A remote sensing data retrieval method based on artificial intelligence

Abstract

The present invention discloses a remote sensing data retrieval method based on artificial intelligence. In an established local retrieval database model, remote sensing data information of various places is classified, including: land data unit group, forest data unit group, grassland data unit group and wetland data unit group. In the retrieval process, the present invention classifies the retrieval information in the retrieval database model. In addition, before the retrieval keyword is input, the different semantics of the retrieval keyword are parsed to ensure that the keyword information with different semantics can be retrieved, and the keyword information with different semantics is classified. Through the classification matching retrieval method, in the retrieval process, only the corresponding keyword information needs to be searched in the corresponding category, so as to improve the speed and efficiency of the retrieval result, and avoid the diversity of the retrieval result, which causes the trouble of subsequent screening and elimination.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a remote sensing data retrieval method based on artificial intelligence. Background Art

[0002] With the advancement of technology, satellite remote sensing image data is applied in more and more industries and fields. Remote sensing data usually refers to data about remote sensing maps or remote sensing images. In remote sensing, in addition to quantitative data, there are a lot of descriptions of geographical concepts and remote sensing methods, which can be collectively referred to as remote sensing knowledge. The "remote sensing knowledge" here is not remote sensing common sense, but information in computer information science.

[0003] There are many ways to collect remote sensing data in modern times, and the storage media and access methods of remote sensing data collected in different ways are also very different. Therefore, it is necessary to use retrieval methods to retrieve relevant information from a large number of remote sensing data. The traditional retrieval method is to enter the search keywords into the retrieval database for retrieval. However, due to the huge amount of information in the database, the detection process is very slow, and there are usually multiple retrieval information results that match the search keywords, which need to be screened and eliminated one by one after the retrieval, reducing the efficiency of data retrieval. Summary of the invention

[0004] The present invention provides a remote sensing data retrieval method based on artificial intelligence, which can effectively solve the problem that the traditional retrieval method proposed in the above background technology is to input the retrieval keywords into the retrieval database for retrieval, but due to the huge amount of information in the database, the detection process is very slow, and there are usually multiple retrieval information results that match the retrieval keywords, which need to be screened and eliminated one by one after the retrieval, reducing the efficiency of data retrieval.

[0005] To achieve the above object, the present invention provides the following technical solution: a remote sensing data retrieval method based on artificial intelligence, comprising the following steps:

[0006] S1. Obtain all remote sensing data information based on artificial intelligence;

[0007] S2, unifying the format of the acquired remote sensing data information;

[0008] S3, establishing a retrieval database model with the processed remote sensing data information;

[0009] S4, classifying the retrieved remote sensing data information in the retrieval database model;

[0010] S5. Obtain the user's search request information and extract the search keywords in the search request information;

[0011] S6. Mining the semantics of keywords based on the search keywords, and analyzing the mined semantics of the keywords;

[0012] S7, grouping the analyzed keyword semantics and establishing semantic groups;

[0013] S8, matching corresponding search;

[0014] S9. Extract and parse the retrieval information.

[0015] Based on the above technical solution, in step S1, the remote sensing data in each remote remote sensing data center is stored in a local database to establish a local database;

[0016] In step S2, the remote sensing center data in different formats uploaded from different locations are unified in format through erdas, envi and ArcGIS software, so that the remote sensing data from different locations are all in a unified format in the local database;

[0017] In step S3, the remote sensing data from various locations are uniformly formatted and retransmitted to the local database, and a local retrieval database model is established.

[0018] Based on the above technical solution, in step S4, the remote sensing data information of each remote location is classified in the established local retrieval database model, including: land data unit group, forest data unit group, grassland data unit group and wetland data unit group, and the land data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the forest data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the grassland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the wetland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group.

[0019] Based on the above technical solution, in step S5, the search input module is used to facilitate the user to input the search information requested by the user, the recognition module is used to obtain the search request information input by the user, and the obtained search information is identified, and finally the search keywords in the identified search request information are filtered and extracted through the screening module.

[0020] Based on the above technical solution, in step S6, after the screening module extracts the keywords in the search request information, the information processing module is used to mine and extract the semantics of the search keywords, and after the semantics of the search keywords are determined, the analysis module is used to analyze the different semantics of the search keywords;

[0021] In step S7, after the analysis module distinguishes the different semantics of the search keywords, a semantic group is established in the search input module, and the search keywords with different semantics are divided into: a first semantic search condition group, a second semantic search condition group and a third semantic search condition group in the semantic group.

[0022] Based on the above technical solution, in step S8, the matching corresponding search specifically includes the following search steps:

[0023] A. inputting the first semantic search condition group into the local search database model;

[0024] B. inputting the second semantic search condition group into the local search database model;

[0025] C. inputting the third semantic search condition group into the local search database model;

[0026] In the step A, the first semantic search condition group is input into the local search database model through the search input module, and the matching module is used to determine whether the first semantic search condition group exists in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group;

[0027] In the step B, the second semantic search condition group is input into the local search database model through the search input module, and the matching module is used to determine whether the second semantic search condition group exists in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group;

[0028] In step C, the third semantic retrieval condition group is input into the local retrieval database model through the retrieval input module, and the matching module is used to determine whether the third semantic retrieval condition group exists in the land data unit group, forest data unit group, grassland data unit group and wetland data unit group.

[0029] Based on the above technical solution, in step A, when the first semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the first semantic retrieval condition group is determined to be an invalid detection condition;

[0030] When the first semantic search condition group is in the land data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the land data unit group;

[0031] When the first semantic search condition group is in the forest data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the forest data unit group;

[0032] When the first semantic search condition group is in the grass data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the grass data unit group;

[0033] When the first semantic retrieval condition group is in the wetland data unit group, the first semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the first semantic retrieval condition group is determined in the wetland data unit group.

[0034] Based on the above technical solution, in step B, when the second semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the second semantic retrieval condition group is determined to be an invalid detection condition;

[0035] When the second semantic search condition group is in the land data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the second semantic search condition group is determined in the land data unit group;

[0036] When the second semantic search condition group is in the forest data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the forest data unit group;

[0037] When the second semantic search condition group is in the grass data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the grass data unit group;

[0038] When the second semantic retrieval condition group is in the wetland data unit group, the second semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the second semantic retrieval condition group is determined in the wetland data unit group.

[0039] Based on the above technical solution, in step C, when the third semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the third semantic retrieval condition group is determined to be an invalid detection condition;

[0040] When the third semantic search condition group is in the land data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the land data unit group;

[0041] When the third semantic search condition group is in the forest data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the forest data unit group;

[0042] When the third semantic search condition group is in the grass data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the third semantic search condition group is determined in the grass data unit group;

[0043] When the third semantic retrieval condition group is in the wetland data unit group, the third semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the third semantic retrieval condition group is determined in the wetland data unit group.

[0044] Based on the above technical solution, in step S9, in step A, step B and step C, when the first semantic retrieval condition group, the second semantic retrieval condition group and the third semantic retrieval condition group are matched with the corresponding sub-unit groups in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the data information of the sub-unit groups matching therewith is extracted through the extraction module, and the retrieved data information is parsed.

[0045] Compared with the prior art, the present invention has the following beneficial effects: the present invention can uniformly format the acquired remote sensing data information before retrieval, thereby ensuring that all retrieval information in the retrieval database model is in a unified format, thereby facilitating the subsequent rapid extraction and analysis of the detection result information. At the same time, during the retrieval process, the present invention classifies the retrieval information in the retrieval database model. In addition, before the retrieval keyword is input, the different semantics of the retrieval keyword are analyzed to ensure that keyword information with different semantics can be retrieved, and the keyword information with different semantics is classified. Through the classification matching retrieval method, during the retrieval process, only the corresponding keyword information needs to be searched in the corresponding category, thereby improving the speed and efficiency of the retrieval results, while avoiding the diversity of the retrieval results and causing the trouble of subsequent screening and elimination. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0047] In the attached picture:

[0048] Figure 1 is a flowchart of the steps of the retrieval method of the present invention;

[0049] Figure 2 It is a flow chart of the steps in step S8 of the present invention. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0051] Example: Figure 1-2 As shown, the present invention provides a technical solution, a remote sensing data retrieval method based on artificial intelligence, comprising the following steps:

[0052] S1. Obtain all remote sensing data information based on artificial intelligence;

[0053] S2, unifying the format of the acquired remote sensing data information;

[0054] S3, establishing a retrieval database model with the processed remote sensing data information;

[0055] S4, classifying the retrieved remote sensing data information in the retrieval database model;

[0056] S5. Obtain the user's search request information and extract the search keywords in the search request information;

[0057] S6. Mining the semantics of keywords based on the search keywords, and analyzing the mined semantics of the keywords;

[0058] S7, grouping the analyzed keyword semantics and establishing semantic groups;

[0059] S8, matching corresponding search;

[0060] S9. Extract and parse the retrieval information.

[0061] Based on the above technical solution, in step S1, the remote sensing data in each remote remote sensing data center is stored in a local database to establish a local database;

[0062] In step S2, the remote sensing center data in different formats uploaded from different locations are unified in format through erdas, envi and ArcGIS software, so that the remote sensing data from different locations are all in a unified format in the local database;

[0063] In step S3, the remote sensing data from various locations are uniformly formatted and retransmitted to the local database, and a local retrieval database model is established.

[0064] Based on the above technical solution, in step S4, the remote sensing data information of each remote location is classified in the established local retrieval database model, including: land data unit group, forest data unit group, grassland data unit group and wetland data unit group, and the land data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the forest data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the grassland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the wetland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group.

[0065] Based on the above technical solution, in step S5, the search input module is used to facilitate the user to input the search information requested by the user, the recognition module is used to obtain the search request information input by the user, and the obtained search information is identified, and finally the search keywords in the identified search request information are filtered and extracted through the screening module.

[0066] Based on the above technical solution, in step S6, after the screening module extracts the keywords in the search request information, the information processing module is used to mine and extract the semantics of the search keywords. After the semantics of the search keywords are determined, the analysis module is used to analyze the different semantics of the search keywords.

[0067] In step S7, after the analysis module distinguishes the different semantics of the search keywords, a semantic group is established in the search input module, and the search keywords with different semantics are divided into: a first semantic search condition group, a second semantic search condition group and a third semantic search condition group in the semantic group.

[0068] Based on the above technical solution, in step S8, the matching corresponding search specifically includes the following search steps:

[0069] A. inputting the first semantic search condition group into the local search database model;

[0070] B. inputting the second semantic search condition group into the local search database model;

[0071] C. inputting the third semantic search condition group into the local search database model;

[0072] In step A, a first semantic search condition group is input into a local search database model through a search input module, and a matching module is used to determine whether the first semantic search condition group exists in a land data unit group, a forest data unit group, a grassland data unit group, and a wetland data unit group;

[0073] In step B, the second semantic search condition group is input into the local search database model through the search input module, and the matching module is used to determine whether the second semantic search condition group exists in the land data unit group, the forest data unit group, the grassland data unit group, and the wetland data unit group;

[0074] In step C, the third semantic retrieval condition group is input into the local retrieval database model through the retrieval input module, and the matching module is used to determine whether the third semantic retrieval condition group exists in the land data unit group, forest data unit group, grassland data unit group and wetland data unit group.

[0075] Based on the above technical solution, in step A, when the first semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the first semantic retrieval condition group is determined to be an invalid detection condition;

[0076] When the first semantic search condition group is in the land data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the land data unit group;

[0077] When the first semantic search condition group is in the forest data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the forest data unit group;

[0078] When the first semantic search condition group is in the grass data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the grass data unit group;

[0079] When the first semantic retrieval condition group is in the wetland data unit group, the first semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the first semantic retrieval condition group is determined in the wetland data unit group.

[0080] Based on the above technical solution, in step B, when the second semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the second semantic retrieval condition group is determined to be an invalid detection condition;

[0081] When the second semantic search condition group is in the land data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the second semantic search condition group is determined in the land data unit group;

[0082] When the second semantic search condition group is in the forest data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the forest data unit group;

[0083] When the second semantic search condition group is in the grass data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the grass data unit group;

[0084] When the second semantic retrieval condition group is in the wetland data unit group, the second semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the second semantic retrieval condition group is determined in the wetland data unit group.

[0085] Based on the above technical solution, in step C, when the third semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the third semantic retrieval condition group is determined to be an invalid detection condition;

[0086] When the third semantic search condition group is in the land data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the land data unit group;

[0087] When the third semantic search condition group is in the forest data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the forest data unit group;

[0088] When the third semantic search condition group is in the grass data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the third semantic search condition group is determined in the grass data unit group;

[0089] When the third semantic retrieval condition group is in the wetland data unit group, the third semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the third semantic retrieval condition group is determined in the wetland data unit group.

[0090] Based on the above technical solution, in step S9, in step A, step B and step C, when the first semantic retrieval condition group, the second semantic retrieval condition group and the third semantic retrieval condition group are matched with the corresponding sub-unit groups in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the data information of the sub-unit groups matching therewith is extracted through the extraction module, and the retrieved data information is parsed.

[0091] Based on the above, the advantages of the present invention are: the present invention can uniformly format the acquired remote sensing data information before retrieval, thereby ensuring that all retrieval information in the retrieval database model is in a unified format, thereby facilitating the subsequent rapid extraction and analysis of the detection result information. At the same time, during the retrieval process, the present invention classifies the retrieval information in the retrieval database model. In addition, before the retrieval keyword is input, the different semantics of the retrieval keyword are analyzed to ensure that keyword information with different semantics can be retrieved, and the keyword information with different semantics is classified. Through the classification matching retrieval method, during the retrieval process, only the corresponding keyword information needs to be searched in the corresponding category, thereby improving the speed and efficiency of the retrieval results, while avoiding the diversity of the retrieval results, causing the trouble of subsequent screening and elimination.

[0092] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote sensing data retrieval method based on artificial intelligence, characterized in that: The steps include: S1. Obtain all remote sensing data information based on artificial intelligence; S2, unifying the format of the acquired remote sensing data information; S3, establishing a retrieval database model with the processed remote sensing data information; S4, classifying the retrieved remote sensing data information in the retrieval database model; S5. Obtain the user's search request information and extract the search keywords in the search request information; S6. Mining the semantics of keywords based on the search keywords, and analyzing the mined semantics of the keywords; S7, grouping the analyzed keyword semantics and establishing semantic groups; S8, matching corresponding search; S9, extracting and parsing retrieval information; In step S6, after the screening module extracts the keywords in the search request information, the information processing module mines and extracts the semantics of the search keywords, and after the semantics of the search keywords are determined, the analysis module analyzes the different semantics of the search keywords; In step S7, after the analysis module distinguishes the different semantics of the search keywords, a semantic group is established in the search input module, and the search keywords with different semantics are divided into: a first semantic search condition group, a second semantic search condition group and a third semantic search condition group in the semantic group; In step S8, the matching corresponding search specifically includes the following search steps: A. inputting the first semantic search condition group into the local search database model; B. inputting the second semantic search condition group into the local search database model; C. inputting the third semantic search condition group into the local search database model; In the step A, the first semantic search condition group is input into the local search database model through the search input module, and the matching module is used to determine whether the first semantic search condition group exists in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group; In the step B, the second semantic search condition group is input into the local search database model through the search input module, and the matching module is used to determine whether the second semantic search condition group exists in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group; In step C, the third semantic retrieval condition group is input into the local retrieval database model through the retrieval input module, and the matching module is used to determine whether the third semantic retrieval condition group exists in the land data unit group, forest data unit group, grassland data unit group and wetland data unit group.

2. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In the step S1, the remote sensing data in each remote sensing data center is stored in a local database to establish a local database; In step S2, the remote sensing center data in different formats uploaded from different locations are unified in format through erdas, envi and ArcGIS software, so that the remote sensing data from different locations are all in a unified format in the local database; In step S3, the remote sensing data from various locations are uniformly formatted and retransmitted to the local database, and a local retrieval database model is established.

3. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In the step S4, the remote sensing data information of each remote location is classified in the established local retrieval database model, including: a land data unit group, a forest data unit group, a grassland data unit group and a wetland data unit group, and the land data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the forest data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the grassland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group; and the wetland data unit group includes: a first data sub-unit group, a second data sub-unit group and a third data sub-unit group.

4. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In step S5, the search input module is used to facilitate the user to input the search information requested by the user, the recognition module is used to obtain the search request information input by the user, and the obtained search information is recognized, and finally the search keywords in the recognized search request information are filtered and extracted by the screening module.

5. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In the step A, when the first semantic search condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the first semantic search condition group is determined to be an invalid detection condition; When the first semantic search condition group is in the land data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the land data unit group; When the first semantic search condition group is in the forest data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the forest data unit group; When the first semantic search condition group is in the grass data unit group, the first semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the first semantic search condition group is determined in the grass data unit group; When the first semantic retrieval condition group is in the wetland data unit group, the first semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the first semantic retrieval condition group is determined in the wetland data unit group.

6. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In the step B, when the second semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the second semantic retrieval condition group is determined to be an invalid detection condition; When the second semantic search condition group is in the land data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the second semantic search condition group is determined in the land data unit group; When the second semantic search condition group is in the forest data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the forest data unit group; When the second semantic search condition group is in the grass data unit group, the second semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the second semantic search condition group is determined in the grass data unit group; When the second semantic retrieval condition group is in the wetland data unit group, the second semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the second semantic retrieval condition group is determined in the wetland data unit group.

7. The remote sensing data retrieval method based on artificial intelligence according to claim 1, characterized in that: In the step C, when the third semantic retrieval condition group does not exist in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the third semantic retrieval condition group is determined to be an invalid detection condition; When the third semantic search condition group is in the land data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the land data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the land data unit group; When the third semantic search condition group is in the forest data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the forest data unit group through the input module, and a sub-unit group matching the third semantic search condition group is determined in the forest data unit group; When the third semantic search condition group is in the grass data unit group, the third semantic search condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the grass data unit group through the input module, and the sub-unit group matching the third semantic search condition group is determined in the grass data unit group; When the third semantic retrieval condition group is in the wetland data unit group, the third semantic retrieval condition group is input into the first data sub-unit group, the second data sub-unit group and the third data sub-unit group in the wetland data unit group through the input module, and the sub-unit group matching the third semantic retrieval condition group is determined in the wetland data unit group.

8. The remote sensing data retrieval method based on artificial intelligence according to claim 6, characterized in that: In step S9, in step A, step B and step C, when the first semantic retrieval condition group, the second semantic retrieval condition group and the third semantic retrieval condition group are matched with the corresponding sub-unit groups in the land data unit group, the forest data unit group, the grassland data unit group and the wetland data unit group, the data information of the sub-unit groups matching therewith is extracted through the extraction module, and the retrieved data information is parsed.

Images