Geospatial information acquisition method and device, electronic equipment and storage medium

Abstract

The invention provides a geospatial intelligence acquisition method and device, electronic equipment and a storage medium, and relates to the technical field of geospatial intelligence, and the method comprises the steps: receiving description information related to a to-be-acquired intelligence; according to the description information, geographic space event information related to the description information is extracted from a data set of the multiple data sources, and multiple geographic space event information corresponding to the multiple data sources one to one is obtained; and generating geospatial intelligence under each data source according to various geospatial event information. According to the method, the efficiency of obtaining the geospatial information from the multi-source data can be improved, manual errors are reduced, and the obtained geospatial information is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the field of geospatial intelligence technology, and in particular to a geospatial intelligence acquisition method and device, electronic equipment and storage medium. Background Art

[0002] With the advancement of technology, the field of geospatial intelligence faces the challenges of data diversity and massiveness. Data sources are extensive, including satellite remote sensing images, drone aerial photography, social media content, sensor networks, and traditional media information. These data are not only huge in quantity, but also in different formats. Structured data represented by geographic information and target positioning, and unstructured data represented by video, images, audio, and text, the difference in data format makes data processing much more difficult. At the same time, the demand for real-time is growing, especially in the fields of military operations and disaster response, which require fast and accurate intelligence support. Traditional manual analysis methods can no longer meet this requirement.

[0003] Faced with massive amounts of data, precision and accuracy are the key to geospatial intelligence, and erroneous information can lead to serious consequences. For example, in target identification and terrain analysis, high-precision data is essential for formulating effective action plans. Therefore, the efficiency and accuracy of manually processing massive amounts of heterogeneous data to obtain geospatial intelligence can no longer meet the needs of current actual conditions. Summary of the invention

[0004] The present invention provides a method and device for acquiring geospatial intelligence, an electronic device and a storage medium, which are used to solve the defects of low accuracy and efficiency in acquiring geospatial intelligence from multi-source data based on manual processing in the prior art, and can improve the efficiency of acquiring geospatial intelligence, reduce manual errors, and make the acquired geospatial intelligence more accurate and reliable.

[0005] The present invention provides a method for acquiring geospatial intelligence, comprising the following steps.

[0006] Receive descriptive information related to the intelligence to be obtained; extract geospatial event information related to the descriptive information from data sets of multiple target data sources based on the descriptive information, and obtain multiple geospatial event information corresponding to the multiple target data sources one by one; generate geospatial intelligence under each data source based on the multiple geospatial event information.

[0007] According to a method for acquiring geospatial intelligence provided by the present invention, after generating geospatial intelligence under each data source based on multiple geospatial event information, the method also includes: generating geospatial prediction intelligence based on the geospatial intelligence under each data source; and outputting the geospatial prediction intelligence.

[0008] According to a method for acquiring geospatial intelligence provided by the present invention, after generating geospatial prediction intelligence based on the geospatial intelligence under each data source, the method further includes: analyzing the probability of occurrence of warning events based on the geospatial prediction intelligence and pre-set warning event information; and issuing an alarm when the probability of occurrence is greater than a set threshold.

[0009] According to a method for acquiring geospatial intelligence provided by the present invention, after generating geospatial intelligence under each data source based on multiple geospatial event information, the method further includes: generating intelligence recommendation information based on the geospatial intelligence under each data source; and outputting the intelligence recommendation information.

[0010] According to a method for acquiring geospatial intelligence provided by the present invention, geospatial event information related to the description information is extracted from data sets of multiple target data sources based on the description information, so as to obtain multiple geospatial event information corresponding to the multiple target data sources one by one, including: selecting multiple target data sources from multiple preset data sources as multiple data sources based on the received data source selection indication information; acquiring data sets of multiple data sources from the multiple data sources based on the data acquisition method corresponding to each of the multiple data sources; preprocessing the data set of the corresponding data source based on the preprocessing method corresponding to each data source; extracting initial processing information from the preprocessing result of the data set of each data source; and entity linking the initial processing information of each data source to obtain multiple geospatial event information.

[0011] According to a method for acquiring geographic space intelligence provided by the present invention, the geographic space intelligence includes: time, geographic location and occurred events.

[0012] The present invention also provides a device for acquiring geographic space intelligence, comprising the following modules: a receiving module, an extracting module, a generating module and an output module.

[0013] The receiving module is used to receive descriptive information related to the intelligence to be obtained.

[0014] The extraction module is used to extract geographic space event information related to the description information from data sets of multiple data sources according to the description information, and obtain multiple geographic space event information corresponding to multiple data sources one by one.

[0015] The generation module is used to generate geospatial intelligence under each data source based on various geospatial event information.

[0016] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, it implements any of the above-mentioned methods for acquiring geospatial intelligence.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for acquiring geospatial intelligence.

[0018] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for acquiring geospatial intelligence as described above is implemented.

[0019] The geospatial intelligence acquisition method and device, electronic device and storage medium provided by the present invention receive description information related to the intelligence to be acquired; extract geospatial event information related to the description information from data sets of multiple data sources based on the description information, and obtain multiple geospatial event information corresponding to multiple data sources one by one; and generate geospatial intelligence under each data source based on the multiple geospatial event information. It can be seen that the present invention can automatically extract geospatial event information corresponding to the data source from multiple data sources, and generate corresponding geospatial intelligence based on the geospatial event information corresponding to each data source, so as to solve the problem of low accuracy and efficiency of obtaining geospatial intelligence from multi-source data based on manual processing in the prior art, improve the efficiency of obtaining geospatial intelligence from multi-source data, reduce manual errors, and make the obtained geospatial intelligence more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is one of the flow charts of the method for acquiring geospatial intelligence provided by the present invention.

[0022] Figure 2 The geospatial intelligence acquisition method provided by the present invention acquires multiple geospatial event information corresponding to multiple data sources.

[0023] Figure 3 It is a schematic diagram of outputting the geospatial intelligence under each data source in the geospatial intelligence acquisition method provided by the present invention.

[0024] Figure 4 This is the second flow chart of the method for acquiring geospatial intelligence provided by the present invention.

[0025] Figure 5 This is the third flow chart of the method for acquiring geospatial intelligence provided by the present invention.

[0026] Figure 6 This is the fourth flow chart of the method for acquiring geospatial intelligence provided by the present invention.

[0027] Figure 7 It is a structural schematic diagram of the geospatial intelligence acquisition device provided by the present invention.

[0028] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Among related technologies, breakthroughs in deep learning, natural language processing (NLP), and computer vision have provided new possibilities for the automatic extraction of multi-source heterogeneous data. These technologies can autonomously learn how to more effectively extract valuable knowledge points from different types of raw data, improving the accuracy and efficiency of data processing.

[0031] Combine the following Figure 1-Figure 6 The geospatial intelligence acquisition method of the present invention is described.

[0032] Figure 1 It is one of the flow charts of the method for obtaining geospatial intelligence provided by the present invention, such as Figure 1 As shown, the method includes the following S110~S130.

[0033] S110: Receive description information related to the intelligence to be obtained.

[0034] The descriptive information related to the intelligence to be obtained includes, for example, time information, geographic location description information, geospatial event keywords, etc. related to the intelligence to be obtained.

[0035] Time information can be, for example, a certain time period. For example, if you want to obtain geospatial intelligence for a certain time period, you can enter the start date and end date of this time period, and the start date and end date are the time information. Time information can also be a specific time point, such as XXXX year X month X day XX time, etc.

[0036] Geographic location description information such as longitude and latitude, or geographical area name (such as XX sea area), etc.

[0037] Geospatial event keywords are keywords that can describe geospatial events, such as keywords related to military operations such as patrol ship escort and illegal entry into territorial waters, and keywords for natural disasters such as tsunamis, red tides, seawater intrusion, oil spills, etc.

[0038] The type of description information of the intelligence to be obtained may include any of the following: text and image. Of course, it can be understood that the types of description information listed above are only exemplary, and the types of description information of the intelligence to be obtained in the embodiment of the present invention include but are not limited to text and image, and may also be voice.

[0039] S120: Extracting geographic space event information related to the description information from the acquired data sets of the multiple data sources according to the description information, and obtaining multiple geographic space event information corresponding to the multiple data sources one by one.

[0040] In some embodiments, multiple target data sources can be selected from multiple preset data sources as the multiple data according to the received data source selection indication information; then, data sets of multiple data sources are obtained from the multiple data sources according to the data acquisition method corresponding to each of the multiple data sources; then, geospatial event information is extracted from the data sets of each data source. The data source selection indication information carries the identifiers of multiple target data sources, so that multiple target data sources can be selected from multiple preset data sources. The data source selection indication information can be generated according to the user's selection operation on multiple preset data sources.

[0041] In some embodiments, in order to obtain more accurate data, after obtaining data sets from multiple data sources, the corresponding data sets can be preprocessed according to the preprocessing method corresponding to each data source; then, initial processing information is extracted from the preprocessing results of each data set; finally, the initial processing information of each data source is entity linked to obtain the geospatial event information corresponding to each data source.

[0042] The following describes the acquisition process of the above-mentioned data set, the preprocessing process of preprocessing the data set of the corresponding data source, the information extraction process and the entity linking process.

[0043] like Figure 2 As shown, the various preset data sources may include: news web page data, social media data, remote sensing image data, drone aerial photography data, etc.

[0044] The multiple data sources can be selected by the user from multiple preset data sources according to actual conditions. Of course, the multiple preset data sources can also be defaulted to be the multiple target data sources.

[0045] Assume that the target data sources we select from multiple preset data sources include: news web page data, social media data, remote sensing image data, and drone aerial photography data. The following uses these four data sources as examples to illustrate the process of obtaining multiple geospatial event information.

[0046] Specifically, news web page data may include, for example, text, pictures, videos, location information, and other data in news web pages issued on various news platforms on the Internet. Social media data may include, for example, text, pictures, videos, location information, and other data on chat software and social media platforms. Remote sensing image data may include, for example, optical images, synthetic aperture radar images, multispectral / hyperspectral images, and other image data; drone aerial photography data may include, for example, infrared images and lidar data.

[0047] The data sets from various data sources can be obtained in different ways. For example, for social media data and news web page data, see Figure 2 , data sets can be acquired through multimodal web page data extraction technology, based on rule template information extraction (a predefined rule framework used to regulate the content and type of information to be obtained (such as pictures or text), etc.), and combining text information and visual information extraction.

[0048] For news web page data and social media data, a general first information extraction model can be constructed using a deep neural network. Visual information and text information are combined, for example, the text information of the web page DOM tree (Document Object ModelTree) and the visual structure information generated by the WEB rendering engine are combined and mapped to a deep neural network for encoding. The key information related to the descriptive information in the news web page (title, content, time, author, category, etc.) is uniformly identified and extracted to obtain an intelligent general parser for heterogeneous data in different web pages, that is, the above-mentioned first information extraction model. Based on the first information extraction module, the news web page data is intelligently extracted, and a data set related to the descriptive information obtained in S110 is extracted from the news web page data and social media data.

[0049] See also Figure 2For remote sensing image data and drone aerial photography data, the corresponding data sets can be obtained through the Application Programming Interface (API) interface or transmission dedicated line. For open data sets such as Landsat, Sentinel, Moderate Resolution Imaging Spectroradiometer (MODIS), etc., the API interface is used to call from related devices; for national or regional data centers, remote sensing image data and drone aerial photography data sets can be obtained from related devices through transmission dedicated lines.

[0050] After obtaining data sets from multiple data sources, in order to filter out unnecessary, useless or mixed noise data, preprocessing can be performed on the data sets obtained from each data source.

[0051] Different preprocessing methods can be used to preprocess data sets from different data sources.

[0052] See also Figure 2 ,For preprocessing the data sets obtained from news web page data and social media data, the preprocessing methods that can be adopted include at least one of the following: missing value processing, removing out-of-bounds values, consistency checking, deleting duplicate values, labeling processing, and formatting.

[0053] Specifically, the missing value processing method is used to handle missing values ​​in the data set, such as using the mean, median, interpolation or prediction model to fill in missing values. The out-of-bounds value removal method is to define a reasonable threshold, detect out-of-range data points in the data set, and delete, replace or mark the out-of-range data points. The consistency check method is used to ensure the consistency of all data in the data set in terms of format, unit and logic. For example, for dates in the data set, all dates are unified in the format of YYYY-MM-DD, the numerical units in the data set are checked, the consistency of cross-table association fields is ensured, and so on. The duplicate value removal method ensures the uniqueness of the data and deletes redundant data by identifying and deleting duplicate records in the data set. The labeling processing method converts categorical variables in data analysis and machine learning into numerical form. For text data, word segmentation, stem extraction and word embedding are performed; formatting includes unifying data formats (such as date and numerical formats), standardizing or normalizing data, and saving data in a set file format.

[0054] See also Figure 2 , for preprocessing the data sets obtained from remote sensing image data and drone aerial photography data, the preprocessing methods that can be used include at least one of the following: image orthorectification, image registration, image fusion, and image mosaic process.

[0055] Specifically, the image orthorectification method uses a data automation processing platform to select control points from the data set, perform regional network joint adjustment on the panchromatic data in the work area, remove and adjust the control points with large residuals, and automatically extract the same-name points in the overlapping areas between scenes on the basis that the control points of each scene meet the regional network error requirements, and remove the same-name points with large residuals until the same-name point errors meet the specified requirements. The image registration method uses the orthorectified panchromatic band image as the control basis, and uses the same-name points of the panchromatic image to register and correct the multispectral data. Image fusion is to fuse high-resolution panchromatic remote sensing images with low-resolution multispectral remote sensing images to obtain fused images with rich color information and high resolution, highlighting the information of ground features. Image mosaicking uses mosaic lines to mosaic the fused digital orthophoto map (DOM) images, and evenly processes the images between adjacent mosaicking areas to keep the color transition between scenes natural, the ground features reasonably connected, and no ghosting or blurring.

[0056] When extracting geospatial event information related to descriptive information from data sets of multiple data sources, the following methods can be used for extraction.

[0057] See also Figure 2 ,For the datasets obtained from news web pages data and social media data, ,entity recognition, relationship extraction and feature extraction can be used to ,extract geospatial event information.

[0058] For example, a joint model that combines a statistical machine learning method based on cascaded conditional random fields with a recognition method based on rule probability automatically identifies named entities of the required category from the input text (i.e., the data set input to the joint model), and then determines the category to which the entity belongs, completing the entity recognition process; a remote supervised relationship extraction method that combines a gated recurrent unit (GRU) neural network and an attention mechanism is used to extract entity relationships, completing the relationship extraction process; and then term frequency-inverse document frequency (TF-IDF) is used for feature extraction, including lexical features, syntactic features, and semantic features, to complete the feature extraction process and obtain the geospatial event information corresponding to the news web page data and social media data.

[0059] See also Figure 2 ,For the data sets obtained from remote sensing image data and ,UAV aerial photography data, feature pyramid construction and target recognition can ,be used to extract geospatial event information.

[0060] For example, a dynamic multi-scale feature pyramid structure can be constructed, and the input feature map can be trained using the anchor mechanism and the regression box mechanism to obtain the candidate box. The multi-scale feature map obtained by adding high-level semantic information and low-level detail information can take into account both category information and location information, and the category information and location information can be determined as the geographic spatial event information corresponding to the remote sensing image data.

[0061] For the geospatial event information of each data source extracted as above, in order to further improve the accuracy of the geospatial event information, the geospatial event information of each data source can be used as the initial processing information of the data source, and the initial processing information can be entity linked to obtain the final geospatial event information of the data source.

[0062] See also Figure 2 , multimodal entity linking can be used to supplement the missing contextual information of the text modality and use implicit reasoning information to help eliminate the ambiguity of text entities. Among them, the processing method of entity linking includes at least one of the following: candidate entity generation, entity disambiguation, and fuzzy reference recognition. Candidate entity generation obtains the multimodal knowledge graph of geospatial event information through a multimodal clustering algorithm, and divides the data samples in the multimodal knowledge graph that are similar to the retrieval data (descriptive information related to the intelligence to be obtained) into the same cluster, so that the similarity between data points in the same cluster is maximized, and the similarity between data points in different clusters is minimized. The entity data in the same cluster is the candidate entity set. The purpose is to calculate the similarity between the retrieval entity (the entity of the descriptive information related to the intelligence to be obtained) and the entities in the candidate entity set (geospatial event information). Entity disambiguation converts multimodal entities into vector representations, fuses the feature vectors of each modality into a comprehensive multimodal feature vector, and finally uses a deep neural network to map the fused multimodal feature vector into a unified vector space. Through similarity calculation, the candidate entity with the highest similarity score is selected as the final disambiguation result to complete the entity linking work and ultimately obtain the geospatial event information corresponding to each data source.

[0063] S130: Generate geospatial intelligence for each data source based on multiple geospatial event information.

[0064] Geospatial intelligence can include: time, geographic location, and events. Geographic location can include longitude and latitude, or other geographic coordinate information located in other ways.

[0065] The time, geographical location and the event occurring at the geographical location at the time are extracted from a variety of geographical space event information as an occurrence event, and the time, geographical location and occurrence event are associated to obtain geographical space intelligence.

[0066] Through S110~S130, multiple geospatial event information corresponding to multiple data sources can be automatically extracted from sources with wide range, complex structures and a large amount of implicit information, and finally geospatial intelligence under each data source can be generated based on the multiple geospatial event information.

[0067] In some embodiments, after the geospatial intelligence under each data source is generated, the geospatial intelligence under each data source can be directly output.

[0068] For example, the geospatial intelligence under each data source can be displayed in a set display mode on the terminal. Figure 3 As shown in the table, each row of the table includes time, geographic location and event, corresponding to a set of intelligence information, and multiple sets of intelligence information are generated in chronological order and arranged in chronological order.

[0069] Of course, it is understandable that Figure 3 Only one display method of geospatial intelligence is used as an example. In specific implementations, the display method of geospatial intelligence includes but is not limited to Figure 3 For example, the relationship between multiple intelligence information can be analyzed to generate a relationship diagram between multiple groups of intelligence information to assist users in analyzing the correlation between multiple groups of intelligence information.

[0070] In some embodiments, Figure 4 As shown, after executing S130, the following S410~S420 may also be executed.

[0071] S410: Generate geospatial predictive intelligence based on the geospatial intelligence under each data source.

[0072] The initial intelligence prediction model can be trained based on the geospatial intelligence from all previously acquired data sources to obtain the target intelligence prediction model.

[0073] The geospatial intelligence currently obtained under each data source is input into the target intelligence prediction model to obtain the geospatial prediction intelligence output by the target intelligence prediction model.

[0074] S420: Output geospatial prediction intelligence.

[0075] The geospatial prediction intelligence is displayed in the display interface of the terminal.

[0076] In some implementations, such as Figure 5 As shown, after executing S130, the following S510~S520 may also be executed.

[0077] S510: Analyze the probability of occurrence of warning events based on geospatial prediction intelligence and pre-set warning event information.

[0078] Warning event information may include warning keywords, warning pictures, etc., and the probability of occurrence of warning events may be analyzed by, for example, calculating the similarity between geospatial prediction intelligence and warning event information, and determining the similarity as the probability of occurrence of warning events.

[0079] S520: When the probability of occurrence is greater than a set threshold, an alarm is issued.

[0080] The threshold value may be set by those skilled in the art according to actual conditions, and the embodiment of the present invention does not limit this.

[0081] In some implementations, such as Figure 6 As shown, after executing S130, the following S610~S620 may also be executed.

[0082] S610: Generate intelligence recommendation information based on the geospatial intelligence under each data source.

[0083] Intelligence recommendation information may include, for example, high-frequency events at the geographical location of geospatial intelligence, or high-profile events at the geographical location, and other related information of events that need to attract the user's attention.

[0084] S620: Output intelligence recommendation information.

[0085] The present invention proposes to construct an automatic knowledge extraction method for multi-source heterogeneous data in the field of geospatial intelligence based on multi-source heterogeneous data such as remote sensing image data, drone aerial photography data, social media data, sensor network data, etc., using deep learning, natural language processing (NLP), knowledge graphs, computer vision and other technologies, to integrate different types of data such as text, pictures, videos, etc. across modalities, improve data processing efficiency and quality, and enhance the analysis capability of geospatial intelligence.

[0086] The method for acquiring geospatial intelligence provided by the present invention receives descriptive information related to the intelligence to be acquired; extracts geospatial event information related to the descriptive information from data sets of multiple data sources based on the descriptive information, and obtains multiple geospatial event information corresponding to the multiple data sources one by one; and generates geospatial intelligence under each data source based on the multiple geospatial event information. It can be seen that the present invention can automatically extract the geospatial event information corresponding to the data source from multiple data sources, generate the geospatial intelligence of the data source based on the geospatial event information corresponding to each data source, and output the geospatial intelligence under each data source, so as to solve the problem of low accuracy and efficiency of acquiring geospatial intelligence from multi-source data based on manual processing in the prior art, improve the efficiency of acquiring geospatial intelligence from multi-source data, reduce manual errors, and make the acquired geospatial intelligence more accurate and reliable.

[0087] The geospatial intelligence acquisition device provided by the present invention is described below. The geospatial intelligence acquisition device described below and the geospatial intelligence acquisition method described above can be referenced to each other.

[0088] Figure 7 Schematic diagram of the structure of the device for acquiring geographic spatial intelligence provided by the present invention. Figure 7 As shown, the geographic spatial intelligence acquisition device 700 includes a receiving module 701, an extraction module 702, and a generation module 703.

[0089] The receiving module 701 is used to receive description information related to the intelligence to be obtained.

[0090] The extraction module 702 is used to extract geographic space event information related to the description information from data sets of multiple data sources according to the description information, and obtain multiple geographic space event information corresponding to multiple data sources one by one.

[0091] The generation module 703 is used to generate geospatial intelligence under each data source according to various geospatial event information.

[0092] In some embodiments, the geospatial intelligence acquisition device 700 further includes: an output module ( Figure 7 ), which is used to output geospatial intelligence under each data source.

[0093] In some embodiments, the geospatial intelligence acquisition device 700 further includes: a prediction information generation module ( Figure 7 Not shown) and the prediction information output module ( Figure 7 not shown).

[0094] The prediction information generation module is used to generate module 703 to generate geospatial prediction intelligence based on the geospatial intelligence under each data source according to various geospatial event information.

[0095] The prediction information output module is used to output geospatial prediction intelligence.

[0096] In some embodiments, the geospatial intelligence acquisition device 700 further includes: an analysis module ( Figure 7 Not shown) and the alarm module ( Figure 7 not shown).

[0097] The analysis module is used to analyze the probability of occurrence of warning events according to the geospatial prediction intelligence and pre-set warning event information after the prediction information generation module generates geospatial prediction intelligence according to the geospatial prediction intelligence under each data source.

[0098] The alarm module is used to issue an alarm when the probability of occurrence is greater than a set threshold.

[0099] In some embodiments, the geospatial intelligence acquisition device 700 further includes: a recommendation information generation module ( Figure 7 ) and the recommendation information output module ( Figure 7 not shown).

[0100] The recommendation information generation module is used to generate the intelligence recommendation information according to the geospatial intelligence under each data source after the generation module 703 generates the geospatial intelligence under each data source according to the various geospatial event information.

[0101] The recommendation information output module is used to output intelligence recommendation information.

[0102] In some embodiments, the extraction module 702 is specifically used to: select multiple target data sources from multiple preset data sources as multiple data sources according to the received data source selection indication information; obtain data sets of multiple data sources from the multiple data sources according to the data acquisition method corresponding to each of the multiple data sources; preprocess the data set of the corresponding data source according to the preprocessing method corresponding to each data source; extract initial processing information from the preprocessing result of the data set of each data source; and perform entity linking on the initial processing information of each data source to obtain multiple geographic spatial event information.

[0103] In some embodiments, geospatial intelligence includes: time, geographic location, and occurrence of events.

[0104] The geospatial intelligence acquisition device provided by the present invention receives description information related to the intelligence to be acquired; extracts geospatial event information related to the description information from data sets of multiple data sources based on the description information, and obtains multiple geospatial event information corresponding to the multiple data sources one by one; and generates geospatial intelligence under each data source based on the multiple geospatial event information. It can be seen that the present invention can automatically extract the geospatial event information corresponding to the data source from multiple data sources, and generate the geospatial intelligence of the data source based on the geospatial event information corresponding to each data source, so as to solve the problem of low accuracy and efficiency of obtaining geospatial intelligence from multi-source data based on manual processing in the prior art, and can improve the efficiency of obtaining geospatial intelligence from multi-source data, reduce manual errors, and make the obtained geospatial intelligence more accurate and reliable.

[0105] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the geospatial intelligence acquisition method, which includes: receiving description information related to the intelligence to be acquired; extracting geospatial event information related to the description information from data sets of multiple data sources according to the description information, and obtaining multiple geospatial event information corresponding to multiple data sources one by one; generating geospatial intelligence under each data source according to the multiple geospatial event information.

[0106] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0107] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the geospatial intelligence acquisition method provided by the above-mentioned methods, which includes: receiving descriptive information related to the intelligence to be acquired; based on the descriptive information, extracting geospatial event information related to the descriptive information from data sets of multiple data sources, and obtaining multiple geospatial event information corresponding to the multiple data sources one by one; based on the multiple geospatial event information, generating geospatial intelligence under each data source.

[0108] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the geospatial intelligence acquisition method provided by the above-mentioned methods, the method comprising: receiving descriptive information related to the intelligence to be acquired; based on the descriptive information, extracting geospatial event information related to the descriptive information from data sets of multiple data sources, and obtaining multiple geospatial event information corresponding to the multiple data sources one by one; based on the multiple geospatial event information, generating geospatial intelligence under each data source.

[0109] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for acquiring geospatial intelligence, characterized in that: include: Receive descriptive information related to the intelligence to be acquired; Extracting, according to the description information, geographic space event information related to the description information from data sets of multiple data sources, and obtaining multiple geographic space event information corresponding to the multiple data sources one by one; Based on the multiple geospatial event information, geospatial intelligence is generated under each data source.

2. The method for acquiring geospatial intelligence according to claim 1, characterized in that: After generating geospatial intelligence under each data source according to the multiple geospatial event information, the method further includes: Generating geospatial predictive intelligence based on the geospatial intelligence under each of the data sources; The geospatial predictive intelligence is output.

3. The method for acquiring geospatial intelligence according to claim 2, characterized in that: After generating geospatial prediction intelligence according to the geospatial intelligence under each of the data sources, the method further includes: Analyze the probability of occurrence of warning events based on the geospatial prediction intelligence and pre-set warning event information; When the occurrence probability is greater than a set threshold, an alarm is issued.

4. The method for acquiring geospatial intelligence according to claim 1, characterized in that: After generating geospatial intelligence under each data source according to the multiple geospatial event information, the method further includes: Generate intelligence recommendation information based on the geospatial intelligence under each of the data sources; Output the intelligence recommendation information.

5. The method for acquiring geospatial intelligence according to any one of claims 1 to 4, characterized in that: The extracting, according to the description information, geospatial event information related to the description information from data sets of multiple data sources to obtain multiple geospatial event information corresponding to the multiple data sources, includes: According to the received data source selection indication information, select multiple target data sources from multiple preset data sources as the multiple data sources; Acquire data sets of the multiple data sources from the multiple data sources according to a data acquisition method corresponding to each of the multiple data sources; Preprocessing the corresponding data set of the data source according to the preprocessing method corresponding to each data source; Extracting initial processing information from the preprocessing results of the data sets of each of the data sources; Entity linking is performed on the initial processing information of each of the data sources to obtain the multiple types of geospatial event information.

6. The method for acquiring geospatial intelligence according to any one of claims 1 to 4, characterized in that: The geospatial intelligence includes: time, geographic location and events.

7. A device for acquiring geospatial intelligence, characterized in that: include: A receiving module, used for receiving description information related to the intelligence to be acquired; An extraction module, configured to extract, according to the description information, geographic space event information related to the description information from data sets of multiple data sources, and obtain multiple geographic space event information corresponding to the multiple data sources one by one; A generation module is used to generate geospatial intelligence under each data source based on the multiple geospatial event information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, it implements the method for acquiring geospatial intelligence as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for acquiring geospatial intelligence as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for acquiring geospatial intelligence as described in any one of claims 1 to 6 is implemented.

Images