Benthic organism sample identification and analysis method and system based on data mining

Abstract

The invention discloses a benthic organism sample identification and analysis method and system based on data mining. The method comprises the following steps: firstly, acquiring standard image data of benthic organisms in different growth stages, extracting appearance features and constructing a feature database; establishing an identification model based on the database, collecting target sample and community three-dimensional structure image data by using an underwater robot, and carrying out initial identification; and if the result is not unique, mining an inter-species relationship, constructing a community relationship network in combination with a graph theory algorithm, calculating the credibility of the identification result, and performing secondary identification to obtain a final result. The method improves the identification accuracy and reliability, and is suitable for marine ecological monitoring and biodiversity research.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biological identification, and in particular to a benthic organism sample identification analysis method and system based on data mining. BACKGROUND

[0002] Benthic organisms are an important component of marine, lake and river ecosystems, and have important significance for ecological environment monitoring, biodiversity protection and water health assessment. Traditional benthic organism identification methods mainly rely on manual classification and microscopic observation, which not only consumes time and effort, but is also easily affected by subjective factors, resulting in large errors in the identification results. In addition, the manual identification method is difficult to adapt to the needs of large-scale sample analysis, limiting the efficiency and accuracy of benthic organism research.

[0003] In recent years, the development of computer vision and data mining technology has provided a new solution for biological identification. Image recognition-based methods can automatically extract biological sample features, improving identification efficiency. However, existing image analysis-based benthic organism identification methods still have weak adaptability in complex environments, especially in cases where there are many types of biological samples and high similarity in morphological characteristics, which can easily lead to misjudgment. In addition, existing methods usually ignore the interspecific relationships of biological communities, which have important reference value in the biological identification process.

[0004] To solve the above problems, the present application proposes a benthic organism sample identification analysis method and system based on data mining, which builds a benthic organism feature database, uses an underwater robot to collect samples, analyzes interspecific relationships using a graph theory algorithm, and performs secondary identification through credibility calculation to improve the accuracy and reliability of identification. This method not only improves the automated identification capability of benthic organism samples, but also enhances the understanding of the overall structure of biological communities, providing a more scientific and effective tool for marine ecological monitoring and biodiversity research. SUMMARY

[0005] To solve at least one of the above technical problems, the present application proposes a benthic organism sample identification analysis method and system based on data mining.

[0006] The first aspect of the present application provides a benthic organism sample identification analysis method based on data mining, comprising: obtaining standard image data of benthic organisms at different growth stages, extracting appearance features of the benthic organisms according to the standard image data, and constructing a benthic organism feature database according to the appearance features; The benthic organism identification model is constructed according to the benthic organism feature database, target benthic organism samples are collected by the underwater robot, three-dimensional structure image data of a benthic organism community within a preset range of a collection point are acquired, and appearance features of the target benthic organism samples are identified based on the benthic organism identification model to obtain initial identification results of the target benthic organism samples; The initial identification results are subjected to uniqueness testing, if the initial identification results of the target benthic organism samples are not unique, data mining is performed on the three-dimensional structure image data of the benthic organism community to determine interspecific relationships of the benthic organism community; Each initial identification result is fused with the interspecific relationships, a relationship network after fusion of each initial identification result and interspecific relationships is constructed based on a graph theory algorithm to obtain a plurality of community interspecific relationship networks; Existence credibility of each initial identification result in the community interspecific relationship network is determined according to the community interspecific relationship network, secondary identification of the target benthic organism samples is performed according to the existence credibility, and final identification results are obtained.

[0007] In the scheme, the standard image data of benthic organisms at different growth stages are acquired, appearance features of the benthic organisms are extracted according to the standard image data, and a benthic organism feature database is constructed according to the appearance features, specifically as follows: The standard image data of benthic organisms at different growth stages are acquired, edge detection is performed on the standard image data based on a Canny operator, and contour features of the benthic organisms at different growth stages are extracted; The contour features are used to calculate the perimeter, area, aspect ratio, and circularity of the benthic organisms at different growth stages to obtain scale features of the benthic organisms; Shape features of the benthic organisms in the standard image data are extracted based on Hu invariant moments, and texture features of the benthic organisms in the standard image data are extracted based on a gray level co-occurrence matrix; Histogram analysis is performed on the standard image data to determine color features of the benthic organisms at different growth stages, and the contour features, scale features, shape features, texture features, and color features are labeled as appearance features of the benthic organisms; A benthic organism feature database is constructed, the appearance features are imported into the benthic organism feature database for storage, and the appearance features in the benthic organism feature database are associated with growth stages of the benthic organisms.

[0008] In the scheme, the benthic organism identification model is constructed according to the benthic organism feature database, the target benthic organism sample is collected by the underwater robot, and the three-dimensional structure image data of the benthic organism community within a preset range of the collection point is obtained, the appearance characteristics of the target benthic organism sample are identified based on the benthic organism identification model, and the initial identification result of the target benthic organism sample is obtained, specifically: The appearance characteristics of benthic organisms at different growth stages in the benthic organism feature database are converted into a numerical expression format, and the benthic organism identification model is constructed according to the appearance characteristics of the data expression format; The target benthic organism sample is collected based on the underwater robot, the position information of the target benthic organism sample collection point is obtained, and the three-dimensional point cloud data within a preset range of the collection point is obtained according to the position information of the collection point; The benthic organism community within a preset range of the collection point is modeled according to the three-dimensional point cloud data, and the three-dimensional structure image data of the benthic organism community is obtained; The image data of the target benthic organism sample is obtained, the appearance characteristics of the target benthic organism sample in the image data are extracted, and the appearance characteristics of the target benthic organism sample are converted into a numerical expression format; The appearance characteristics of the target benthic organism sample in the numerical expression format are imported into the benthic organism identification model for data matching, and the Euclidean distance between the appearance characteristics of the target benthic organism sample and the appearance characteristics of benthic organisms at different growth stages in the benthic organism feature database is calculated; The similarity between the target benthic organism sample and each benthic organism at different growth stages in the benthic organism feature database is evaluated according to the Euclidean distance; The name of the benthic organism and the growth stage to which the benthic organism belongs are output when the similarity is greater than a preset value, and the initial identification result of the target benthic organism sample by the benthic organism identification model is obtained.

[0009] In the scheme, the initial identification result is subjected to uniqueness test, and if the initial identification result of the target benthic organism sample is not unique, data mining is performed on the benthic organism community three-dimensional structure image data to determine the interspecific relationship of the benthic organism community, specifically: The benthic organism identification type data contained in the initial identification result is obtained, the similarity of each benthic organism identification type is obtained, and a similarity distribution curve is constructed; According to the similarity distribution curve, if the maximum similarity value is greater than a preset similarity value and there is no other data point greater than the preset similarity value in the similarity distribution curve, the benthic organism type corresponding to the maximum similarity value and the growth stage to which the benthic organism belongs are marked as the unique identification result; if the initial identification result is a unique identification result, taking the initial identification result as a final identification result of the target benthic organism sample; if multiple data points greater than the preset similarity value or the maximum similarity value is less than the preset similarity value appear in the similarity distribution curve, marking the initial identification result of the target benthic organism sample as a non-unique identification result; if the initial identification result is a non-unique identification result, labeling each biological species in the three-dimensional structure image data of the benthic organism community with a name, and performing data mining on each biological species based on a crawler technology to obtain food web and trophic relationship information of each biological species; determining the interspecific relationship of the benthic organism community where the target benthic organism sample is located according to the food web and trophic relationship information.

[0010] In this scheme, the initial identification result is fused with the interspecific relationship, a relationship network after fusion of each initial identification result and interspecific relationship is constructed based on a graph theory algorithm, and a plurality of community interspecific relationship networks are obtained, specifically: When the initial identification result is a non-unique identification result and multiple data points greater than the preset similarity value appear in the similarity distribution curve, the benthic organism identification type corresponding to the data points greater than the preset similarity value is taken as a fusion species element; When the initial identification result is a non-unique identification result and the maximum similarity value in the similarity distribution curve is less than the preset similarity value, the benthic organism identification type corresponding to the preset number of data points with the maximum similarity in the similarity distribution curve is taken as a fusion species element; obtaining food web and trophic relationship information of each fusion species element, calculating the similarity degree between each fusion species element and the food web and trophic relationship information of each biological species in the benthic organism community, and determining the niche overlap index of each fusion species element and each biological species in the benthic organism community according to the similarity degree; if the niche overlap index of the fusion species element and a biological species in the benthic organism community is greater than a preset index, the fusion species element and the biological species are marked as a competitive relationship, and the interspecific relationship of the fusion species element and other biological species in the benthic organism community is determined according to the interspecific relationship of the benthic organism community, to obtain a first fusion scheme; if the niche overlap index of the fusion species element and the biological species in the benthic organism community is not greater than the preset index, the interspecific relationship of the fusion species element and each biological species in the benthic organism community is determined according to the food web and trophic relationship information of the fusion species element of the fusion species element, to obtain a second fusion scheme; The fusion species element and the interspecies relationship of the benthic community are fused according to the first fusion scheme and the second fusion scheme, and a relationship network after fusion of the fusion species element and the interspecies relationship is constructed based on a graph algorithm, to obtain multiple community interspecies relationship networks.

[0011] In the scheme, the existence credibility of each initial identification result in the community interspecies relationship network is determined according to the community interspecies relationship network, and the target benthic organism sample is subjected to secondary identification according to the existence credibility, to obtain a final identification result, specifically: The number of connections of each initial identification result with other network nodes in the community interspecies relationship network is determined according to the community interspecies relationship network, and the correlation degree of each initial identification result in the community interspecies relationship network is determined according to the number of connections; The niche rationality of each initial identification result in the community interspecies relationship network is determined according to the niche index and the interspecies relationship of each initial identification result in the community interspecies relationship network; The existence credibility of each initial identification result in the community interspecies relationship network is determined by comprehensive scoring according to the correlation degree and the niche rationality; The target benthic organism sample is subjected to secondary identification according to the existence credibility, and the initial identification result with the highest existence credibility is taken as the final identification result.

[0012] The second aspect of the present application also provides a benthic organism sample identification and analysis system based on data mining, which comprises a memory and a processor, and the memory comprises a benthic organism sample identification and analysis method program based on data mining, and the benthic organism sample identification and analysis method program based on data mining is executed by the processor to realize the following steps: Standard image data of benthic organisms at different growth stages are acquired, appearance features of the benthic organisms are extracted according to the standard image data, and a benthic organism feature database is constructed according to the appearance features; A benthic organism identification model is constructed according to the benthic organism feature database, a target benthic organism sample is collected based on an underwater robot, three-dimensional structure image data of a benthic organism community within a preset range of a collection point are acquired, and appearance features of the target benthic organism sample are identified based on the benthic organism identification model, to obtain an initial identification result of the target benthic organism sample; The initial identification result is subjected to uniqueness inspection, if the initial identification result of the target benthic organism sample is not unique, data mining is performed on the three-dimensional structure image data of the benthic organism community, to determine interspecies relationships of the benthic organism community; Each initial identification result is fused with the interspecies relationships, a relationship network after fusion of each initial identification result and the interspecies relationships is constructed based on a graph algorithm, to obtain multiple community interspecies relationship networks; According to the existence credibility of each initial identification result in the community population relationship network determined according to the community interspecific relationship network, the target benthic organism sample is subjected to secondary identification according to the existence credibility, and a final identification result is obtained.

[0013] The application discloses a benthic organism sample identification analysis method and system based on data mining. The method first acquires standard image data of benthic organisms at different growth stages, extracts appearance features, and constructs a feature database; an identification model is established based on the database, target samples and community three-dimensional structure image data are collected by using an underwater robot, initial identification is performed; if the result is not unique, interspecific relationships are mined, a community relationship network is constructed by combining a graph algorithm, the credibility of the identification result is calculated, secondary identification is performed, and a final result is obtained. The application improves identification accuracy and reliability, and is suitable for marine ecological monitoring and biodiversity research. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 A flowchart of a benthic organism sample identification analysis method based on data mining is shown. Figure 2 A flowchart of constructing a benthic organism feature database is shown. Figure 3 A flowchart of obtaining a final identification result is shown. Figure 4 A block diagram of a benthic organism sample identification analysis system based on data mining is shown. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0017] Figure 1 A flowchart of a benthic organism sample identification analysis method based on data mining is shown.

[0018] As Figure 1 shown, the first aspect of the present application provides a benthic organism sample identification analysis method based on data mining, comprising: S102, standard image data of benthic organisms in different growth stages is acquired, appearance features of the benthic organisms are extracted according to the standard image data, and a benthic organism feature database is constructed according to the appearance features; S104, a benthic organism identification model is constructed according to the benthic organism feature database, a target benthic organism sample is collected by the underwater robot, three-dimensional structure image data of a benthic organism community in a preset range of the collection point is acquired, appearance features of the target benthic organism sample are identified based on the benthic organism identification model, and an initial identification result of the target benthic organism sample is obtained; S106, uniqueness verification is performed on the initial identification result, if the initial identification result of the target benthic organism sample is not unique, data mining is performed on the three-dimensional structure image data of the benthic organism community to determine interspecific relationships of the benthic organism community; S108, each initial identification result is fused with the interspecific relationships, a relationship network after fusion of each initial identification result and the interspecific relationships is constructed based on a graph theory algorithm, and a plurality of community interspecific relationship networks are obtained; S110, existence credibility of each initial identification result in the community interspecific relationship network is determined according to the community interspecific relationship network, secondary identification is performed on the target benthic organism sample according to the existence credibility, and a final identification result is obtained.

[0019] It should be noted that through standard image data acquisition, appearance features of benthic organisms in different growth stages are covered, so that the identification model is comprehensive, the benthic organism feature database is constructed, the features of the biological sample are associated with the growth stage to form structured data for subsequent matching; the identification model is constructed according to the feature database, the underwater robot is used to collect the sample and the three-dimensional structure image data of the benthic organism community, and then the appearance features of the sample are identified by the identification model to obtain the initial identification result, which realizes rapid preliminary identification of the target benthic organism sample and improves the identification efficiency. The initial identification result is subjected to uniqueness verification, if the initial identification result is not unique, the three-dimensional structure image data is mined to determine the interspecific relationships, which can solve the problem of ambiguous identification result and provide more dimensional information for accurate identification. The initial identification result is fused with the interspecific relationships to construct a relationship network, which can be analyzed in depth from the perspective of ecological relationship, existence credibility is determined and secondary identification is performed to obtain the final result, which greatly improves the accuracy and reliability of the identification of the benthic organism sample. The benthic organism sample does not include microorganisms that are not visible to the naked eye.

[0020] Figure 2 A flowchart for constructing a benthic organism feature database is shown.

[0021] According to the embodiment of the present application, the standard image data of benthic organisms in different growth stages is acquired, the appearance features of benthic organisms are extracted according to the standard image data, and a benthic organism feature database is constructed according to the appearance features, specifically: S202, standard image data of benthic organisms in different growth stages is acquired, and the standard image data is edge detected based on a Canny operator to extract contour features of benthic organisms in different growth stages; S204, the perimeter, area, aspect ratio and circularity of benthic organisms in different growth stages are calculated according to the contour features to obtain scale features of benthic organisms; S206, shape features of benthic organisms in the standard image data are extracted based on Hu invariant moments, and texture features of benthic organisms in the standard image data are extracted based on a gray level co-occurrence matrix; S208, histogram analysis is performed on the standard image data to determine color features of benthic organisms in different growth stages, and the contour features, scale features, shape features, texture features and color features are labeled as appearance features of benthic organisms; S210, a benthic organism feature database is constructed, the appearance features are imported into the benthic organism feature database for storage, and the appearance features in the benthic organism feature database are associated with the growth stages of benthic organisms.

[0022] It should be noted that by acquiring standard image data of benthic organisms in different growth stages, the contour features are extracted by edge detection using a Canny operator to accurately outline the shape of benthic organisms, providing a basis for subsequent analysis. The perimeter, area and other scale features are calculated based on the contour features to quantify the size and shape of benthic organisms. The shape and texture features are extracted using Hu invariant moments and a gray level co-occurrence matrix to describe the appearance details from different angles. The color features are determined by histogram analysis to improve the dimension of appearance features. These features are labeled and imported into the database for storage, and are also associated with the growth stages to construct a comprehensive and structured benthic organism feature database, laying a data foundation for subsequent benthic organism identification. The standard image data is clear image data of benthic organisms.

[0023] According to the embodiment of the present application, the benthic organism identification model is constructed according to the benthic organism feature database, the target benthic organism sample is collected based on an underwater robot, three-dimensional structure image data of benthic organism communities within a preset range of the collection point is acquired, the appearance features of the target benthic organism sample are identified based on the benthic organism identification model to obtain an initial identification result of the target benthic organism sample, specifically: The appearance features of benthic organisms in different growth stages in the benthic organism feature database are converted into a numerical expression format, and the benthic organism identification model is constructed according to the appearance features of the data expression format; Collecting a target benthic organism sample based on an underwater robot, obtaining position information of a collection point of the target benthic organism sample, and obtaining three-dimensional point cloud data within a preset range of the collection point according to the position information of the collection point; Modeling a benthic organism community within the preset range of the collection point according to the three-dimensional point cloud data, and obtaining benthic organism community three-dimensional structure image data; Obtaining image data of the target benthic organism sample, extracting appearance features of the target benthic organism sample in the image data, and converting the appearance features of the target benthic organism sample into a numerical expression format; Importing the appearance features of the target benthic organism sample in the numerical expression format into the benthic organism identification model for data matching, and calculating the Euclidean distance between the appearance features of the target benthic organism sample and the appearance features of benthic organisms at different growth stages in a benthic organism feature database; Evaluating the similarity between the target benthic organism sample and each benthic organism at different growth stages in the benthic organism feature database according to the Euclidean distance; Outputting the name of the benthic organism and the growth stage to which the benthic organism belongs when the similarity is greater than a preset value, and obtaining an initial identification result of the target benthic organism sample by the benthic organism identification model.

[0024] It should be noted that converting the benthic organism feature database and the appearance features of the target sample into a numerical format solves the problem of data format difference, realizes data standardization and compatibility, and accurately quantifies feature differences by using the Euclidean distance, thereby providing a reliable basis for screening. In the identification process, the computer can quickly complete data processing by automatic matching identification based on similarity, process a large number of samples in a short time, effectively exclude interference terms by a preset similarity threshold, reduce the risk of misjudgment, and improve the reliability of the identification result.

[0025] According to an embodiment of the present application, the initial identification result is subjected to uniqueness verification, and if the initial identification result of the target benthic organism sample is not unique, the benthic organism community three-dimensional structure image data is subjected to data mining to determine the interspecific relationship of the benthic organism community, specifically as follows: Obtaining benthic organism identification type data contained in the initial identification result, obtaining the similarity of each benthic organism identification type, and constructing a similarity distribution curve; According to the similarity distribution curve, if the maximum value of the similarity is greater than a preset similarity value and there is no other data point greater than the preset similarity value in the similarity distribution curve, the benthic organism type corresponding to the maximum value of the similarity and the growth stage to which the benthic organism belongs are marked as a unique identification result; If the initial identification result is a unique identification result, the initial identification result is taken as a final identification result of the target benthic organism sample. If multiple data points greater than the preset similarity value or the maximum similarity value is less than the preset similarity value appear in the similarity distribution curve, the initial identification result of the target benthic organism sample is marked as a non-unique identification result; If the initial identification result is a non-unique identification result, the name of each biological species in the three-dimensional structure image data of the benthic organism community is labeled, and data mining is performed on each biological species based on a crawler technology to obtain food web and nutritional relationship information of each biological species; The interspecific relationship of the benthic organism community in which the target benthic organism sample is located is determined according to the food web and nutritional relationship information.

[0026] It should be noted that different types of benthic organisms may have similar appearance characteristics at certain growth stages, such as similar larval morphology of some small benthic organisms. When similarity matching is performed based on appearance characteristics and a benthic organism feature database, multiple high similarity results may occur. When multiple data points greater than the preset similarity value appear in the similarity distribution curve, it means that multiple different types of benthic organisms have a high similarity to the target benthic organism sample, and it is difficult to determine which type the target sample belongs to. If the maximum similarity value is less than the preset similarity value, it means that the similarity of the target benthic organism sample to all types in the benthic organism feature database is not high enough, and it cannot be determined that the target benthic organism sample has sufficient similarity to any type of benthic organism in the existing database to determine its type, so a unique identification result cannot be obtained.

[0027] According to an embodiment of the present application, the initial identification result is fused with the interspecific relationship, a relationship network after fusion of each initial identification result and interspecific relationship is constructed based on a graph theory algorithm, and multiple community interspecific relationship networks are obtained, specifically: When the initial identification result is a non-unique identification result and multiple data points greater than the preset similarity value appear in the similarity distribution curve, the benthic organism identification type corresponding to the data points greater than the preset similarity value is taken as a fusion species element; When the initial identification result is a non-unique identification result and the maximum similarity value in the similarity distribution curve is less than the preset similarity value, the benthic organism identification type corresponding to a preset number of data points with the maximum similarity in the similarity distribution curve is taken as a fusion species element; It should be noted that when multiple data points greater than the preset similarity value appear in the similarity distribution curve, the benthic organism identification types corresponding to these data points have high similarity with the target benthic organism sample, and they are all likely to be the true attribution types of the target sample. Taking these types as the fusion species elements greatly reduces the amount of data analysis and avoids further processing of low-similarity identification results; and when the maximum similarity is less than the preset similarity value, it indicates that there is no clear matching type with high similarity to the target sample. At this time, the benthic organism identification types corresponding to the preset number of data points with the maximum similarity in the similarity distribution curve are selected as the fusion species elements, because these data points, although the similarity does not reach the preset high value, are relatively close to the target sample. By selecting them, the most likely benthic organism type can be screened out within a limited range, improving the accuracy of the final identification.

[0028] Obtaining food web and nutrient relationship information of each fusion species element, calculating the similarity between each fusion species element and the food web and nutrient relationship information of each biological species in the benthic community, and determining the niche overlap index of each fusion species element and each biological species in the benthic community according to the similarity; If the niche overlap index of the fusion species element and a biological species in the benthic community is greater than a preset index, the fusion species element and the biological species are identified as a competitive relationship, and the interspecific relationship of the fusion species element and other biological species in the benthic community is determined according to the interspecific relationship of the benthic community, to obtain a first fusion scheme; If the niche overlap index of the fusion species element and the biological species in the benthic community is not greater than the preset index, the interspecific relationship of the fusion species element and each biological species in the benthic community is determined according to the food web and nutrient relationship information of the fusion species element, to obtain a second fusion scheme; Fusing the interspecific relationship of the fusion species element and the benthic community according to the first fusion scheme and the second fusion scheme, and constructing a relationship network of the fused interspecific relationship of the fusion species element and the benthic community based on a graph theory algorithm, to obtain a plurality of community interspecific relationship networks.

[0029] It should be noted that when the niche overlap index of the fusion species element and a biological species in the benthic community is greater than a preset index, it indicates that there is a large degree of competition between the two in resource acquisition and living space. For example, two benthic organisms that both take the same algae as the main food source and have a high degree of overlap in the habitat area have a high niche overlap index. Based on this, they are marked as a competitive relationship, and then the interspecific relationship of the fusion species element and other biological species can be determined based on the interspecific relationship of the benthic community, and the first fusion scheme is obtained. If the niche overlap index is not greater than the preset index, it indicates that the competitive relationship between the fusion species element and the biological species in the community is not significant. At this time, based on the food web and nutritional relationship information of the fusion species element itself, the interspecific relationship between it and each biological species in the community can be more comprehensively determined, and the second fusion scheme is formed. The fusion of the interspecific relationship of the fusion species element and the benthic community is inserting the fusion species element into the interspecific relationship of the benthic community. For example, there are fusion species elements A, B, C and species D, E, F contained in the interspecific relationship. Each time fusion only fuses one element into the interspecific relationship. The elements contained in the fused multiple community interspecific relationships are (A, D, E, F), (B, D, E, F), (C, D, E, F). The purpose of this is to determine the existence rationality of the fusion species element in the interspecific relationship of the benthic community in the subsequent invention steps, and then the fusion species element with the most reasonable existence is taken as the final identified species. The higher the similarity between the food web and nutritional relationship information of the fusion species element and the biological species in the benthic community, the higher the niche overlap index. The fusion species element is the candidate species used as the target benthic biological sample for the final species identification type.

[0030] Figure 3 A flowchart for obtaining the final identification result of the present application is shown.

[0031] According to the embodiment of the present application, the existence credibility of each initial identification result in the community interspecific relationship network is determined according to the community interspecific relationship network, the target benthic biological sample is identified again according to the existence credibility, and the final identification result is obtained. Specifically: S302, the connection number of each initial identification result with other network nodes in the community interspecific relationship network is determined according to the community interspecific relationship network, and the association degree of each initial identification result in the community interspecific relationship network is determined according to the connection number; S304, the niche rationality of each initial identification result in the community interspecific relationship network is determined according to the niche index and interspecific relationship of each initial identification result in the community interspecific relationship network; S306, the existence credibility of each initial identification result in the community interspecific relationship network is determined by comprehensive scoring according to the association degree and niche rationality. S308, according to the existence credibility, the target benthic organism sample is identified again, and the initial identification result with the highest existence credibility is taken as the final identification result.

[0032] It should be noted that the determination of the existence credibility combines the correlation degree and the niche rationality. The correlation degree reflects the connection number of the initial identification result in the community population relationship network, and the more the connection number is, the closer the relationship between the identification result and other organisms in the community is, and the more universal and reasonable the existence in the community is. The niche rationality is obtained based on the niche index and the interspecific relationship, and reflects the rationality of the identification result in the niche distribution and interspecific relationship. Through the comprehensive score of the two dimensions, the position and role of the benthic organism in the community ecological structure are comprehensively considered, and the one-sidedness of the single factor judgment is avoided. Through the determination of the existence credibility, the result most consistent with the community ecological relationship can be screened from the multiple candidate results. This process further verifies and optimizes the initial identification result, effectively eliminates the unreasonable result, and greatly improves the accuracy and reliability of the final identification result. When the identification result is not unique, it is difficult to determine the species to which the target benthic organism sample belongs only by relying on the appearance characteristics. Through the analysis of the community interspecific relationship network, more identification clues can be provided from the ecological level. For example, if two benthic organisms with similar appearance have different positions in the food web, one of which feeds on algae and the other of which feeds on small plankton, they can be accurately distinguished according to the food web information, thereby effectively improving the accuracy of identification and reducing misjudgment.

[0033] Figure 4 A block diagram of a benthic organism sample identification analysis system based on data mining is shown.

[0034] The second aspect of the present application also provides a benthic organism sample identification analysis system 4 based on data mining, which comprises a memory 41 and a processor 42, wherein the memory comprises a benthic organism sample identification analysis method program based on data mining, and the benthic organism sample identification analysis method program based on data mining is executed by the processor to realize the following steps: Obtaining standard image data of benthic organisms at different growth stages, extracting appearance characteristics of the benthic organisms according to the standard image data, and constructing a benthic organism feature database according to the appearance characteristics; Constructing a benthic organism identification model according to the benthic organism feature database, collecting a target benthic organism sample based on an underwater robot, and obtaining three-dimensional structure image data of a benthic organism community within a preset range of the collection point, identifying the appearance characteristics of the target benthic organism sample based on the benthic organism identification model, and obtaining an initial identification result of the target benthic organism sample; The initial identification result is subjected to uniqueness test, if the initial identification result of the target benthic organism sample is not unique, the three-dimensional structure image data of the benthic organism community is subjected to data mining, and the interspecific relationship of the benthic organism community is determined; Each initial identification result is fused with the interspecific relationship, a relationship network after fusion of each initial identification result and the interspecific relationship is constructed based on a graph algorithm, and a plurality of community interspecific relationship networks are obtained; The existence credibility of each initial identification result in the community interspecific relationship network is determined according to the community interspecific relationship network, the target benthic organism sample is subjected to secondary identification according to the existence credibility, and a final identification result is obtained.

[0035] The application discloses a benthic organism sample identification analysis method and system based on data mining. The method firstly acquires standard image data of benthic organisms at different growth stages, extracts appearance features and constructs a feature database; an identification model is established based on the database, three-dimensional structure image data of a target sample and a community are collected by using an underwater robot, initial identification is performed; if the result is not unique, interspecific relationships are mined, a community relationship network is constructed by combining a graph algorithm, the credibility of the identification result is calculated, secondary identification is performed, and a final result is obtained. The application improves identification accuracy and reliability, and is suitable for marine ecological monitoring and biodiversity research.

[0036] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above-described device embodiments are only illustrative. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0037] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0038] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0039] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0040] Alternatively, the integrated unit of the present application can be stored in a computer readable storage medium if it is realized in the form of a software function module and sold or used as an independent product. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a RAM, a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0041] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for identifying and analyzing benthic organism samples based on data mining, characterized in that, Includes the following steps: Obtain standard image data of benthic organisms at different growth stages, extract the appearance features of benthic organisms based on the standard image data, and construct a benthic organism feature database based on the appearance features; A benthic organism identification model is constructed based on the benthic organism characteristic database. The target benthic organism sample is collected by an underwater robot, and three-dimensional structural image data of the benthic organism community within a preset range of the collection point is obtained. The appearance characteristics of the target benthic organism sample are identified based on the benthic organism identification model to obtain the initial identification result of the target benthic organism sample. The initial identification results are tested for uniqueness. If the initial identification results of the target benthic organism sample are not unique, data mining is performed on the three-dimensional structural image data of the benthic community to determine the interspecific relationships of the benthic community. Each initial identification result is fused with the interspecific relationship, and a relationship network after the fusion of each initial identification result and the interspecific relationship is constructed based on graph theory algorithm to obtain multiple community interspecific relationship networks; The credibility of each initial identification result in the community population relationship network is determined based on the community interspecific relationship network. The target benthic organism sample is then re-identified based on the credibility of the existence to obtain the final identification result.

2. The method for identifying and analyzing benthic organism samples based on data mining according to claim 1, characterized in that, The process of acquiring standard image data of benthic organisms at different growth stages, extracting appearance features of benthic organisms based on the standard image data, and constructing a benthic organism feature database based on the appearance features specifically involves: Standard image data of benthic organisms at different growth stages are obtained, and edge detection is performed on the standard image data based on the Canny operator to extract the contour features of benthic organisms at different growth stages. Based on the outline features, the perimeter, area, length-to-width ratio, and roundness of benthic organisms at different growth stages are calculated to obtain the scale characteristics of benthic organisms. Shape features of benthic organisms in the standard image data are extracted based on Hu invariant moments, and texture features of benthic organisms in the standard image data are extracted based on gray-level co-occurrence matrix. Histogram analysis was performed on the standard image data to determine the color characteristics of benthic organisms at different growth stages, and the outline features, scale features, shape features, texture features, and color features were labeled as the appearance features of benthic organisms. A benthic organism characteristic database is constructed, the appearance characteristics are imported into the benthic organism characteristic database for storage, and the appearance characteristics in the benthic organism characteristic database are associated with the growth stages of the benthic organisms.

3. The method for identifying and analyzing benthic organism samples based on data mining according to claim 1, characterized in that, The process involves constructing a benthic organism identification model based on the benthic organism characteristic database, collecting target benthic organism samples using an underwater robot, acquiring three-dimensional structural image data of the benthic organism community within a preset range of the collection point, and identifying the appearance characteristics of the target benthic organism samples based on the benthic organism identification model to obtain the initial identification results of the target benthic organism samples. Specifically: The appearance characteristics of benthic organisms at different growth stages in the benthic organism characteristic database are converted into numerical expression formats, and a benthic organism identification model is constructed based on the appearance characteristics in the data expression formats. The underwater robot collects target benthic organism samples, obtains the location information of the target benthic organism sample collection point, and obtains three-dimensional point cloud data within a preset range of the collection point based on the location information of the collection point. The benthic community within a preset range of the collection point is modeled based on the three-dimensional point cloud data to obtain three-dimensional structural image data of the benthic community. Acquire image data of the target benthic organism sample, extract the appearance features of the target benthic organism sample from the image data, and convert the appearance features of the target benthic organism sample into a numerical expression format; The appearance features of the target benthic organism sample in numerical expression format are imported into the benthic organism identification model for data matching, and the Euclidean distance between the appearance features of the target benthic organism sample and the appearance features of benthic organisms at different growth stages in the benthic organism feature database is calculated. The similarity between the target benthic organism sample and benthic organisms at each different growth stage in the benthic organism characteristic database is assessed based on the Euclidean distance. The benthic organisms whose similarity is greater than the preset value are output along with their growth stage to obtain the initial identification results of the benthic organism identification model for the target benthic organism sample.

4. The method for identifying and analyzing benthic organism samples based on data mining according to claim 1, characterized in that, The initial identification results are subjected to a uniqueness test. If the initial identification results of the target benthic organism sample are not unique, data mining is performed on the three-dimensional structural image data of the benthic community to determine the interspecific relationships of the benthic community. Specifically: Obtain the benthic organism identification type data contained in the initial identification results, obtain the similarity of each benthic organism identification type, and construct a similarity distribution curve; According to the similarity distribution curve, if the maximum similarity value is greater than the preset similarity value and there are no other data points in the similarity distribution curve that are greater than the preset similarity value, then the benthic organism type and the growth stage of the benthic organism corresponding to the maximum similarity value will be identified as the unique identification result. If the initial identification result is the only identification result, the initial identification result shall be taken as the final identification result of the target benthic organism sample; If multiple data points with a similarity value greater than the preset similarity value appear in the similarity distribution curve, or if the maximum similarity value is less than the preset similarity value, the initial identification result of the target benthic organism sample will be marked as a non-unique identification result. If the initial identification result is not unique, the name of each species in the three-dimensional structure image data of the benthic community is labeled, and data mining is performed on each species based on crawler technology to obtain the food web and nutrient relationship information of each species. The interspecific relationships within the benthic community of the target benthic organism sample are determined based on the food web and nutrient relationship information.

5. The method for identifying and analyzing benthic organism samples based on data mining according to claim 4, characterized in that, The process involves fusing each initial identification result with the interspecific relationship, constructing a relationship network based on graph theory algorithms, and obtaining multiple interspecific relationship networks for communities. Specifically: When the initial identification result is not unique and multiple data points with a similarity value greater than the preset similarity value appear in the similarity distribution curve, the benthic organism identification type corresponding to the data points with a similarity value greater than the preset similarity value is used as the fusion species element. When the initial identification result is not unique and the maximum similarity value in the similarity distribution curve is less than the preset similarity value, the benthic organism identification type corresponding to the preset number of data points with the highest similarity in the similarity distribution curve is used as the fusion species element. Obtain food web and trophic relationship information for each fused species element, calculate the similarity between each fused species element and the food web and trophic relationship information of each species in the benthic community, and determine the niche overlap index between each fused species element and each species in the benthic community based on the similarity. If the niche overlap index between the fused species element and a certain species in the benthic community is greater than a preset index, the fused species element and that species are identified as competing, and the interspecific relationships between the fused species element and other species in the benthic community are determined based on the interspecific relationships of the benthic community, thus obtaining the first fusion scheme. If the niche overlap index between the fused species element and the species in the benthic community is not greater than the preset index, then the interspecific relationship between the fused species element and each species in the benthic community is determined based on the food web and trophic relationship information of the fused species element, and the second fusion scheme is obtained. According to the first fusion scheme and the second fusion scheme, the fused species elements are fused with the interspecific relationships of the benthic community, and a relationship network after the fusion of fused species elements and interspecific relationships is constructed based on graph theory algorithm to obtain multiple community interspecific relationship networks.

6. The method for identifying and analyzing benthic organism samples based on data mining according to claim 1, characterized in that, The process involves determining the credibility of each initial identification result within the community population relationship network based on the interspecific relationship network, and then performing a secondary identification of the target benthic organism sample based on the credibility of the existence to obtain the final identification result. Specifically: The number of connections between each initial identification result and other network nodes in the community population relationship network is determined based on the community interspecific relationship network, and the degree of association of each initial identification result in the community interspecific relationship network is determined based on the number of connections. The niche rationality of each initial identification result in the interspecific relationship network of the community is determined based on the niche index and interspecific relationship of each initial identification result in the interspecific relationship network of the community; Based on the correlation and niche rationality, a comprehensive score is calculated to determine the credibility of each initial identification result in the interspecific relationship network of the community. The target benthic organism sample was re-identified based on the credibility of the existence, and the initial identification result with the highest credibility was taken as the final identification result.

7. A data mining-based benthic organism sample identification and analysis system, characterized in that, The data mining-based benthic organism sample identification and analysis system includes a storage device and a processor. The storage device includes a data mining-based benthic organism sample identification and analysis method program. When the data mining-based benthic organism sample identification and analysis method program is executed by the processor, the following steps are implemented: Obtain standard image data of benthic organisms at different growth stages, extract the appearance features of benthic organisms based on the standard image data, and construct a benthic organism feature database based on the appearance features; A benthic organism identification model is constructed based on the benthic organism characteristic database. The target benthic organism sample is collected by an underwater robot, and three-dimensional structural image data of the benthic organism community within a preset range of the collection point is obtained. The appearance characteristics of the target benthic organism sample are identified based on the benthic organism identification model to obtain the initial identification result of the target benthic organism sample. The initial identification results are tested for uniqueness. If the initial identification results of the target benthic organism sample are not unique, data mining is performed on the three-dimensional structural image data of the benthic community to determine the interspecific relationships of the benthic community. Each initial identification result is fused with the interspecific relationship, and a relationship network after the fusion of each initial identification result and the interspecific relationship is constructed based on graph theory algorithm to obtain multiple community interspecific relationship networks; The credibility of each initial identification result in the community population relationship network is determined based on the community interspecific relationship network. The target benthic organism sample is then re-identified based on the credibility of the existence to obtain the final identification result.

Images