to generate target track data.

[0050] According to a technical solution of the present invention, the situation generation unit includes:

[0051] The situation generation unit includes:

[0052] A target situation analysis module, which is used to display the target track of a single target and predict the speed and course; classify multiple targets into different groups through rough classification of the targets, and determine the group category according to the target attribute characteristics through the D-S evidence theory, and judge the intention of the group targets;

[0053] A target threat estimation module, which is used to extract threat elements according to the target attribute characteristics of the target, and calculate the priority degree of each target through quantitative processing of the threat elements, calculate the target priority coefficient according to the target type, platform type and distance, and determine the target priority;

[0054] A situation output module, which is used to output the situation data of a single target and multiple targets into the intelligence situation database.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention proposes a multi-source data fusion, situation generation and management method and system. The method uses a fuzzy decision-making association strategy to perform data association on the original target data from multiple intelligence sources, and performs data fusion processing on the associated target data through the D-S evidence theory algorithm to obtain more accurate and clear target data; through target situation estimation and target threat assessment of the associated and fused target data, comprehensive and high-quality information is formed for the reference of the commander or directly assisting the commander in decision-making.

[0057] In the present invention, when using the module decision-making association strategy to perform data association on multiple observation values and target characteristics, the calculation amount is small and the accuracy is high, and the result can be output in real time. The fuzzy decision-making target data association strategy mainly uses multiple characteristics between multiple targets for fuzzy decision-making, such as the spatial coordinate distance threshold between target data, course and speed characteristics, target identity information, relative position relationship of the same target at several moments, etc., and finally realizes data association between targets, which has the advantages of wide applicability, few constraint conditions, can perform data association through multiple observation values and target characteristics, small calculation amount, high accuracy and real-time result output.

[0058] In the present invention, the D-S evidence theory algorithm is used as the data fusion algorithm. The D-S evidence theory algorithm can effectively reason and analyze incomplete information and uncertain information, and can perform multi-source heterogeneous data fusion more effectively and quickly, so as to help users obtain effective fusion strategies and accurate syntheses, and finally provide efficient and credible information reference for the decision-making of the decision-making agency. Description of the Drawings

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0060] Figure 1 Schematically showing a flowchart of a multi-source data fusion and situation generation method provided in an embodiment of the present invention;

[0061] Figure 2 Schematically showing a structural diagram of a multi-source data fusion and situation generation system provided in an embodiment of the present invention;

[0062] Figure 3 Schematically showing an architecture diagram of a multi-source data fusion and situation generation system provided in an embodiment of the present invention;

[0063] Figure 4 Schematically showing a flowchart of a multi-source data fusion and situation generation system provided in an embodiment of the present invention;

[0064] Figure 5 Schematically showing a specific flowchart of data association according to an embodiment of the present invention;

[0065] Figure 6 Schematically showing a specific flowchart of data fusion processing according to an embodiment of the present invention. Specific Embodiments

[0066] The description of the embodiments of this specification should be combined with the corresponding accompanying drawings, and the accompanying drawings should be a part of the complete specification. In the accompanying drawings, the shape or thickness of the embodiments can be enlarged and simplified or conveniently marked. Furthermore, each part of the structure in the accompanying drawings will be described separately. It should be noted that the elements not shown or described in words in the drawings are in the forms known to those of ordinary skill in the art.

[0067] Any reference to directions and orientations in the description of the embodiments herein is only for convenience of description and should not be construed as any limitation on the protection scope of the present invention. The following description of the preferred embodiments involves combinations of features, which may exist independently or in combination. The present invention is not particularly limited to the preferred embodiments. The scope of the present invention is defined by the claims.

[0068] Such as Figure 1As shown in the figure, a multi-source data fusion, situation generation and management method of the present invention includes the following steps:

[0069] Step S1: Obtain the original target data of multiple intelligence sources, parse and preprocess the original target data, and establish an original target database;

[0070] Among them, the preprocessing includes unified alignment processing of the time system, space coordinate system, and target characteristic parameter measurement unit of the original target data.

[0071] Step S2: Adopt a fuzzy decision-making association strategy to perform data association on the preprocessed target data; use the D-S evidence theory algorithm to perform data fusion processing on the associated target data, and establish a fusion database;

[0072] Step S3: Generate a target track according to the data fusion processing result, and establish a target track database;

[0073] Step S4: Perform target situation estimation and target threat assessment according to the generation result of the target track, output the situation result, and establish an intelligence situation database;

[0074] Step S5: Manage and display the original target data of the original target database, the fusion data of the fusion database, the target track data of the target track database, and the situation data of the intelligence situation database.

[0075] The present invention introduces a target data association algorithm with fuzzy decision-making to perform multi-dimensional association on multi-source data, which can use multiple characteristics between multiple targets for fuzzy decision-making, and finally realize data association between targets. It has the advantages of wide applicability, few constraint conditions, can perform data association through multiple observation values and target characteristics, small calculation amount, high accuracy, and can output results in real time.

[0076] The present invention introduces the D-S evidence theory algorithm to fuse multi-source data. Compared with other data fusion algorithms, the D-S evidence theory can effectively reason and analyze incomplete information and uncertain information, and can perform fusion of multi-source heterogeneous data more effectively and quickly, so as to help users obtain effective fusion strategies and accurate syntheses, and finally provide efficient and credible information reference for the decision-making of the decision-making agency, solving the problems of difficult association processing, insufficient collaborative positioning and fusion verification ability existing in the current conventional multi-dimensional data association algorithms, and at the same time solving the problems of large amount of data and slow fusion speed in the data fusion process.

[0077] As Figure 2 shown, the present invention also provides a multi-source data fusion and situation generation system for implementing the above method, including an access and display unit, a data fusion unit, and a situation generation unit.

[0078] An access and display unit, which is used to obtain and parse the target data and situation data of multiple information sources, and display and manage the target data and situation data; specifically, the access and display unit includes:

[0079] A data input module, which is used to obtain and parse the target data of multiple information sources to form original target data;

[0080] A data preprocessing module, which is used to perform unified alignment processing on the time system, space coordinate system, and target feature parameter measurement units of the original target data;

[0081] A data management module, which is used to generate an original target library, a fusion database, a target track library, and an intelligence situation library, and perform data management operations through the original target data in the original target library, the fusion data in the fusion database, the target track data in the target track library, and the situation data in the intelligence situation library;

[0082] A two-dimensional and three-dimensional display module, which is used to display the original target data, the fusion data, the target track data, and the situation data according to the original target library, the fusion database, the target track library, and the intelligence situation library, and edit the target track data and the situation data.

[0083] A data fusion unit, which is used to perform data association and data fusion on the target data, and generate target track data according to the fused data; specifically, the data fusion unit includes:

[0084] A data fusion module, which is used to adopt a fuzzy decision-making association strategy, and based on the spatial coordinate distance threshold, speed and heading characteristics, target identity information, and relative position relationship characteristics of the unified target at several moments, perform the association of the original target data, and perform data fusion processing on the associated target data according to the D-S evidence theory algorithm to generate the fusion data;

[0085] A track generation module, which is used to generate a target track according to the fusion data to generate target track data.

[0086] A situation generation unit, which performs situation analysis according to the target track data, and generates and outputs situation data. Specifically, the situation generation unit includes:

[0087] A target situation analysis module, which is used to display the target track and predict the speed and heading of a single target; classify multiple targets into different groups through rough classification of the targets, and determine the group category according to the target attribute characteristics through the D-S evidence theory, and perform intention judgment on the group targets;

[0088] The target threat estimation module is used to extract threat elements according to the target attribute characteristics of the target, and calculate the priority degree of each target through the quantification process of the threat elements, calculate the target priority coefficient according to the target type, platform type and distance, and determine the target priority;

[0089] The situation output module is used to output the situation data of single targets and multiple targets into the intelligence situation database.

[0090] The present invention will be specifically described below through embodiments.

[0091] The architecture of the multi-source data fusion and situation generation system provided by this embodiment is as Figure 3 shown, including an infrastructure layer, a software service layer, and an application layer.

[0092] As a channel for intelligence collection, the infrastructure layer obtains intelligence information through various platform sensors such as space-based, air-based, and shore-based platforms, providing data support for the data fusion and situation generation system.

[0093] The software service layer includes two processing functions of data fusion and situation analysis. It is the core working unit of the system, responsible for the entire processing links such as data management, fusion processing, and situation analysis.

[0094] The application layer is an interactive interface for providing system applications, including the invocation of the software service layer, the display of interfaces such as situation information, track information, and threat information, and the output of situation information.

[0095] The business workflow of the multi-source data fusion and situation generation system provided by this embodiment is as Figure 3 shown, and is specifically described as follows:

[0096] Step S1: Obtain the original target data of multiple intelligence sources, parse and preprocess the original target data, and establish an original target library.

[0097] According to the startup of the software of the multi-source data fusion and situation generation system, external data access is detected, and the accessed intelligence data is parsed; and the accessed original target data is preprocessed to perform unified alignment processing of the time system, space coordinate system, and target feature parameter measurement unit. The multi-source data is intelligence information obtained through various platform sensors such as space-based, air-based, and shore-based platforms.

[0098] Due to the different installation positions of various detection devices and platform sensors used for intelligence collection in the infrastructure layer, and the inconsistent detection and scanning cycles, it is necessary to perform unified alignment processing of the time system for the original target data obtained by the system.

[0099] The unified alignment of the time system involves two situations: inconsistent time sampling intervals and inconsistent acquisition times:

[0100] 1. Inconsistent time sampling intervals

[0101] When the time sampling intervals of the original target data are inconsistent, there are multiple high-frequency data in the retention time intervals of the low-frequency data. Therefore, the following three methods are generally used to uniformly align the time systems of the original target data with inconsistent time sampling intervals:

[0102] 1) Select the original target data with the most occurrences in the high-frequency original target data as the replacement for the high-frequency original target data in the entire retention time period of the low-frequency data. For example, in a 1-second time interval, 100 communication signal samples are received, and the modulation method with the most occurrences is BPSK (accounting for 80%), then it is considered that all the signals received in the entire 1-second interval are of the BPSK type.

[0103] 2) Receive data in real time and establish a time data table according to the received data at the receiving moment. Among them, the time data table obtains data at regular intervals according to the set time threshold, regards these data as sent by the same target, and integrates these data into the database.

[0104] Through the time data table, receive the data sent by the same target at fixed time intervals, and realize the unification of the time systems of the original intelligence data from multiple information sources of the same target.

[0105] 3) Select an intermediate frequency according to the acquisition frequency of the low-frequency original target data and the acquisition frequency of the high-frequency original target data, and screen all the acquired original target data according to the intermediate frequency.

[0106] For example, in a 1-second interval, the data that changes 100 times is reported 10 times according to the status. After such screening, the data can partially reflect the change trend without bringing too much data pressure.

[0107] 2. The data acquisition times are not at the same moment

[0108] Take the union of the update times of the acquired multiple-channel original target data as the data update time point. At each data update time, use the latest data status as the attribute status of this time point.

[0109] The preprocessed original target data is managed in the database and stored in different database forms according to the data sources.

[0110] Step S2: Adopt a fuzzy decision-making association strategy to perform data association on the preprocessed target data; use the D-S evidence theory algorithm to perform data fusion processing on the associated target data and establish a fusion database.

[0111] A key to data fusion is the association between data. In a multi-sensor fusion system, there is a large amount of acquired data. It is not an easy task to select the associated data from this large amount of data. In data association, generally, the association of the time axis, the space axis, and the spatio-temporal axis needs to be solved. Different fields have different algorithms in data association.

[0112] Data correlation processing includes three processing methods, namely time-axis correlation (performing data correlation processing in chronological order, suitable for data fusion of a single sensor), space-axis correlation (performing correlation processing on the data of each sensor at the same moment, suitable for primary fusion processing of multi-sensor data), and spatio-temporal axis correlation (performing correlation processing on all measurement data of all sensors, suitable for large data fusion systems).

[0113] The core issues of data correlation are how to overcome the correlation caused by the inaccuracy of sensor measurements and interference, that is, to maintain data consistency; how to control and reduce the complexity of correlation calculations, and develop algorithms and models for correlation processing, fusion processing, and system simulation.

[0114] Specifically, as Figure 5 shown, the data association includes the following steps:

[0115] Step S211: Screen the preprocessed target data;

[0116] Determine the effective target data range according to the acquisition time of the target data and the longitude and latitude range where the target is located; screen the preprocessed target data according to the effective target data range, and remove the scattered points outside the effective target data range to avoid the interference of scattered points on subsequent data association.

[0117] Step S212: Determine whether the screened target data satisfies the Euclidean distance membership between targets; if so, execute step S213; otherwise, execute step 217;

[0118] By judging whether the target data satisfies the Euclidean distance membership between targets, data association processing of the target data is realized based on the spatial coordinate threshold characteristics of the target data;

[0119] Step S213: Determine whether the screened target data satisfies the Euclidean distance membership between azimuths; if so, execute step S214; otherwise, execute step 217;

[0120] By judging whether the target data satisfies the Euclidean distance membership between azimuths of the target data, data association processing of the target data is realized based on the azimuth characteristics of the target data;

[0121] Step S214: Determine whether the filtered target data satisfies the Euclidean distance membership degree between speeds; if so, execute Step S215; otherwise, execute Step 217;

[0122] By determining whether the target data satisfies the Euclidean distance membership degree between speeds, data association processing of the target data is realized based on the speed characteristics of the target data.

[0123] Step S215: Determine whether the filtered target data satisfies the Euclidean distance membership degree between headings; if so, execute Step S216; otherwise, execute Step 217;

[0124] By determining whether the target data satisfies the Euclidean distance membership degree between headings, data association processing of the target data is realized based on the heading characteristics of the target data;

[0125] Step S216: Output: Association information;

[0126] Step S217: Output: Association failed.

[0127] The system adopts a fuzzy decision-making strategy for data association. Through the calculation and judgment based on the spatial coordinate distance threshold, speed and heading characteristics, target identity information, and the relative position relationship characteristics of the same target at several moments, the association of the original target data is carried out.

[0128] Due to insufficient information or the complexity of decision-making problems, it is often difficult to obtain accurate data or information, resulting in certain fuzziness and uncertainty in the decision-making process. Compared with ordinary multi-attribute decision-making methods, the fuzzy multi-attribute decision-making method uses the theory and methods of fuzzy mathematics and can better express and process the fuzziness of data. Therefore, the research on the fuzzy multi-attribute decision-making method based on the association rule mining algorithm can not only better cope with the fuzziness and uncertainty in the decision-making process but also improve the accuracy of the decision-making result.

[0129] The specific steps are as follows: First, search for alternative data in the database, including vectors of state estimates such as the position, speed, or identity of the target measurement in the previous sampling period. Then, correct the alternative data to the observation time, calculate the predicted position of the alternative target, and perform threshold filtering to remove incorrect measurement data and interference factors that appear during the association process. According to the fuzzy association formula, calculate the association matrix, and illustrate the relationship between the information data and a certain state vector through the allocation strategy.

[0130] As Figure 6 shown, the data fusion includes the following steps:

[0131] Step S221: Input the associated target data according to the target task;

[0132] Step S222: Perform probability assignment on the basic raw data according to the target data attribute characteristics;

[0133] Step S223: Set up inference rules. According to the D-S fusion principle: For a finite number of mass functions m 1 , m 2 , …, m n on Θ, the D-S combination is:

[0134]

[0135] where,

[0136]

[0137] Step S224: According to the D-S principle, perform uncertainty transfer in the inference network;

[0138] Step S225: Perform basic probability adjustment by comparing the probability after D-S combination with the original probability;

[0139] Step S226: According to the correlation processing results of different data sources, perform different path decision fusion;

[0140] Step S227: Calculate the fusion result and output the fusion information.

[0141] When performing data fusion, the information provided by each sensor is generally incomplete, inaccurate, fuzzy, and sometimes even contradictory, that is, it contains a lot of uncertainty. To perform fusion, it is necessary to reason based on this uncertain information to achieve the purpose of target identity recognition and attribute decision.

[0142] Uncertainty reasoning is the basis of target recognition and attribute information fusion, and it is also a kind of reasoning based on uncertain knowledge on the basis of non-classical logic. It starts from the initial evidence of uncertainty and, by applying uncertain knowledge, infers conclusions with a certain degree of uncertainty and reasonable or nearly reasonable. The DS evidence theory is an important tool for dealing with uncertain information reasoning and can handle the uncertainty caused by "unknown". It uses the belief function instead of probability as a measure, and establishes the belief function by restricting the probability of some events without having to specify the precise and difficult-to-obtain probability. When the constraint is restricted to a strict probability, it becomes the probability theory. Static reasoning or deduction includes all possible states of the system or common assumptions, and then assigns probabilities or mass assignment functions to these assumptions and combines them to make a final decision.

[0143] Step S2 also includes: automatically batch the fused target points to obtain several batches of fused data, and each batch of fused data has a unique target batch number.

[0144] Multiple batches of fused data are obtained through data fusion, and each batch of fused data can be used to describe a set of targets. The targets include individual targets or group targets.

[0145] By automatically batch-coding the fused targets, a target batch number is generated as a unique identification code, which facilitates a series of subsequent operations such as track generation, track management, and situation analysis for the fused targets. At the same time, it facilitates target clustering and intention analysis of group targets, thereby improving the organization of data management and the data processing efficiency during analysis.

[0146] Step S3: According to the data fusion processing results, generate target tracks and establish a target track library;

[0147] Step S31: According to several batches of the fused data, through a track generation regression algorithm, generate tracks for each batch of the fused data in sequence, and generate one or more initial target track data;

[0148] Step S32: According to the track generation results obtained in Step S31, eliminate target data that is outside the initial target tracks;

[0149] When the target data does not conform to the track generation rules, the target data is regarded as a free target point and the free target point is deleted.

[0150] Step S33: Aggregate the same target point traces for multiple initial target track data generated based on the same batch of fused data;

[0151] In the actually obtained target data, interference clutter usually exists, manifested as possible interference around the real track. Therefore, after aggregating the same target point traces, it is necessary to extract the track and use a monotonically increasing time sequence to describe the movement track of a target.

[0152] When there are multiple target tracks at the same time, the point trace data will be mixed with each other. Coupled with clutter and false alarms, it will cause greater interference. Aggregating the same target point traces is to classify the original point trace data separately and condense the point trace data generated by the same target together, which is convenient for subsequent track extraction.

[0153] Step S34: Aggregate the initial target track data of several batches after aggregating the same target point traces to generate target track data, and perform warehousing processing on the target track data.

[0154] Before performing warehousing management on the generated target track data, track fusion is also included.

[0155] Track fusion is to fuse multi-source data with the track of one of the data through a certain algorithm, so that the accuracy after fusion is higher than that of a single sensor, that is, closer to the real track. At the same time, after track fusion, the complexity of the integrated navigation display system interface will be reduced, and the redundancy of multi-source information will be avoided, which brings inconvenience to the operators.

[0156] Establish a target track library to manage the generated target track data in the library. When new data of a certain target is accessed, update the track data corresponding to the target according to the newly accessed target data, and update the target track library at the same time; when a certain target is confirmed to be destroyed, terminate the target track after manual confirmation.

[0157] Step S4: According to the generation result of the target track, conduct target situation estimation and target threat assessment, output the situation result, and establish an intelligence situation library;

[0158] Predict the target dynamics such as heading and speed based on the target track data and the fused target point information, conduct target clustering, predict the intention according to the target group, and calculate the target threat coefficient, evaluate the target threat level and threat range; mark the situation of multiple targets in the same target group with a single color, output the situation data in the standard format, and manage the output situation data in the library.

[0159] Among them, the target track display and the prediction of speed and heading of a single target are carried out through the target situation analysis module; multiple targets are roughly classified into different groups, and the group category is determined according to the target attribute characteristics through the D-S evidence theory, and the intention of the group target is judged.

[0160] Target prediction is the premise of threat assessment. The output of threat assessment is theoretically to give the conditional probabilities of various hypotheses for the commander's reference. Future target prediction refers to predicting the possible future situation based on the understanding of the current situation and the result of threat analysis.

[0161] Based on the analysis result of the target situation analysis module, the threat elements are extracted by the target threat estimation module according to the target attribute characteristics of the target, and through the quantization processing of the threat elements, calculate the priority degree of each target, calculate the target priority coefficient according to the target type, platform type and distance, and determine the target priority.

[0162] Threat assessment mainly involves the estimation of risks and the estimation of the weak links of our forces restricted by the enemy. The threat assessment method describes all environmental elements in the battlefield according to the comprehensive view of the battlefield situation, and quantifies the estimation of the enemy's forces to form a threat analysis of both sides of the battlefield situation. Its main content is to reason about the enemy's behavior and action intentions, that is, what the result of the situation action is under the current event situation and what impact it has on us. Through threat assessment of the results formed by the situation, threat analysis element extraction is carried out to form a suitable set of hypotheses, and the abstract understanding of threat analysis is completed. Threat assessment includes the analysis of the motion parameters and combat intentions of the situation entities of both sides of the enemy and us, and gives various inferences of the battlefield situation in real time.

[0163] The situation output can output the situation data to the outside of the system or to the data input module through the situation output module. The formats of the output situation data include situation XML, thematic map JPG, thematic report PDF, etc.

[0164] Step S5: Manage and display the original target data of the original target library, the fusion data of the fusion database, the target track data of the target track library, and the situation data of the intelligence situation library.

[0165] The original target data of the original target library, the fusion data of the fusion database, the target track data of the target track library, and the situation data of the intelligence situation library can be operated on data management through the data management module, including the display and editing of various types of data.

[0166] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or terminal device including the said element.

[0167] Finally, it should be noted that the above is the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those skilled in the art of this technology, once the basic creative concept of the present invention is known, without departing from the principle of the present invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A multi-source data fusion and situation generation method, characterized in that, it includes the following steps: Step S1, obtain the original target data of multiple intelligence sources, parse and preprocess the original target data, and establish an original target library; Step S2, adopt a fuzzy decision-making association strategy to perform data association on the preprocessed target data; Adopt the D-S evidence theory algorithm to perform data fusion processing on the associated target data, and establish a fusion database; Step S3, generate a target track according to the data fusion processing result, and establish a target track library; Step S4, perform target situation estimation and target threat assessment according to the generation result of the target track, output the situation result, and establish an intelligence situation library; Step S5, manage and display the original target data of the original target library, the fusion data of the fusion database, the target track data of the target track library, and the situation data of the intelligence situation library; In the step S2, the adoption of the fuzzy decision-making association strategy to perform data association on the preprocessed target data specifically includes: Step S211, screen the preprocessed target data; Step S212, judge whether the screened target data satisfies the Euclidean distance membership degree between targets; if so, execute step S213; otherwise, execute step 217; Step S213, judge whether the screened target data satisfies the Euclidean distance membership degree between azimuths; if so, execute step S214; otherwise, execute step 217; Step S214, judge whether the screened target data satisfies the Euclidean distance membership degree between speeds; if so, execute step S215; otherwise, execute step 217; Step S215, judge whether the screened target data satisfies the Euclidean distance membership degree between headings; if so, execute step S216; otherwise, execute step 217; Step S216, the screened target data is association information; Step S217, the association of the screened target data fails; The data association includes: first, search for alternative data in the database, including the vectors of the position, speed, or identity state estimation of the target measurement in the previous sampling period; then correct the alternative data to the observation time, calculate the predicted position of the alternative target, and then perform threshold filtering to remove incorrect measurement data and interference factors that appear during the association process. Calculate the association matrix according to the fuzzy association formula, and explain the relationship between the information data and a certain state vector through the allocation strategy; In the step S2, the adoption of the D-S evidence theory algorithm to perform data fusion processing on the associated target data specifically includes: Step S221, input the associated target data according to the target task; Step S222, perform probability assignment on the basic original data according to the attribute characteristics of the target data; Step S223, set the inference rule. According to the D-S fusion principle: For a finite number of mass functions m 1 , m 2 , …, m n on Θ, their D-S composition is: Among them, Step S224, according to the D-S principle, infer the uncertainty transfer of the network; Step S225, perform basic probability adjustment by comparing the probability after D-S synthesis with the original probability; Step S226, perform different-path decision fusion according to the association processing results of different data sources; Step S227, calculating the fusion result and outputting the fusion information; In the step S2, multiple batches of fused data are obtained through data fusion, and each batch of fused data is used to describe a group of targets; the targets include single targets or group targets; before establishing the fusion database, it also includes automatically batching the fused target points to obtain several batches of fused data, each batch of fused data has a unique target batch number, which is used for track generation, track management, situation analysis, grouping of targets and intention analysis of group targets after fusion.

2. The multi-source data fusion and situation generation method according to claim 1, It is characterized in that In the step S1, the preprocessing includes uniformly aligning the time system, space coordinate system, and target feature parameter measurement unit of the original target data.

3. The multi-source data fusion and situation generation method according to claim 1, It is characterized in that In step S3, the target track generation includes: Step S31, according to the batches of fused data, using a track generation regression algorithm, generating tracks for each batch of fused data in turn, to generate one or more initial target track data; Step S32, according to the track generation result obtained in step S31, the target data outside the initial target track is eliminated; Step S33, performing same-target point track aggregation on a plurality of initial target track data generated based on the same batch of fused data; Step S34, performing track aggregation on several batches of initial target track data after the same target point track aggregation, generating target track data, and performing storage processing on the target track data.

4. A multi-source data fusion and situation generation system, It is characterized in that The method for implementing any one of claims 1 to 3 comprises: An access and display unit, used to acquire and analyze target data and situation data from multiple intelligence sources, and to display and manage the target data and situation data; A data fusion unit, used for performing data association and data fusion on the target data, and generating target track data according to the fused data; The situation generating unit performs situation analysis according to the target track data, and generates and outputs situation data.

5. The multi-source data fusion and situation generation system according to claim 4, It is characterized in that The access and display unit comprises: Data input module, used to obtain and analyze target data from multiple intelligence sources to form original target data; A data preprocessing module, used for uniformly aligning the time system, space coordinate system and target characteristic parameter measurement unit of the original target data; A data management module, used to generate an original target library, a fusion database, a target track library and an intelligence situation library, and perform data management operations through the original target data in the original target library, the fusion data in the fusion database, the target track data in the target track library and the situation data in the intelligence situation library; A two - and three - dimensional display module, configured to display the original target data, the fusion data, the target track data, and the situation data according to the original target library, the fusion database, the target track library, and the intelligence situation library, and to edit the target track data and the situation data.

6. The multi - source data fusion and situation generation system according to claim 4, characterized in that the data fusion unit includes: A data fusion module, configured to use a fuzzy decision - making association strategy, based on a spatial coordinate distance threshold, speed and heading features, target identity information, and relative position relationship features of a unified target at several moments, to perform association of the original target data, and according to the D - S evidence theory algorithm, to perform data fusion processing on the associated target data to generate the fusion data; A track generation module, configured to generate target track data by generating a track for a target according to the fusion data.

7. The multi - source data fusion and situation generation system according to claim 6, characterized in that the situation generation unit includes: A target situation analysis module, configured to perform target track display and prediction of speed and heading for a single target; to perform rough classification of multiple targets into different groups, and to determine the group category according to target attribute features through the D - S evidence theory, and to perform intention judgment on group targets; A target threat estimation module, configured to extract threat elements according to the target attribute features of the target, and through quantization processing of the threat elements, calculate the priority degree of each target, calculate the target priority coefficient according to the target type, platform type, and distance, and determine the target priority; A situation output module, configured to output the situation data of a single target and multiple targets to the intelligence situation library.

Images