Big data space-time autonomous association method for star group geometry and radiation recalibration

Abstract

The invention provides a big data space-time autonomous association method for star group geometry and radiation recalibration. The method comprises the following steps: acquiring remote sensing image data and multivariate information data acquired by a star group network; establishing a multi-source heterogeneous information label based on the remote sensing image data and the multivariate information data; establishing a comprehensive index table based on the multivariate heterogeneous information class and a preset retrieval strategy; and inputting the comprehensive index table into the big data space-time autonomous association model to retrieve and obtain candidate associated data, and performing condition screening on the candidate associated data to obtain target associated data. The remote sensing image data and the multivariate information data collected by the satellite group networking are processed to generate the comprehensive index table, matching and association of the remote sensing image data and the historical remote sensing image data can be achieved, customized adjustment can be conducted according to a retrieval strategy, the retrieval efficiency is improved, the redundancy of big data is reduced, and the retrieval efficiency is improved. And researchers can conveniently carry out automatic data mining work of batch processing.

Description

Technical Field

[0001] The present disclosure relates to the technical field of big data spatiotemporal autonomous correlation technology for constellation geometry and radiation recalibration, and in particular to a big data spatiotemporal autonomous correlation method for constellation geometry and radiation recalibration. Background Art

[0002] Among current technologies, satellite remote sensing technology is booming. Whether in the civilian or military fields, the multi-satellite and multi-payload collaborative observation technology of constellation networking has become an inevitable development trend. Multi-satellite joint observation and data comprehensive application have entered the normal operation mode. The domestic high-resolution series and resource series satellites have attempted dual-satellite networking observation and operation. The commercial satellite Sino-European Bit hyperspectral satellite constellation has been operating in a network for many years. Changguang Satellite has also adopted a multi-satellite networking approach to build the Jilin-1 satellite constellation to provide commercial satellite data services. Abroad, the Dove small satellite constellation (including more than 190 small satellites) launched by Planet Labs Inc. in the United States has achieved global coverage with an ultra-high spatial resolution of 3 meters almost every day, providing unprecedented opportunities for monitoring fine-scale changes on the surface.

[0003] With the advancement of Earth observation technology, satellites are rapidly expanding in constellation networks, and the ability to acquire remote sensing data is continuously improving. High-resolution and high-frequency remote sensing data can be acquired more easily and quickly, leading to an explosive growth in data volume and ushering in the era of remote sensing big data. However, mechanisms for correlating and sharing remote sensing data information have yet to be fully established. The demand for target information has also expanded from static target interpretation to comprehensive understanding and analysis across all dimensions. To effectively organize and manage large amounts of remote sensing image data and meet these demands, a large amount of valid and correlated image data is urgently needed. Therefore, it is necessary to establish correlation information for multi-source remote sensing image data to facilitate data sharing, application, and comprehensive analysis. Therefore, rapidly correlating and analyzing information in multiple dimensions, such as time and space, based on massive, multi-source, heterogeneous remote sensing data is a critical issue for the future development of remote sensing data. Summary of the Invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] Therefore, one objective of the present disclosure is to propose a method for associating data in a constellation network.

[0006] A second objective of the present disclosure is to provide a data association device for a constellation network.

[0007] A third objective of the present disclosure is to provide an electronic device.

[0008] A fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0009] A fifth object of the present disclosure is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes a constellation network data association method, including: obtaining remote sensing image data collected by the constellation network and multivariate information data corresponding to the remote sensing image data; establishing multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data; establishing a comprehensive index table based on the multivariate heterogeneous information class and a preset retrieval strategy; inputting the comprehensive index table into a big data spatiotemporal autonomous association model to retrieve candidate association data, and performing conditional screening on the candidate association data to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the constellation network.

[0011] According to one embodiment of the present disclosure, the comprehensive index table is established based on the multi-source heterogeneous information class and a preset retrieval strategy, including: selecting at least one target data tag from the multi-source heterogeneous information tags based on the retrieval strategy; and establishing the comprehensive index table based on the target data tag.

[0012] According to one embodiment of the present disclosure, the establishment of multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data also includes: obtaining label construction rules; establishing sub-label data labels of the remote sensing image data and the multivariate information data based on the label construction rules; and establishing multi-source heterogeneous information labels of the remote sensing image data based on all sub-label data labels.

[0013] According to one embodiment of the present disclosure, the conditional screening of the candidate associated data to obtain target associated data includes: for any candidate associated data, obtaining a screening rule corresponding to the candidate associated data; and screening the candidate associated data based on the screening rule to obtain the target associated data.

[0014] According to an embodiment of the present disclosure, before filtering the candidate associated data based on the filtering rules to obtain the target associated data, the method further includes: judging the rationality of the filtering rules; and judging that the filtering rules are rational.

[0015] According to one embodiment of the present disclosure, establishing a multi-source heterogeneous information label based on the remote sensing image data and the multivariate information data includes: normalizing the remote sensing image data and the multivariate information data according to preset data processing rules to generate the multi-source heterogeneous information label.

[0016] According to one embodiment of the present disclosure, the target associated data is associated with a recalibration data parameter library.

[0017] To achieve the above-mentioned purpose, the second aspect embodiment of the present disclosure proposes a star cluster network data association device, including: an acquisition module for acquiring remote sensing image data collected by the star cluster network and multivariate information data corresponding to the remote sensing image data; a construction module for establishing multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data; an establishment module for establishing a comprehensive index table based on the multivariate heterogeneous information class and a preset retrieval strategy; a retrieval module for inputting the comprehensive index table into a big data spatiotemporal autonomous association model to retrieve candidate association data, and perform conditional screening on the candidate association data to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the star cluster network.

[0018] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the star cluster network data association method as described in the first aspect embodiment of the present disclosure.

[0019] To achieve the above-mentioned purpose, the fourth embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the star cluster network data association method as described in the first embodiment of the present disclosure.

[0020] To achieve the above-mentioned purpose, the fifth embodiment of the present disclosure proposes a computer program product, including a computer program, which, when executed by a processor, is used to implement the star cluster network data association method as described in the first embodiment of the present disclosure.

[0021] Therefore, by processing the remote sensing image data and multivariate information data collected by the constellation network to generate a comprehensive index table, it is possible to match and associate the remote sensing image data with the historical remote sensing image data, and it can be customized according to the retrieval strategy, which improves the retrieval efficiency, reduces the redundancy of big data, and facilitates researchers to carry out automated data mining work for batch processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of a method for associating data in a constellation network according to an embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram of another method for associating data in a constellation network according to an embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram of another method for associating data in a constellation network according to an embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram of another method for associating data in a constellation network according to an embodiment of the present disclosure;

[0026] Figure 5 This is a schematic diagram of a data association device for a constellation network according to an embodiment of the present disclosure;

[0027] Figure 6 is a schematic diagram of an electronic device according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0029] The acquisition, storage, use, and processing of data in this disclosed technical solution comply with the relevant provisions of relevant laws and regulations.

[0030] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0031] Constellation images are affected by factors such as the orbital altitude of the networked satellites, revisit period, cloud and fog weather, pointing accuracy, constellation imaging time, space temperature and temperature environment, shooting angle, solar altitude, atmospheric radiation conditions, star sensor reference switching, long-period low-frequency error, platform sensor measurement reference change, and platform sensor equipment aging. Existing constellation historical remote sensing big data and real-time imagery have significant differences in geometry, spectrum, and radiometry. This leads to inconsistencies in spatial and radiometric references, resulting in inconsistencies in the radiometric and geometric quality of long-term remote sensing imagery. To address this inconsistency in geometric and radiometric quality, it is necessary to conduct real-time detection of long-period spatial reference change parameters and radiometric reference parameters for constellation data, achieve overall recalibration of historical observation data, and thereby improve the geometric and radiometric quality of constellation images. The core of achieving constellation geometric and radiometric recalibration is to establish correlations between historical observation data. This is achieved by autonomously correlating the multi-dimensional information of constellation historical data with geometric / radiometric correction accuracy, enabling the establishment of a compensation model for recalibration. Therefore, this disclosure proposes a big data spatiotemporal autonomous correlation method for constellation geometric and radiometric recalibration to address the aforementioned issues.

[0032] In order to solve the above problems, the present disclosure proposes a method for associating data in a constellation network. Figure 1 As shown, Figure 1 FIG. 1 is a schematic diagram of a method for associating data in a constellation network according to an embodiment of the present disclosure. The method for associating data in a constellation network comprises the following steps:

[0033] S101, acquiring remote sensing image data collected by a constellation network and multivariate information data corresponding to the remote sensing image data.

[0034] The star cluster network data association method of the embodiment of the present application can be applied to the scenario of automatic retrieval and / or automatic comparison of star cluster network data. The execution entity of the star cluster network data association of the embodiment of the present application can be the star cluster network data association device of the embodiment of the present application, and the star cluster network data association device can be set on an electronic device.

[0035] In the embodiments of the present disclosure, multivariate information data is data used to describe attribute information or other ancillary information of remote sensing image data. For example, multivariate information data may include the acquisition coordinates of the remote sensing image data, the identification of the acquisition satellite, the acquisition time, and latitude and longitude information.

[0036] In the embodiment of the present disclosure, the metadata file of the remote sensing image data may be analyzed to determine the multivariate information data corresponding to the remote sensing image data.

[0037] S102, establishing multi-source heterogeneous information labels based on remote sensing image data and multi-information data.

[0038] It should be noted that multi-source heterogeneous information refers to the types of remote sensing image data and multi-element information data. In the embodiments of the present disclosure, there are many methods for establishing multi-source heterogeneous information labels based on remote sensing image data and multi-element information data, which are not limited here.

[0039] In one possible implementation, remote sensing image data and multi-element information data can be processed using an analysis model to determine the multi-source heterogeneous information labels corresponding to each of the remote sensing image data and the multi-element information data. This analysis model can be pre-trained and stored in the storage space of an electronic device for easy access when needed.

[0040] In another possible implementation method, the labels of the remote sensing image data and the multivariate information data can also be analyzed to determine the multi-source heterogeneous information labels corresponding to the remote sensing image data and the multivariate information data.

[0041] S103, establishing a comprehensive index table based on multiple heterogeneous information categories and preset retrieval strategies.

[0042] It should be noted that the comprehensive index table may include multiple index information or one index information, and the specific needs are limited according to actual index requirements or index strategies.

[0043] In the embodiment of the present disclosure, there are many methods for establishing a comprehensive index table based on multi-dimensional heterogeneous information classes and preset retrieval strategies, which are not limited here.

[0044] S104: Input the comprehensive index table into the big data spatiotemporal autonomous association model to retrieve candidate association data, and perform conditional screening on the candidate association data to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the constellation network.

[0045] It should be noted that the Big Data Spatiotemporal Autonomic Correlation Model is a database model proposed in this disclosure that stores all historical remote sensing image data from a constellation network. This Big Data Spatiotemporal Autonomic Correlation Model can be of various types, for example, a relational database model, a hierarchical database model, a network database model, and so on.

[0046] By establishing a big data spatiotemporal autonomous correlation model, a reliable storage space can be provided for historical remote sensing image data, and a data basis can be provided for subsequent data retrieval and horizontal and vertical comparison of data.

[0047] In the above embodiment, remote sensing image data collected by the constellation network and the corresponding multivariate information data are first acquired. Multi-source heterogeneous information is then established based on the remote sensing image data and the multivariate information data. A comprehensive index table is then established based on the multivariate heterogeneous information classes and a preset retrieval strategy. Finally, the comprehensive index table is input into a big data spatiotemporal autonomous association model to retrieve candidate associated data, and conditional screening is performed on the candidate associated data to obtain target associated data. The big data spatiotemporal autonomous association model stores the historical remote sensing image data of the constellation network. Thus, by processing the remote sensing image data collected by the constellation network and the multivariate information data to generate a comprehensive index table, matching and association between remote sensing image data and historical remote sensing image data can be achieved. This can also be customized based on the retrieval strategy, improving retrieval efficiency, reducing the redundancy of big data, and facilitating automated data mining for batch processing by researchers.

[0048] In the embodiment of the present disclosure, multi-source heterogeneous information labels are established based on remote sensing image data and multi-information data. The remote sensing image data and multi-information data can be normalized according to preset data processing rules to generate multi-source heterogeneous information labels.

[0049] It should be noted that the remote sensing image data and multivariate information data can be calculated using a preset normalization algorithm, and can also be processed using a pre-trained normalization model to obtain multi-source heterogeneous information labels.

[0050] In the above embodiment, a comprehensive index table is established based on multiple heterogeneous information types and preset retrieval strategies, and the search strategy can also be used to Figure 2 Explaining further, the method includes:

[0051] S201 : Select at least one target data tag from multi-source heterogeneous information tags based on a retrieval strategy.

[0052] It should be noted that the search strategy is designed in advance and can be changed according to actual search needs. There can be one or more search strategies, which can be specifically limited according to actual search needs.

[0053] The retrieval strategy can include a single target data tag or multiple target data tags. In one possible implementation, a comprehensive index table can be established using one-to-one and one-to-many association models. This allows for both statistical analysis of data based on a single model and complex statistical analysis based on deep associations across multiple models. The index table can include information such as the satellite name, sensor name, solar altitude, solar azimuth, sensor altitude, sensor azimuth, roll angle, gain, integration level, cloud cover percentage, imaging time, geographic range, and the latitude and longitude of the target center point. This index table can be expanded based on research needs.

[0054] S202: Create a comprehensive index table based on the target data label.

[0055] In the disclosed embodiment, at least one target data tag is first selected from the multi-source heterogeneous information tags based on the search strategy, and then a comprehensive index table is created based on the target data tag. This allows the resulting comprehensive index table to be adjusted based on different search accuracies and requirements, improving the user experience and search results.

[0056] In the above embodiment, multi-source heterogeneous information labels are established based on remote sensing image data and multi-information data, and Figure 3 Explaining further, the method includes:

[0057] S301, obtaining label construction rules.

[0058] S302: Create sub-label data labels for remote sensing image data and multivariate information data based on label construction rules.

[0059] It should be noted that the label construction rules corresponding to different data may be different, and can be set according to actual construction requirements. No limitation is made here.

[0060] For example, satellite names use the satellite number as the partition field, and sensor names use the sensor's English abbreviation as the partition field. This type of data can be used to analyze changes in single satellite or single sensor data and identify changes in the characteristics of different satellites or sensors by determining whether the required data is consistent with the relevant fields in the database.

[0061] Cloud cover percentage uses the percentage of cloud cover covering the geographic area of the scene as the partition key. 10% can be selected as the partition granularity, with a conditional constraint of 10% before and after the desired cloud cover percentage. This can be used to analyze the impact of cloud cover percentage on the accuracy of geometric correction of remote sensing images.

[0062] Sun Altitude uses the specific sun altitude angle as the partition key. You can select 5° as the partition granularity and set the conditional constraint within a range of 5° before and after the desired sun altitude. This can be used to analyze the impact of sun altitude on the accuracy of geometric correction of remote sensing images.

[0063] The roll angle partition key is the specific roll angle. You can select 2° as the partition granularity and set a conditional constraint within a range of 2° before and after the desired roll angle. This can be used to analyze the impact of the roll angle on the accuracy of geometric correction of remote sensing images.

[0064] The gain and integral levels are partitioned by the gears involved in the radiometric calibration, and can be divided into different granularities based on the specific gears set for the payload. This can be used to analyze the impact of different gears for the same payload, or different payloads in the same gear, on the accuracy of geometric correction of remote sensing images.

[0065] Imaging time uses the start / end / target point detection time as the partition key. Imaging time can be partitioned into a first-level range partition by month and a second-level single-value partition by day. This can be used to analyze changes in the geometric correction accuracy of remote sensing images over a time dimension of 24 hours or longer.

[0066] The imaging area uses the four corner points of the detected geographic range or the longitude and latitude of the target center point as the partition key, which can be used to analyze the impact of different terrain types, such as cities, hills, and land-sea boundaries, on the geometric correction accuracy of remote sensing images.

[0067] S303: Establish multi-source heterogeneous information labels for remote sensing image data based on all sub-label data labels.

[0068] In the disclosed embodiment, label construction rules are first obtained. Then, based on the label construction rules, sub-label data labels are created for the remote sensing image data and multi-information data. Finally, multi-source heterogeneous information labels are created for the remote sensing image data based on all sub-label data labels. This not only improves the efficiency of data processing and analysis, but also enhances the ability to understand complex phenomena, providing strong support for scientific research and practical applications, while also providing a data foundation for subsequent retrieval.

[0069] In the above embodiment, the candidate related data are conditionally screened to obtain the target related data. Figure 4 Explaining further, the method includes:

[0070] S401: For any candidate associated data, obtain a screening rule corresponding to the candidate associated data.

[0071] It should be noted that the screening rules are used to ensure the accuracy of the final retrieved data or to constrain the associated data. By setting the screening rules, it is possible to ensure that obviously useless data or erroneous data are screened out.

[0072] S402: Screen candidate related data based on screening rules to obtain target related data.

[0073] By setting filtering rules, you can ensure that obviously useless or erroneous data is filtered out, thereby improving the effectiveness and accuracy of the target related data finally obtained.

[0074] In one possible implementation, the multi-source heterogeneous information can be extracted from the meta files corresponding to each remote sensing image data in a specified database. This information is then preprocessed to form a metadata file with a unified content format. The satellite information is then integrated using string similarity matching. The Jaro similarity is given by the following formula: m is the number of character matches, t is half the number of characters that matched but were in the wrong order, and s1 and s2 are the lengths of the two strings being compared.

[0075]

[0076] The Constellation Remote Sensing Big Data Spatiotemporal Autonomous Association Model filters metadata files in a unified content format one by one according to the variable constraint range. The model then converts the results into a unified binary 0-1 association method based on whether the constraint conditions are met. The association method is as follows: a and b are the constraint boundaries, and x is the data to be filtered.

[0077]

[0078] It should be noted that before filtering candidate related data based on the filtering rules to obtain target related data, the rationality of the filtering rules needs to be judged. On the premise that the filtering rules are judged to be reasonable, the candidate related data are filtered based on the filtering rules.

[0079] In the disclosed embodiment, the target-related data is associated with the recalibration data parameter library. It should be noted that the recalibration data parameter library is a database that stores the retrieval results of the remote sensing image data currently collected by the constellation network, which can be directly retrieved later for comparison and analysis.

[0080] Corresponding to the star cluster networking data association method provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a star cluster networking data association device. Since the star cluster networking data association device provided in the embodiment of the present disclosure corresponds to the star cluster networking data association method provided in the above-mentioned embodiments, the implementation method of the above-mentioned star cluster networking data association method is also applicable to the star cluster networking data association device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0081] Figure 5 FIG. 1 is a schematic diagram of a data association device for a constellation network according to an embodiment of the present disclosure. Figure 5As shown, the constellation network data association device 500 includes: an acquisition module 510 , a construction module 520 , a building module 530 and a retrieval module 540 .

[0082] The acquisition module 510 is used to acquire the remote sensing image data collected by the constellation network and the multivariate information data corresponding to the remote sensing image data.

[0083] The construction module 520 is used to establish multi-source heterogeneous information labels based on remote sensing image data and multi-information data.

[0084] The establishment module 530 is used to establish a comprehensive index table based on multiple heterogeneous information types and a preset retrieval strategy.

[0085] The retrieval module 540 is used to input the comprehensive index table into the big data spatiotemporal autonomous association model to retrieve candidate association data and perform conditional screening on the candidate association data to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the constellation network.

[0086] According to one embodiment of the present disclosure, a comprehensive index table is established based on multi-source heterogeneous information classes and a preset retrieval strategy, including: selecting at least one target data tag from multi-source heterogeneous information tags based on the retrieval strategy; and establishing a comprehensive index table based on the target data tag.

[0087] According to one embodiment of the present disclosure, establishing multi-source heterogeneous information labels based on remote sensing image data and multi-information data also includes: obtaining label construction rules; establishing sub-label data labels for remote sensing image data and multi-information data based on the label construction rules; and establishing multi-source heterogeneous information labels for remote sensing image data based on all sub-label data labels.

[0088] According to an embodiment of the present disclosure, conditional screening is performed on candidate association data to obtain target association data, including: obtaining a screening rule corresponding to any candidate association data; and screening the candidate association data based on the screening rule to obtain the target association data.

[0089] According to an embodiment of the present disclosure, before screening candidate associated data based on screening rules to obtain target associated data, the method further includes: judging the rationality of the screening rules; and judging that the screening rules are rational.

[0090] According to one embodiment of the present disclosure, multi-source heterogeneous information labels are established based on remote sensing image data and multi-information data, including: normalizing the remote sensing image data and the multi-information data according to preset data processing rules to generate multi-source heterogeneous information labels.

[0091] According to one embodiment of the present disclosure, the target-related data is associated with a recalibration data parameter library.

[0092] Therefore, by processing the remote sensing image data and multivariate information data collected by the constellation network to generate a comprehensive index table, it is possible to match and associate the remote sensing image data with the historical remote sensing image data, and it can be customized according to the retrieval strategy, which improves the retrieval efficiency, reduces the redundancy of big data, and facilitates researchers to carry out automated data mining work for batch processing.

[0093] In order to implement the above embodiment, the present disclosure further provides an electronic device 600. Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure, such as Figure 6 As shown, the electronic device 600 includes: a processor 601 and a memory 602 in communication with the processor, the memory 602 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 601 to implement the present disclosure. Figure 1-Figure 4 A method for associating data in a constellation network according to an embodiment.

[0094] In order to implement the above embodiment, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the above embodiment. Figure 1-Figure 4 A method for associating data in a constellation network according to an embodiment.

[0095] In order to implement the above embodiments, the present disclosure also provides a computer program product, including a computer program, which implements the above embodiments when executed by a processor. Figure 1-Figure 4 A method for associating data in a constellation network according to an embodiment.

[0096] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0097] This application contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0098] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0099] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0100] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0101] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0102] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0104] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0105] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for associating data in a constellation network, characterized in that: include: Acquire remote sensing image data collected by the constellation network and multivariate information data corresponding to the remote sensing image data; Establishing multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data; Establishing a comprehensive index table based on the multi-dimensional heterogeneous information class and the preset retrieval strategy; The comprehensive index table is input into a big data spatiotemporal autonomous association model to retrieve candidate association data, and the candidate association data is conditionally screened to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the constellation network.

2. The method according to claim 1, characterized in that The establishing of a comprehensive index table based on the multi-dimensional heterogeneous information class and the preset retrieval strategy includes: Selecting at least one target data tag from the multi-source heterogeneous information tags based on the retrieval strategy; The comprehensive index table is established based on the target data tag.

3. The method according to claim 1 or 2, characterized in that The establishing of multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data further includes: Get label building rules; Establishing sub-label data labels for the remote sensing image data and the multivariate information data based on the label construction rule; Multi-source heterogeneous information labels of the remote sensing image data are established based on all sub-label data labels.

4. The method according to claim 1, wherein The conditionally screening the candidate associated data to obtain target associated data includes: For any candidate associated data, obtaining a screening rule corresponding to the candidate associated data; The candidate associated data are screened based on the screening rule to obtain the target associated data.

5. The method according to claim 4, characterized in that Before filtering the candidate associated data based on the filtering rule to obtain the target associated data, the method further includes: Making a reasonable judgment on the screening rules; It is determined that the screening rules are reasonable.

6. The method according to claim 4, characterized in that The method further comprises: The target associated data is associated with a recalibration data parameter library.

7. The method according to claim 1, characterized in that The establishing of multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data includes: The remote sensing image data and the multivariate information data are normalized according to preset data processing rules to generate the multi-source heterogeneous information labels.

8. A data association device for a constellation network, characterized in that: include: An acquisition module, configured to acquire remote sensing image data collected by the constellation network and multivariate information data corresponding to the remote sensing image data; A construction module, configured to establish multi-source heterogeneous information labels based on the remote sensing image data and the multivariate information data; An establishment module for establishing a comprehensive index table based on the multi-dimensional heterogeneous information class and a preset retrieval strategy; A retrieval module is used to input the comprehensive index table into a big data spatiotemporal autonomous association model to retrieve candidate association data and perform conditional screening on the candidate association data to obtain target association data, wherein the big data spatiotemporal autonomous association model stores historical remote sensing image data of the constellation network.

9. An electronic device, characterized in that: Including memory and processor; The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images