Multi-factor comprehensive lake island classification and identification method and system, product and medium

Abstract

The invention discloses a multi-factor comprehensive lake-island classification and identification method and system, a product and a medium, and relates to the field of lake-island classification, and the method comprises the steps: firstly obtaining multi-dimensional data, including image data, environmental data and impact factors, of a target lake-island, carrying out the text matching of the impact factors, dividing the impact factors into ecological factors and humanity factors, and carrying out the text matching of the impact factors; according to the method, preliminary classification of lake and island features is realized, then, deep analysis is performed on images and ecological data by the method, more detailed ecological and humanistic features are extracted, secondary factors are formed, and finally, the extracted features are matched with a preset classification list to obtain a final classification type of a target lake and island. The automatic classification process not only improves the classification efficiency, but also reduces personal errors, so that the lake island classification result is more objective and accurate.

Description

Technical Field

[0001] The present application relates to the field of lake island classification, and in particular to a multi-factor comprehensive lake island classification and identification method, system, product and medium. Background Art

[0002] With the increasing awareness of ecological and environmental protection, the research and management of lake island ecosystems have received increasing attention. As a unique ecological unit, the classification and identification of lake islands are crucial for the formulation of effective protection strategies and management measures. Accurate lake island classification can help researchers and managers better understand the ecological characteristics, cultural characteristics and interactions of lake islands.

[0003] Among the related technologies, the classification and identification of lake islands mainly relies on remote sensing image analysis and field surveys. Researchers obtain image data of lake islands through satellites or aerial photography, and classify the lake islands based on the ecological and cultural information collected through field surveys. This method usually uses pre-set classification standards, such as area size, vegetation coverage or water quality indicators. During the classification process, researchers divide the lake islands into different types based on these standards, and determine the final classification results through manual interpretation and data analysis.

[0004] This classification method often requires manual data preprocessing and feature extraction, which reduces the efficiency of lake island classification. Summary of the invention

[0005] The present application provides a multi-factor comprehensive lake island classification and identification method, system, product and medium for improving the efficiency of lake island classification.

[0006] In a first aspect, the present application provides a multi-factor integrated lake island classification and identification method, which is applied to a multi-factor integrated lake island classification and identification system, the method comprising: obtaining image data, lake island environmental data and influencing factors of a target lake island in a target area, the lake island environmental data comprising lake island ecological data and lake island humanities data, the influencing factor being a factor that affects the classification of the target lake island; performing text matching on the influencing factor according to preset environmental monitoring data and preset humanities data, determining the influencing factor that conforms to the preset environmental monitoring data as a first-level ecological factor, and determining the influencing factor that conforms to the preset humanities data as a first-level humanities factor; detecting the image data and the lake island ecological data, extracting the ecological factor parameters of the target lake island to obtain first-level ecological data, and using the first-level ecological data as a second-level ecological factor; extracting the humanities factor parameters of the target lake island according to the lake island humanities data to obtain first-level humanities data, and using the first-level humanities data as a second-level humanities factor; determining whether the second-level ecological factor and the second-level humanities factor conform to the preset lake island classification list, obtaining a matching sequence, and determining the classification type of the target lake island according to the matching sequence.

[0007] By adopting the above technical solution, we first obtain multi-dimensional data of the target lake island, including image data, environmental data and influencing factors. By performing text matching on the influencing factors, we divide them into ecological factors and cultural factors, thereby achieving a preliminary classification of the lake island characteristics. Subsequently, the method conducts an in-depth analysis of the image and ecological data, extracts more detailed ecological and cultural characteristics, and forms secondary factors. Finally, by matching the extracted features with the preset classification list, we obtain the final classification type of the target lake island. This automated classification process not only improves the efficiency of classification, but also reduces human errors, making the lake island classification results more objective and accurate.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of performing text matching on the influencing factor according to the preset environmental monitoring data and the preset humanities data, determining the influencing factor that meets the preset environmental monitoring data as an ecological factor, and determining the influencing factor that meets the preset humanities data as a humanities factor, specifically includes: performing semantic analysis on the influencing factor, and extracting influencing keywords of the influencing factor; constructing a knowledge graph containing the preset environmental monitoring data and the preset humanities data; calculating the impact similarity between the influencing factor and the nodes in the knowledge graph; if the impact similarity is greater than the preset impact threshold, determining the influencing factor as an ecological factor, and if the impact similarity is not greater than the preset impact threshold, determining the influencing factor as a humanities factor.

[0009] By adopting the above technical solution, semantic analysis is performed on the influencing factors and keywords are extracted, which lays the foundation for subsequent matching. A knowledge graph containing preset environmental monitoring data and humanities data is constructed as a reference standard for classification. The impact similarity between the influencing factors and the knowledge graph nodes is calculated, and it can accurately determine whether each factor belongs to ecological factors or humanities factors. The classification method based on knowledge graph and semantic analysis improves the accuracy and efficiency of classification. The automated classification process saves time and manpower, can process a large number of influencing factors, and realizes a comprehensive analysis of the characteristics of lake islands.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of detecting the image data and the lake island ecological data, and extracting the ecological factor parameters of the target lake island to obtain the primary ecological data specifically includes: segmenting the image data, extracting the geographical characteristic parameters of the target lake island, and the geographical characteristic parameters include the lake island area, water body range and vegetation coverage area; fusing the geographical characteristic parameters with the lake island ecological data to obtain the ecological characteristic vector of the target lake island, and the lake island ecological data includes vegetation type, farming conditions and construction conditions; calculating the statistical characteristic value of each parameter in the ecological characteristic vector, and taking the statistical characteristic values ​​of all parameters as the primary ecological data, and the primary ecological data includes the lake island area, water body range, vegetation coverage area, vegetation type, farming conditions and construction conditions.

[0011] By adopting the above technical solution, the geographical characteristic parameters of the lake island, including area, water range and vegetation coverage area, are extracted by segmenting the image data, providing basic data for subsequent ecological characteristic analysis. The geographical characteristic parameters are fused with the lake island ecological data to obtain the ecological characteristic vector. The data fusion method makes the description of ecological characteristics more comprehensive and accurate. The statistical characteristic value of each parameter in the ecological characteristic vector is calculated to obtain the primary ecological data. The multi-dimensional ecological data includes the physical characteristics of the lake island, as well as ecological information such as vegetation type, farming conditions and construction conditions, realizing the comprehensive extraction and quantification of the ecological characteristics of the lake island.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of determining whether the secondary ecological factor and the secondary human factor conform to the preset lake island classification list to obtain a matching sequence, and determining the classification type of the target lake island according to the matching sequence, specifically includes: judging the secondary ecological factor and the secondary human factor in turn with each classification condition in the preset lake island classification list; if the secondary ecological factor and the secondary human factor meet the classification conditions, the corresponding position in the initial sequence is recorded as 1, if not, it is recorded as 0 to obtain a matching sequence; determining the classification type of the target lake island according to the matching sequence.

[0013] By adopting the above technical solution, the secondary ecological factors and secondary human factors are judged against each classification condition in the preset lake island classification list to form a matching sequence. When the classification condition is met, the corresponding position in the initial sequence is recorded as 1, and when it is not met, it is recorded as 0. The generation process of the matching sequence converts the complex lake island characteristics into a concise digital representation, which is convenient for subsequent classification judgment. The classification type of the target lake island is determined according to the matching sequence, which realizes the automation and standardization of the classification process, and quantifies the matching process of the lake island characteristics and the preset classification conditions, making the classification results more objective and reliable.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the computer determines that the secondary ecological factor and the secondary human factor conform to a preset lake island classification list to obtain a matching sequence, and determines the classification type of the target lake island according to the matching sequence, the method also includes: obtaining historical classification data of the target lake island, the historical classification data including the type of the target lake island at a historical time point; constructing a time series model, and inputting the historical classification data into the time series model to obtain a classification type change trend of the target lake island; predicting the type of the target lake island at a preset future time point according to the classification type change trend to obtain a predicted type; calculating the type similarity between the predicted type and the classification type; if the type similarity is greater than a preset similarity threshold, generating lake island evolution warning information and sending it to the client.

[0015] By adopting the above technical solution, the historical classification data of the target lake island is obtained, and the time series model is constructed to obtain the classification type change trend of the target lake island. The type of the target lake island at a preset future time point is predicted using the change trend to obtain the predicted type. The similarity between the predicted type and the current classification type is calculated. When the similarity is greater than the preset threshold, the lake island evolution warning information is generated and sent to the client. This method not only realizes the classification of the current state of the lake island, but also predicts its future change trend. The introduction of the time series model transforms the lake island classification from static analysis to dynamic prediction, which helps to take protective measures in advance to prevent the deterioration of the lake island ecology and achieve sustainable management of the lake island.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the step of predicting the type of the target lake island at a preset future time point based on the classification type change trend specifically includes: calculating the type change cycle and type change rate parameters of the target lake island based on the historical classification data; inputting the type change cycle and the type change rate parameters into a type prediction model to obtain a predicted type.

[0017] By adopting the above technical solution, the type change cycle and type change rate parameters of the target lake island are calculated based on the historical classification data, and these parameters are input into the type prediction model to obtain the predicted type. The introduction of the change cycle and rate parameters enables the prediction model to capture the regular characteristics of lake island type changes. The use of the type prediction model transforms the complex lake island evolution process into a quantifiable and predictable mathematical model, which improves the accuracy of the prediction and provides a longer-term planning basis for lake island management.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the type similarity between the predicted type and the classification type, the method includes: if the type similarity is not greater than a preset similarity threshold, generating evolution prompt information based on the predicted type and sending it to the client.

[0019] By adopting the above technical solution, when the similarity between the predicted type and the current classification type is not greater than the preset similarity threshold, the system generates evolution prompt information based on the predicted type and sends it to the client. The setting of the preset similarity threshold ensures that the system can identify significant changes in lake island types. The generation process of evolution prompt information takes into account the characteristics of the predicted type and provides users with specific and targeted information. Sending the prompt information to the client realizes timely feedback of lake island classification results.

[0020] In the second aspect, an embodiment of the present application provides a multi-factor integrated lake island classification and identification system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, and the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the multi-factor integrated lake island classification and identification system to perform the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product is run on a multi-factor integrated lake island classification and identification system, the above-mentioned multi-factor integrated lake island classification and identification system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a multi-factor integrated lake island classification and identification system, the multi-factor integrated lake island classification and identification system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It can be understood that the multi-factor integrated lake island classification and identification system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application first obtains multi-dimensional data of the target lake island, including image data, environmental data and influencing factors, and divides the influencing factors into ecological factors and cultural factors through text matching, thereby achieving a preliminary classification of the lake island characteristics. Subsequently, the method conducts an in-depth analysis of the image and ecological data, extracts more detailed ecological and cultural characteristics, and forms secondary factors. Finally, by matching the extracted features with the preset classification list, the final classification type of the target lake island is obtained. This automated classification process not only improves the efficiency of classification, but also reduces human errors, making the lake island classification results more objective and accurate.

[0025] 2. This application conducts semantic analysis on the influencing factors and extracts keywords, laying the foundation for subsequent matching. It constructs a knowledge graph containing preset environmental monitoring data and humanities data as a reference standard for classification, calculates the impact similarity between the influencing factors and the knowledge graph nodes, and can accurately determine whether each factor is an ecological factor or a humanities factor. The classification method based on knowledge graph and semantic analysis improves the accuracy and efficiency of classification. The automated classification process saves time and manpower, can process a large number of influencing factors, and realizes a comprehensive analysis of the characteristics of lake islands.

[0026] 3. This application forms a matching sequence by judging the secondary ecological factors and the secondary human factors against each classification condition in the preset lake island classification list. When the classification condition is met, the corresponding position in the initial sequence is recorded as 1, and when it is not met, it is recorded as 0. The matching sequence generation process converts the complex lake island characteristics into a concise digital representation to facilitate subsequent classification judgments. The classification type of the target lake island is determined according to the matching sequence, which realizes the automation and standardization of the classification process, quantifies the matching process between the lake island characteristics and the preset classification conditions, and makes the classification results more objective and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a multi-factor comprehensive lake island classification and identification method in an embodiment of the present application; Figure 2 This is another flow chart of the multi-factor integrated lake island classification and identification method in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the multi-factor integrated lake island classification and identification system in the embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the multi-factor comprehensive lake island classification and identification method in the embodiment of the present application.

[0031] S101, obtaining image data, lake island environmental data and influencing factors of a target lake island in a target area, wherein the lake island environmental data includes lake island ecological data and lake island cultural data, and the influencing factors are factors that affect the classification of the target lake island.

[0032] The target area represents the specific geographical scope where lake island classification and identification is required. The target lake island refers to the specific lake island that needs to be classified and identified within the target area. Image data is used to represent the visual information of the lake island, such as satellite images or aerial photos. Lake island environmental data refers to various data describing the ecological and cultural characteristics of lake islands. Influencing factors represent various factors that may affect the classification of lake islands. Lake island ecological data include natural environmental information such as vegetation coverage and water quality conditions. Lake island cultural data include social environmental information such as population and economic activities.

[0033] Specifically, before starting the lake island classification and identification process, it is necessary to first obtain relevant data of the target lake island. The system obtains high-resolution satellite images or aerial photos of specific lake islands in the target area through remote sensing equipment or databases as image data. At the same time, the system collects ecological environmental parameters and humanistic and social indicators of the lake island from environmental monitoring sites, field survey reports and other channels to form lake island environmental data.

[0034] S102, performing text matching on the influencing factors according to preset environmental monitoring data and preset humanities data, determining the influencing factors that match the preset environmental monitoring data as primary ecological factors, and determining the influencing factors that match the preset humanities data as primary humanities factors.

[0035] Among them, the preset environmental monitoring data refers to a predefined series of environmental indicators and parameters. The preset humanities data refers to a predefined set of humanities and social indicators. Text matching refers to comparing the text similarity between the influencing factors and the preset data. The first-level ecological factors represent directly related environmental impact factors. The first-level humanities factors represent directly related social impact factors.

[0036] Specifically, after obtaining the influencing factors, the system needs to preliminarily classify these factors to determine whether they are ecological factors or human factors. The system first calls the preset environmental monitoring data set and humanities data set. Then, the system performs text analysis on each influencing factor to extract its keywords and semantic features. Next, the system matches these features with the preset data set and calculates the similarity. If an influencing factor has a high degree of match with the environmental monitoring data, it is classified as a first-level ecological factor; if it has a high degree of match with the humanities data, it is classified as a first-level humanities factor.

[0037] In some embodiments, factor classification can be achieved in a variety of ways: Optionally, the system can use the following steps to perform text matching and factor classification: First, use natural language processing technology to segment and tag the influencing factors. Then build a word vector model for preset environmental monitoring data and humanities data. Then calculate the cosine similarity between the influencing factor and the preset data word vector. Then set a similarity threshold, and those above the threshold are classified as corresponding first-level factors. Finally, for factors that are difficult to judge, a machine learning classifier is used for further classification. Optionally, the system can also perform factor classification in the following way: First, establish a knowledge graph of environmental monitoring and humanities data. Then extract the semantic features of the influencing factors and map them to the knowledge graph. Then calculate the semantic distance between the influencing factor and the knowledge graph node. Then determine the factor category based on the minimum value of the semantic distance.

[0038] S103, detecting the image data and the lake island ecological data, extracting the ecological factor parameters of the target lake island to obtain primary ecological data, and using the primary ecological data as the secondary ecological factor.

[0039] Among them, image data represents the visual information of the target lake island, such as satellite images or aerial photos. Lake island ecological data refers to various data describing the natural environmental characteristics of the lake island, including water quality, vegetation coverage, etc. Detection refers to the processing and analysis of images and data through computer vision and data analysis technology. Ecological factor parameters are used to represent various factors affecting the lakeshore ecosystem, such as water area, vegetation index, etc. Primary ecological data refers to quantitative information directly extracted from images and ecological data.

[0040] Specifically, after acquiring image data and lake island ecological data, the system needs to conduct in-depth analysis of these raw data to extract more valuable ecological information. First, the system uses image processing technology to pre-process satellite images or aerial photos, including denoising, enhancement, and correction. Then, the system uses computer vision algorithms to extract features from the processed images and identify key elements such as water body boundaries, vegetation coverage areas, and artificial buildings. At the same time, the system performs statistical analysis on the lake island ecological data and calculates the mean, variance, and other statistical quantities of various ecological indicators. Next, the system combines the image analysis results with the ecological data statistical results to extract a series of quantitative parameters that can comprehensively reflect the ecological status of the lake island. These parameters constitute the primary ecological data.

[0041] In some embodiments, the extraction and processing of ecological data can be achieved in a variety of ways: Optionally, the system can use the following steps to process data: Satellite images are subjected to noise removal, contrast enhancement and geometric correction to ensure image quality and geographic location accuracy. The characteristics of multispectral images are used to set the near-infrared band reflectance threshold to identify water areas. The water body boundary is refined through morphological operations to obtain accurate lake island contours, and then the normalized vegetation index (NDVI) is calculated. The vegetation coverage area is divided according to the NDVI value, and the vegetation coverage degree is evaluated. Combined with the water quality data collected on the spot, the spatial interpolation method is used to estimate the distribution of water quality parameters in the entire lake area. Finally, the extracted water area, vegetation coverage, water quality parameters and other information are integrated into structured data to form primary ecological data.

[0042] Optionally, the system can also process data in the following ways: collect seasonal satellite images over many years, analyze seasonal and interannual trends in water area, calculate other vegetation indices such as the Enhanced Vegetation Index (EVI) in addition to NDVI, comprehensively evaluate vegetation health, use night light data to analyze the relationship between human activity intensity and water quality parameters, comprehensively consider water body changes, vegetation conditions, water quality and the impact of human activities, build simple models to assess ecosystem vulnerability, and create various charts and graphs based on the extracted ecological parameters to intuitively display the ecological status of the lake islands.

[0043] S104, extracting the human factor parameters of the target lake island according to the lake island human data to obtain primary human data, and using the primary human data as the secondary human factors.

[0044] Among them, lake island human data refers to various data that describe the social environment and human activity characteristics of lake islands, including demographics, economic indicators, etc. The human factor parameters are used to represent the various factors that affect the social and cultural characteristics of lake islands, such as population density, economic development level, etc. The first-level human data refers to the quantitative information directly extracted from the original human data. The second-level human factors represent the human influence factors that have been preliminarily processed and classified, and are used for subsequent lake island classification analysis.

[0045] Specifically, after obtaining the humanities data of the lake islands, the system needs to systematically process and analyze these data to extract key information that can accurately reflect the humanities characteristics of the lake islands. First, the system cleans and standardizes various types of humanities data to ensure the consistency and comparability of the data. Then, the system uses statistical analysis methods to calculate the descriptive statistics of various humanities indicators, such as mean, median, standard deviation, etc. Next, the system conducts correlation analysis to identify interrelated humanities factors and perform appropriate data dimensionality reduction or clustering. After that, the system combines expert knowledge and data mining technology to extract the key parameters that best reflect the humanities characteristics of the lake islands from the processed data. These parameters constitute the first-level humanities data. Finally, the system further classifies and organizes these first-level humanities data to form structured second-level humanities factors.

[0046] For example, the first-level factors include residential population, control requirements, ecological and construction conditions, cultural resources and island size, etc. The original lake and island cultural data obtained by the system include demographic data, administrative divisions, and distribution of tourist facilities. The system first cleans and processes these original data to obtain a standardized data set. Then, the system extracts relevant data representing the first-level factors according to the provided examples: for the residential population, the system counts the number of permanent residents on the lake island and classifies it as the second-level factor "inhabited" or "uninhabited". For the management and control requirements, the system performs natural language processing on the administrative division data, and concludes that the island belongs to a single management zone or multiple management zones based on the administrative division data, and obtains the corresponding second-level factors. For the ecology and construction conditions, the system analyzes satellite images, extracts the distribution of construction areas, and combines topographic data to determine vegetation coverage and construction density to obtain the second-level factors reflecting the intensity of construction activities. For cultural resources, the system counts the number of cultural relics and scenic spots on the island to determine whether they are rich and obtain the corresponding second-level factors. For the size of the island, the system calculates the area of ​​the island and determines whether it is greater than or less than 100 hectares to obtain the corresponding second-level factors. Finally, the system selects factors representing human characteristics, such as the residential population, construction conditions, and cultural resources, based on the extracted second-level factors, and determines them as second-level cultural factors; and selects factors representing natural characteristics, such as management and control requirements and island size, and determines them as second-level ecological factors.

[0047] In some embodiments, the extraction of primary humanities data can be achieved in a variety of ways: Optionally, the system can take the following steps: according to the first-level factors in the example, extract the numerical values ​​of indicators such as residential population conditions, management and control requirements, and cultural resources in the original data, process and calculate these indicator data, and obtain the first-level cultural data expressing the first-level factors, such as uninhabited or inhabited, etc., correspond the first-level cultural data to the second-level factors in the example to form standardized second-level cultural factors, and according to the definition of the second-level factors, select the first-level data representing the cultural characteristics to constitute the result.

[0048] Optionally, the system can also go through the following steps: construct an ontology model knowledge graph containing example first-level factors, map text data to knowledge graph nodes, activate relevant branches, determine the first-level humanities data expressed based on the branch activation status, convert the first-level data, and obtain the standardized second-level humanities factors in the example. It can be understood that other methods can also be used to extract the first-level humanities data, which is not limited here.

[0049] S105: Determine whether the secondary ecological factor and the secondary human factor conform to a preset lake island classification list, obtain a matching sequence, and determine the classification type of the target lake island according to the matching sequence.

[0050] Among them, the secondary ecological factor refers to the processed and classified ecological data indicators, which are used to reflect the ecological and environmental characteristics of the lake island. The secondary human factors refer to the processed and integrated human data indicators, which are used to represent the human characteristics of the lake island. The preset lake island classification list refers to the pre-defined lake island types and their corresponding ecological and human characteristics standards. The matching sequence indicates the degree of matching between the secondary factors of the target lake island and the preset classification standards. The classification type refers to the category to which the lake island belongs determined based on the matching results.

[0051] This step is performed after the extraction of secondary ecological factors and secondary human factors is completed, and is used to determine the specific type of the target lake island. Specifically, the system first compares the extracted secondary ecological factors and secondary human factors with the various type standards in the preset lake island classification list. During the comparison process, the system calculates the similarity or matching degree of each factor with each type standard to form a matching sequence. This sequence contains the degree of matching of the target lake island under each classification standard. Then, the system analyzes this matching sequence, usually using the highest matching principle or comprehensive scoring method to determine the final lake island classification type. If there are multiple types with similar matching degrees, the system may use suboptimal matching or mixed types to describe the characteristics of the lake island.

[0052] In some embodiments, the matching and determination process of lake island classification can be implemented in a variety of ways: Optionally, the system can use the following steps for classification: standardize the secondary ecological factors and secondary human factors to make indicators of different dimensions comparable. For example, the Z-score standardization or Min-Max scaling method can be used to calculate the Euclidean distance or cosine similarity between the standardized factors and the standards of each type in the preset classification list to obtain a similarity matrix. For each preset type, calculate its comprehensive matching degree with the target lake island in all factors, and sort them from high to low by matching degree. Set a matching degree threshold, filter out candidate types that exceed the threshold, and if only one type exceeds the threshold, directly determine it as that type; if there are multiple types, select the type with the highest matching degree as the final classification result. Optionally, the system can also perform classification in the following ways: assign importance weights to different secondary factors based on expert experience or data-driven methods (such as principal component analysis), construct a fuzzy relationship matrix, convert the secondary factor values ​​into membership, and then perform fuzzy comprehensive operations to obtain the membership of each preset type. First, fuzzy evaluation is performed on the ecological factors and humanistic factors respectively, and then the two evaluation results are fuzzily combined again to obtain the final classification result. A confidence score is calculated for each possible classification result to reflect the reliability of the classification result. If the matching degrees of multiple types are similar and high, multiple type labels can be marked for the lake island to reflect its complex characteristics.

[0053] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the multi-factor comprehensive lake island classification and identification method in the embodiment of the present application.

[0054] S201, obtaining image data, lake island environmental data and influencing factors of a target lake island in a target area, wherein the lake island environmental data includes lake island ecological data and lake island cultural data, and the influencing factors are factors that affect the classification of the target lake island.

[0055] It can be understood that this step is similar to step S101 and will not be described in detail here.

[0056] S202: Perform semantic analysis on the impact factor to extract influencing keywords of the impact factor.

[0057] Semantic analysis is the process of using natural language processing technology to deeply analyze text and obtain the semantic information and keywords expressed in the text. Impact factors refer to various factors that may affect the classification of lake islands. Extracting influencing keywords means identifying the core words that can express the nature of its impact from the text description of the impact factor.

[0058] Specifically, the multi-factor integrated lake island classification and identification system first uses natural language processing technologies such as word segmentation and part-of-speech tagging to perform semantic analysis on the text description of the influencing factors, identify important word classes such as nouns, verbs, and adjectives in the text, and determine keywords that can accurately summarize the nature of the influencing factors by counting the frequency and association of these words, such as "pollution", "industry", "population" and other words. These keywords are extracted as semantic features of the influencing factors to provide a basis for subsequent factor classification and matching. For example, if the words "industrial wastewater" and "fertilizer and pesticide" appear in the description text of an influencing factor, the system can determine that the influencing factor is related to water pollution and extract "pollution" as the influencing keyword.

[0059] S203: construct a knowledge graph including the preset environmental monitoring data and the preset humanities data.

[0060] A knowledge graph is a structured knowledge base that expresses concepts and the relationships between concepts. Preset environmental monitoring data refers to predefined environmental monitoring indicators and thresholds. Preset humanities data refers to predefined statistical data related to humanities activities. Building a knowledge graph means using knowledge representation technology to organize environmental monitoring data and humanities data in a network model, express the relationship between concepts, and form a structured knowledge base.

[0061] Specifically, the multi-factor comprehensive lake island classification and identification system can construct a knowledge graph in the following way: First, the system organizes environmental monitoring data, identifies monitoring indicators representing water quality, atmosphere, etc., such as COD, ammonia nitrogen, PM2.5, etc., and represents each indicator and its standard threshold as a concept node. Secondly, the system organizes humanities data, identifies social statistical indicators such as population and GDP, and also represents each indicator as a concept node. Then, the system analyzes the inherent connection between indicators and establishes semantic associations between nodes using attributes, relationships, etc. Finally, the system displays the final constructed knowledge graph in a certain visualization method. For example, the "COD" node can have a "reflection" relationship with the "water quality" node, and the "GDP" node can have a "positive correlation" relationship with the "intensity of economic activity".

[0062] S204: Calculate the impact similarity between the impact factor and the nodes in the knowledge graph.

[0063] Calculating influence similarity means using a similarity algorithm to quantify the degree of semantic connection between the influence factor and each node in the knowledge graph. The higher the influence similarity, the closer the influence factor is to the node in terms of semantics.

[0064] Specifically, the multi-factor integrated lake island classification and identification system can calculate the impact similarity through the following steps: first, extract the keywords of the impact factor and represent them as vectors; then, access the knowledge graph, traverse each node, and also represent the node name and related attributes as vectors; then, the system calls the word vector similarity algorithm, such as word co-occurrence similarity, word vector cosine similarity, etc., to calculate the similarity between the impact factor vector and each node vector; finally, return the highest similarity as the impact similarity between the impact factor and the node. For example, if the keyword of the impact factor is "pollution" and there is a "COD" node in the knowledge graph, the system can calculate the cosine similarity of the two word vectors. Since the two are semantically close and have a high similarity, it is determined that the impact factor and the "COD" node have a strong semantic correlation.

[0065] S205. If the impact similarity is greater than a preset impact threshold, the impact factor is determined as an ecological factor; if the impact similarity is not greater than the preset impact threshold, the impact factor is determined as a humanistic factor.

[0066] Impact similarity refers to the semantic matching degree between the impact factor and the knowledge graph node. The preset impact threshold is a threshold pre-set for impact similarity. Ecological factors refer to factors related to environmental monitoring data. Humanistic factors refer to factors related to humanistic activities.

[0067] Specifically, after calculating the impact similarity between the influencing factors and each node, the multi-factor comprehensive lake island classification and identification system needs to judge the category of the influencing factors based on the threshold: First, the system pre-sets a threshold for impact similarity, which can be determined by training samples. Then, the system determines whether the maximum impact similarity between each influencing factor and the knowledge graph node is greater than the preset threshold. If it is greater, it is determined that the influencing factor is strongly correlated with the environmental monitoring data and is classified as an ecological factor. If it is not greater, it is determined that it is strongly correlated with the humanities data and is classified as a humanities factor. For example, if the maximum similarity of "pollution" is 0.8, which exceeds the preset threshold of 0.7, it is determined to be an ecological factor related to water quality. Conversely, if the maximum similarity of "industrial structure" is 0.5, it is determined to be a humanities factor related to economic activities.

[0068] S206: Segment the image data to extract geographic feature parameters of the target lake island, which include lake island area, water body range, and vegetation coverage area.

[0069] Image segmentation is to divide an image into regions with different characteristics. Geographical characteristic parameters are quantitative indicators that describe the geographical information of lake islands. They include lake island area, water body range, and vegetation coverage area. Image segmentation to extract geographic characteristic parameters is to obtain quantitative information about lake island areas through segmentation algorithms.

[0070] Specifically, the multi-factor integrated lake island classification and recognition system can use the following technical means to perform image segmentation: First, pre-process the satellite or aerial images to achieve interference removal and image enhancement. Then, apply boundary or region-based image segmentation algorithms, such as Canny edge detection, to segment the contour area of ​​the lake island. Next, set different threshold conditions to continue segmenting the water body range and different types of vegetation coverage areas. Finally, calculate the area of ​​each segmented area to obtain geographic element parameters such as lake island area, water body area, and vegetation coverage area. For example, the system can first use the Sobel edge detection algorithm to segment the lake island boundary, and then use the maximum inter-class variance method to segment the water body and land cover type, and then obtain geographic features such as area parameters.

[0071] S207, integrating the geographic feature parameters with the lake island ecological data to obtain an ecological feature vector of the target lake island, wherein the lake island ecological data includes vegetation type, farming conditions, and construction conditions.

[0072] Geographic feature parameters are quantitative indicators obtained through image segmentation. Lake island ecological data are qualitative information describing the ecological conditions of lake islands. Fusion of the two to obtain ecological feature vectors means integrating the two types of data to construct a quantitative vector that expresses the ecological characteristics of lake islands.

[0073] Specifically, the multi-factor comprehensive lake island classification and recognition system can perform data fusion through the following steps: First, the system organizes the geographic feature parameters obtained by image segmentation. Then, the system processes the lake island ecological data and encodes qualitative indicators, such as encoding different vegetation types into different numerical values. Next, the system splices the encoded ecological data with the geographic feature parameters to construct a high-dimensional vector describing the ecological conditions of the lake island as an ecological feature vector. Each dimension in the vector represents a geographical or ecological parameter. Finally, the system can normalize the ecological feature vector to make the features of each dimension comparable, and then input it into the classification model. For example, the system can construct an ecological feature vector containing 10 dimensions, in which the first 3 dimensions represent the lake island area, water body range, and vegetation rate, and the last 7 dimensions represent the coverage rate of different vegetation types.

[0074] S208. Calculate the statistical characteristic value of each parameter in the ecological characteristic vector, and use the statistical characteristic values ​​of all parameters as primary ecological data, which includes lake island area, water body range, vegetation coverage area, vegetation type, farming conditions and construction conditions, and use the primary ecological data as secondary ecological factors.

[0075] The primary ecological data is a statistical data set that can comprehensively reflect the ecological status of the target lake island by summarizing and calculating the various parameters in the ecological characteristic vector through statistical analysis methods. The secondary ecological factors are the core parameters extracted from the primary ecological data that best represent the ecological characteristics of the lake island.

[0076] Specifically, the multi-factor integrated lake island classification and identification system can obtain primary ecological data by the following technical means: Taking whether there are people living as an example, the primary ecological factor can be expressed as a binary variable, 1 means that there are people living, and 0 means that there are no people living. The system can detect the characteristics related to human residence in the ecological feature vector, such as night light data. If it is greater than a certain threshold, it is judged as 1, otherwise it is 0. Taking the building area as an example, the primary ecological factor can be expressed as a specific value, such as the building coverage area calculated in square meters. The system can calculate the number of pixels in the building area through the image segmentation algorithm and then convert it into the actual area size. Specifically, the multi-factor integrated lake island classification and identification system can obtain primary ecological data through the following steps: First, the system obtains the constructed ecological feature vector, which contains the encoded ecological data indicators. Then, the system sets the judgment rules or calculation methods for each ecological data indicator to obtain the primary ecological data representing the factor. Then, the system integrates all the primary ecological factors to form a primary ecological data set, which fully reflects the ecological status of the target lake island. Finally, the system can extract the main secondary ecological factors based on the primary data set, providing a key basis for the subsequent lake island classification.

[0077] S209, extracting the human factor parameters of the target lake island according to the lake island human data to obtain primary human data, and using the primary human data as the secondary human factor.

[0078] It can be understood that this step is similar to step S104 and will not be described in detail here.

[0079] S210, sequentially judging the secondary ecological factor and the secondary humanistic factor against each classification condition in the preset lake island classification list.

[0080] Secondary ecological factors are key ecological parameters extracted from primary ecological data. Secondary human factors are key human parameters extracted from primary human data. The preset lake island classification list is the classification conditions of different types of lake islands defined in advance. Judgment refers to comparing factor parameters and classification conditions one by one to see if they match.

[0081] Specifically, the multi-factor comprehensive lake island classification and identification system needs to make judgments according to the following steps: First, the system obtains a preset lake island classification list, which contains characteristic conditions of different types of lake islands, such as area size, vegetation coverage, etc. Then, the system takes out the first classification condition, such as "area greater than 1,000 square kilometers", and matches it with the secondary ecological factor "lake island area". The system takes out each condition in the classification list in turn to determine whether the secondary ecological factor and the secondary human factor meet the condition. The system completes the judgment of the secondary factors and classification conditions one by one to form a judgment result sequence, which provides a basis for the subsequent final classification.

[0082] S211. If the secondary ecological factor and the secondary human factor meet the classification conditions, the corresponding positions in the initial sequence are recorded as 1; if not, they are recorded as 0, and a matching sequence is obtained.

[0083] After the judgment is made, the judgment result needs to be encoded into a sequence. The satisfied condition is recorded as 1, and the unsatisfied condition is recorded as 0. The matching sequence reflects the matching status of the target lake island and each classification standard.

[0084] Specifically, the multi-factor integrated lake island classification and recognition system can adopt the following technical means to generate a matching sequence: first, the system initializes an empty sequence with a length equal to the number of conditions in the classification list. Then, each time a condition is judged, if the factor is met, 1 is written in the corresponding sequence position, otherwise 0 is written. Finally, after the system completes all judgments, a matching sequence consisting of 0-1 is obtained. For example, if the classification list has 4 conditions and the judgment results are "satisfied, not satisfied, satisfied, not satisfied", then the matching sequence is {1, 0, 1, 0}.

[0085] S212: Determine the classification type of the target lake island according to the matching sequence.

[0086] For example, suppose the following lake island classification system is pre-set: Class 1 - Ecological Conservation Class, Condition 1: No one lives there, Condition 2: Single control area, Condition 3: Natural vegetation coverage > 90%, Condition 4: No water conservancy facilities, Condition 5: Area < 1 square kilometer, Class 2 - Cultivation Conservation Class, Condition 1: No permanent residents, Condition 2: Single control area, Condition 3: Natural vegetation coverage 60%-90%, Condition 4: There is a small amount of farming activities, Condition 5: No permanent buildings, Class 3 - Protection and Coordination Class, Condition 1: Scattered population distribution, Condition 2: Single or dual control area, Condition 3: Natural vegetation coverage 30%-60%, Condition 4: There are tourist facilities, Condition 5: Area 1-10 square kilometers, Class 4 - Protection and Utilization Class, Condition 1: There are relatively dense settlements, Condition 2 : Composite control area, condition 3: natural vegetation coverage rate <30%, condition 4: existence of urban construction, condition 5: area >10 square kilometers, and the matching sequence of the target lake island is: {1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0}, the judgment logic is: count the number of values ​​​​of each category condition in the matching sequence with a value of 1, indicating the number of conditions met, class 1 condition matching number: 5, class 2 condition matching number: 1, class 3 condition matching number: 2, class 4 condition matching number: 1, comparing the matching number of each category, class 1 has the largest number of matching conditions, which is 5. Therefore, based on "the category with the most matching conditions" as the judgment rule, the system determines that the target lake island belongs to category 1-ecological conservation.

[0087] S213: Acquire historical classification data of the target lake island, where the historical classification data includes the type of the target lake island at a historical time point.

[0088] Historical classification data refers to the classification type results of the target lake island at various time points in the past. The historical time point can be the end of the year in the past many years, or a more fine-grained monthly or quarterly time period. Type refers to the lake island category determined according to the classification system, such as ecological conservation category. Acquisition refers to extracting the lake island classification results of the historical time period from the database or records.

[0089] Specifically, the multi-factor integrated lake island classification and identification system can obtain the historical classification data of the target lake island in the following way: the system first connects to the lake island classification database, which stores the classification results of various lake islands over the years, including lake island ID, time, classification label and other information. Based on the ID of the target lake island, the system extracts the classification results of the lake island in the past 5 or 10 years in chronological order. These time-stamped classification results constitute the historical classification data of the lake island. For example, the classification category of the target lake island at the end of each year in the past 10 years can be obtained to reflect the evolution of the lake island category.

[0090] S214: construct a time series model, and input the historical classification data into the time series model to obtain the classification type change trend of the target lake island.

[0091] The time series model is a statistical analysis model that reflects the characteristics of time-sequential data. After the historical classification data is input into the time series model, the changing trend and pattern of the data can be detected. The classification type change trend refers to the overall direction of the change of the classification category of the target lake island over time.

[0092] Specifically, the multi-factor integrated lake island classification and identification system can obtain the classification change trend through the following steps: First, the system calls the time series analysis algorithm, such as the ARIMA model, to build a time series model suitable for describing the classification data. Then, the system inputs the acquired historical classification data into the model in chronological order. Next, the system simulates the training to obtain the model parameters. Finally, the system predicts the trend of the input classification sequence in the future and outputs the change trend of the classification type, such as gradually turning to the ecological type.

[0093] S215. Calculate the type change cycle and type change rate parameters of the target lake island based on the historical classification data.

[0094] Specifically, the multi-factor integrated lake island classification and recognition system can calculate the above parameters through the following technical means: the system first loads the historical classification data time series, and then uses Fourier transform and other signal analysis algorithms to detect the main frequency domain components of the sequence and determine the cycle length of the type change. The system can also calculate the change amount of the classification category at two adjacent time points and determine the change rate in different time periods. Finally, the system performs statistical analysis on the change cycle and change rate to obtain quantitative parameters that can express the dynamic change characteristics of the classification.

[0095] S216: Input the type change period and the type change rate parameters into the type prediction model to obtain the predicted type.

[0096] The type change cycle reflects the characteristics of the target lake island classification type changing in a certain period. The type change rate reflects the speed of the classification type change. These two parameters can reasonably and quantitatively describe the dynamic characteristics of the lake island classification evolution process.

[0097] The type prediction model can be established through machine learning algorithms to analyze historical data and predict future trends. Inputting the above two parameters into the prediction model can help the model learn the periodic laws and rate characteristics of lake island classification changes, thereby obtaining more accurate classification predictions.

[0098] Specifically, the following technical means can be used to establish a type prediction model: Construct an LSTM recursive neural network, and set up memory units to save historical states for model time series data. The network input layer accesses the type change cycle and change rate as model feature parameters. Set a hidden layer with a loop structure in the middle of the network to learn time-related knowledge. Set up multiple nodes in the output layer to represent different classification types, generate prediction probabilities through softmax, provide labeled historical classification data sets, train the network model, input the change cycle and change rate parameters of the test data, run the model for prediction, parse the output probability, and determine the classification type with the highest probability as the prediction result. By inputting key time series feature parameters, the type prediction model can learn and simulate the evolution process of lake island classification, and finally output the predicted classification type in the future.

[0099] S217: Calculate the type similarity between the predicted type and the classified type.

[0100] The prediction type is the result obtained by the time series model. The classification type is the classification result at the current moment. By calculating the similarity between the two, we can determine the degree of deviation between the prediction result and the actual situation.

[0101] Specifically, the multi-factor integrated lake island classification recognition system can calculate type similarity using the following method: First, the system represents both the predicted type and the classified type as a type-encoded vector. Then, the system calls text similarity algorithms, such as Hamming distance, edit distance, cosine similarity, etc., to calculate the similarity between the two vectors. Finally, the system outputs a similarity value. If it is close to 1, it means the prediction is accurate. If it is lower, the prediction has a large deviation.

[0102] S218. If the type similarity is greater than a preset similarity threshold, lake island evolution warning information is generated and sent to the client.

[0103] The preset similarity threshold is a threshold predefined by the system for judging the prediction deviation. If the type similarity is too low, it means that the prediction has a large deviation, and there may be abnormal changes in the lake island type. At this time, it is necessary to remind the user and generate an early warning message to send to the client.

[0104] Specifically, the multi-factor integrated lake island classification and recognition system can generate and send warning information through the following steps: the system first presets a type similarity threshold, such as 0.7. Then the system determines whether the calculated similarity is lower than the threshold. If it is lower, the system calls the warning information generation module to generate functional text or audio alarm information. Finally, the system sends the warning information to the user terminal client through the API interface to remind the user to pay attention to the abnormal evolution of the lake island status.

[0105] S219: If the type similarity is not greater than a preset similarity threshold, generating evolution prompt information according to the predicted type and sending it to the client.

[0106] The prediction type is the future classification result predicted by the time series model. When the prediction is biased, prompt information needs to be generated based on the prediction type result to inform the user of the predicted classification and possible evolution direction.

[0107] Specifically, the multi-factor integrated lake island classification and recognition system can generate and send prompt information through the following technical means: the system first calculates the type similarity between the predicted classification and the actual classification, and determines whether the similarity is lower than the preset threshold of 0.8. If so, it enters the prompt generation process. The system calls the natural language generation algorithm to generate text prompt information based on the predicted classification results. For example, "The system predicts that the lake island will evolve into a protection coordination type in the future." Speech synthesis can also be called to generate voice prompt information.

[0108] The following describes the multi-factor integrated lake island classification and recognition system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the structure of a physical device of the multi-factor integrated lake island classification and identification system in the embodiment of the present application.

[0109] It should be noted that Figure 3 The structure of the multi-factor integrated lake island classification and identification system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0110] like Figure 3 As shown, the multi-factor integrated lake island classification and identification system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0111] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0112] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0113] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0115] Specifically, the multi-factor integrated lake island classification and identification system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the multi-factor integrated lake island classification and identification method provided in the above embodiment is implemented.

[0116] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the multi-factor integrated lake island classification and identification system described in the above embodiment; or may exist independently without being assembled into the multi-factor integrated lake island classification and identification system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the multi-factor integrated lake island classification and identification system, the multi-factor integrated lake island classification and identification system implements the multi-factor integrated lake island classification and identification method provided in the above embodiment.

[0117] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0118] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0119] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A multi-factor comprehensive lake island classification and identification method. It is characterized in that A lake island classification and identification system applied to multi-factor integration, the method comprising: Acquire image data, lake island environmental data, and influencing factors of a target lake island in a target area, wherein the lake island environmental data includes lake island ecological data and lake island cultural data, and the influencing factors are factors that affect the classification of the target lake island; Performing text matching on the influencing factors according to the preset environmental monitoring data and the preset humanities data, determining the influencing factors that match the preset environmental monitoring data as primary ecological factors, and determining the influencing factors that match the preset humanities data as primary humanities factors; Detecting the image data and the lake island ecological data, extracting ecological factor parameters of the target lake island to obtain primary ecological data, and using the primary ecological data as secondary ecological factors; Extracting the human factor parameters of the target lake island according to the lake island human data to obtain primary human data, and using the primary human data as secondary human factors; It is determined whether the secondary ecological factor and the secondary human factor conform to a preset lake island classification list to obtain a matching sequence, and the classification type of the target lake island is determined according to the matching sequence.

2. The method according to claim 1, It is characterized in that The step of performing text matching on the influencing factors according to the preset environmental monitoring data and the preset humanities data, determining the influencing factors that match the preset environmental monitoring data as ecological factors, and determining the influencing factors that match the preset humanities data as humanities factors specifically includes: Performing semantic analysis on the impact factor to extract influencing keywords of the impact factor; Constructing a knowledge graph including the preset environmental monitoring data and the preset humanities data; Calculate the impact similarity between the impact factor and the nodes in the knowledge graph; If the impact similarity is greater than a preset impact threshold, the impact factor is determined as an ecological factor; if the impact similarity is not greater than the preset impact threshold, the impact factor is determined as a humanistic factor.

3. The method according to claim 1, It is characterized in that The step of detecting the image data and the lake island ecological data and extracting the ecological factor parameters of the target lake island to obtain the primary ecological data specifically includes: Segmenting the image data to extract geographic feature parameters of the target lake island, wherein the geographic feature parameters include lake island area, water body range, and vegetation coverage area; The geographical characteristic parameters are integrated with the lake island ecological data to obtain the ecological characteristic vector of the target lake island, wherein the lake island ecological data includes vegetation type, farming conditions and construction conditions; The statistical characteristic value of each parameter in the ecological characteristic vector is calculated, and the statistical characteristic values ​​of all parameters are used as primary ecological data, wherein the primary ecological data includes lake island area, water body range, vegetation coverage area, vegetation type, farming conditions and construction conditions.

4. The method according to claim 1, It is characterized in that The step of determining whether the secondary ecological factor and the secondary human factor conform to a preset lake island classification list, obtaining a matching sequence, and determining the classification type of the target lake island according to the matching sequence specifically includes: Sequentially judge the secondary ecological factor and the secondary human factor against each classification condition in the preset lake island classification list; If the secondary ecological factor and the secondary human factor meet the classification conditions, the corresponding positions in the initial sequence are recorded as 1, and if not, they are recorded as 0, to obtain a matching sequence; The classification type of the target lake island is determined according to the matching sequence.

5. The method according to claim 1, It is characterized in that After determining whether the secondary ecological factor and the secondary human factor conform to a preset lake island classification list, obtaining a matching sequence, and determining the classification type of the target lake island according to the matching sequence, the method further includes: Acquire historical classification data of the target lake island, wherein the historical classification data includes the type of the target lake island at a historical time point; Constructing a time series model, and inputting the historical classification data into the time series model to obtain the classification type change trend of the target lake island; Predicting the type of the target lake island at a preset future time point according to the change trend of the classification type to obtain a predicted type; Calculating the type similarity between the predicted type and the classified type; If the type similarity is greater than a preset similarity threshold, lake island evolution warning information is generated and sent to the client.

6. The method according to claim 5, It is characterized in that The step of predicting the type of the target lake island at a preset future time point according to the classification type change trend specifically includes: Calculate the type change cycle and type change rate parameters of the target lake island according to the historical classification data; The type change period and the type change rate parameters are input into a type prediction model to obtain a predicted type.

7. The method according to claim 6, It is characterized in that After the step of calculating the type similarity between the predicted type and the classified type, the method comprises: If the type similarity is not greater than a preset similarity threshold, then an evolution prompt message is generated according to the predicted type and sent to the client.

8. A multi-factor integrated lake island classification and identification system. It is characterized in that The multi-factor integrated lake island classification and identification system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the multi-factor integrated lake island classification and identification system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, It is characterized in that When the instruction is executed on a multi-factor integrated lake island classification and identification system, the multi-factor integrated lake island classification and identification system executes the method as described in any one of claims 1-7.

10. A computer program product, It is characterized in that When the computer program product is run on a multi-factor integrated lake island classification and identification system, the multi-factor integrated lake island classification and identification system is enabled to execute the method according to any one of claims 1 to 7.

Images