Fish data processing method and device based on machine learning, medium and program

Abstract

The invention relates to the technical field of vehicles, in particular to a fish data processing method, device, medium and program based on machine learning, and the method comprises the steps: obtaining fish data and environment data of a target water area; extracting at least one fish morphological feature in the fish data and an environment feature of the environment data; the at least one fish morphological feature and the environment feature are input into a machine learning model, the machine learning model outputs a fish and environment matching result, and the machine learning model generates a fish morphological matrix based on the at least one fish morphological feature and generates an environment feature matrix based on the environment feature; determining a matching result of the fish and the environment according to the similarity of the fish form matrix and the environment feature matrix; and determining fishes matched with the target water area according to a matching result. Therefore, the problems of time consumption, labor consumption, low accuracy and the like due to the fact that the fishes cannot adapt to the current water area environment when the types of the fishes suitable for being cultured in the current water area are selected according to experience in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a fish data processing method, device, medium and program based on machine learning. Background Art

[0002] In traditional fish farming and environmental management, since different water bodies correspond to different aquatic environments, it is very important to understand the interaction between fish and specific environments.

[0003] In related technologies, empirical knowledge and manual observation are often relied upon to determine whether fish are suitable for a specific environment, so as to recommend corresponding fish for different water environments. However, this method is not only time-consuming and labor-intensive, but also difficult to accurately predict the adaptability of fish in a specific environment, resulting in limited effectiveness of fish farming and environmental protection measures. Summary of the invention

[0004] The present application provides a fish data processing method, device, medium and program based on machine learning to solve the problems in the related technology of selecting the type of fish suitable for breeding in the current water area based on experience, which leads to the inability of fish to adapt to the current water environment, resulting in time-consuming and labor-intensive processing and low accuracy.

[0005] The first aspect of the present application provides a fish data processing method based on machine learning, comprising the following steps: acquiring fish data and environmental data of a target water area; extracting at least one fish morphological feature in the fish data and the environmental feature of the environmental data; inputting the at least one fish morphological feature and the environmental feature into a machine learning model, and the machine learning model outputs a matching result between the fish and the environment, wherein the machine learning model generates a fish morphological matrix based on at least one fish morphological feature and an environmental feature matrix based on the environmental feature, and determines the matching result between the fish and the environment according to the similarity between the fish morphological matrix and the environmental feature matrix; and determines the fish that matches the target water area according to the matching result.

[0006] Optionally, the machine learning model includes an input layer, a feature extraction layer, a matching layer and an output layer, wherein the input layer extracts at least one fish morphological feature and environmental feature of the input; the feature extraction layer extracts the plant species corresponding to the fish and the environment from the fish morphological features and the environmental features; the matching layer determines the matching result based on the plant species corresponding to the fish and the environment; and the output layer outputs the matching result between the fish and the environment.

[0007] Optionally, the feature extraction layer includes multiple convolution layers, wherein each convolution layer performs a convolution operation on the at least one word vector to obtain fish species corresponding to the fish morphological features and environmental features and plant species corresponding to the environment, and the multiple convolution layers extract plant species suitable for the survival of each type of fish layer by layer; the matching layer determines the matching result by comparing the plant species for the survival of each type of fish with the plant species corresponding to the environment.

[0008] Optionally, before inputting the at least one fish morphological feature and the environmental feature into the machine learning model, it also includes: obtaining a training data set and a verification data set, wherein the training data set and the verification data set both include fish data and environmental data; training the machine learning model using the training data set, and verifying the machine learning model using the verification data set until a preset stop condition is met.

[0009] Optionally, the obtaining of environmental data of the target water area includes: extracting water samples of the target water area; analyzing gene sequences of the water samples to determine plant species existing in the current environment; and generating environmental data of the target water area according to the plant species.

[0010] Optionally, the obtaining of fish data includes: identifying external morphological characteristic images of different fish; converting the external morphological characteristic images into grayscale images, and generating corresponding fish data according to the grayscale images.

[0011] Optionally, fish that match the target waters are determined based on the matching result, including: if the fish matches the environment, providing fish breeding suggestions; if the fish does not match the environment, recommending fish species suitable for the specific environment, or selecting the best breeding environment for the specific fish species.

[0012] A second aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the fish data processing method based on machine learning as described in the above embodiment.

[0013] The third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the fish data processing method based on machine learning as described in the above embodiment.

[0014] The fourth aspect of the present application provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the fish data processing method based on machine learning as described in the above embodiment is implemented.

[0015] Therefore, this application has at least the following beneficial effects:

[0016] The embodiment of the present application can extract at least one fish morphological feature in fish data and environmental features of environmental data, input at least one fish morphological feature and environmental feature into a machine learning model, and the machine learning model outputs the matching result between the fish and the environment, and determines the fish that matches the target water area based on the matching result, thereby being able to accurately predict the adaptability of the fish in the current water environment, so as to make corresponding breeding suggestions, greatly improving the efficiency of fish breeding and the sustainability of the ecosystem.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0019] Figure 1 A flow chart of a fish data processing method based on machine learning provided according to an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a method for fish data machine learning based on the fusion of environmental DNA and morphological learning provided according to an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0023] The following describes the fish data processing method, electronic device, storage medium and program based on machine learning according to an embodiment of the present application with reference to the accompanying drawings.

[0024] Specifically, Figure 1 A flow chart of a fish data processing method based on machine learning provided in an embodiment of the present application.

[0025] like Figure 1 As shown, the fish data processing method based on machine learning includes the following steps:

[0026] In step S101, fish data and environmental data of the target water area are obtained.

[0027] Among them, the target waters can be selected according to actual needs without specific limitations.

[0028] It can be understood that the embodiments of the present application can obtain fish data and environmental data of the target waters to facilitate the subsequent extraction of at least one fish morphological feature in the fish data and an environmental feature of the environmental data.

[0029] In an embodiment of the present application, obtaining environmental data of a target water area includes: extracting water samples of the target water area; analyzing the gene sequences of the water samples to determine the plant species present in the current environment; and generating environmental data of the target water area based on the plant species.

[0030] It can be understood that the embodiments of the present application can extract water samples from the target water area; analyze the genetic sequences of the water samples to determine the plant types existing in the current environment; and generate environmental data of the target water area based on the plant types, so as to facilitate the subsequent determination of matching fish based on the plant types.

[0031] Specifically, sampling personnel need to reach the target waters and use professional sampling tools (such as water sample bottles, sampling nets, etc.) to collect water samples. When sampling, the representativeness of the samples should be considered to ensure that different areas of the target waters are covered, so as to more comprehensively reflect the situation of the entire water area; and extract DNA from the collected water samples; use polymerase chain reaction (PCR) technology to amplify specific DNA fragments, which usually contain plant-specific markers, such as certain regions in the chloroplast genome; sequence the amplified DNA fragments, which can be achieved through high-throughput sequencing technology; compare the sequenced data with a known plant DNA database to identify the plant species present in the water sample; bioinformatics software and algorithms may be used during the analysis process to assist in processing large amounts of data and screen out effective information.

[0032] In an embodiment of the present application, obtaining fish data includes: identifying external morphological characteristic images of different fish; converting the external morphological characteristic images into grayscale images, and generating corresponding fish data based on the grayscale images.

[0033] It can be understood that the embodiments of the present application can identify the external morphological characteristic images of different fish; convert the external morphological characteristic images into grayscale images, and generate corresponding fish data based on the grayscale images to facilitate the subsequent extraction of fish morphological characteristics.

[0034] Specifically, if Figure 2As shown in the figure, the recognition of fish external morphological feature images: using image recognition technology, the external morphological features of fish, such as body shape, color, spot distribution, fin shape, etc., can be automatically identified from the photos of fish taken; deep learning methods, especially convolutional neural networks (CNNs), can be used to train a large number of fish images so that the model can automatically capture these features. Grayscale image conversion and fish data generation: the identified fish external morphological feature images are converted into grayscale images, which can reduce the data dimension and simplify the calculation complexity; the corresponding fish data is generated according to the pixel values ​​of the grayscale images; the value of each pixel reflects the brightness information of the position, which can be used to construct the fish morphology matrix.

[0035] In step S102, at least one fish morphological feature in the fish data and an environmental feature in the environmental data are extracted.

[0036] It can be understood that the embodiments of the present application can extract at least one fish morphological feature in the fish data and the environmental feature of the environmental data to facilitate the subsequent determination of the matching result between the fish and the environment.

[0037] In step S103, at least one fish morphological feature and environmental feature are input into the machine learning model, and the machine learning model outputs the matching result between the fish and the environment, wherein the machine learning model generates a fish morphological matrix based on the at least one fish morphological feature and an environmental feature matrix based on the environmental feature, and determines the matching result between the fish and the environment according to the similarity between the fish morphological matrix and the environmental feature matrix.

[0038] The machine learning model includes an input layer, a feature extraction layer, a matching layer and an output layer, wherein the input layer extracts at least one fish morphological feature and environmental feature of the input; the feature extraction layer extracts the plant species corresponding to the fish and the environment from the fish morphological features and the environmental features; the matching layer determines the matching result according to the plant species corresponding to the fish and the environment; and the output layer outputs the matching result between the fish and the environment. The feature extraction layer includes multiple convolutional layers, wherein each convolutional layer performs a convolution operation on at least one word vector to obtain the plant species corresponding to the fish morphological features and the environmental features respectively, and the multiple convolutional layers extract the plant species suitable for each fish to survive layer by layer; the matching layer compares the plant species corresponding to the environment and the plant species corresponding to each fish to survive to determine the matching result.

[0039] It can be understood that the embodiment of the present application can input at least one fish morphological feature and environmental feature into a machine learning model, and the machine learning model outputs the matching result between the fish and the environment to improve the accuracy of the matching between the fish and the environment.

[0040] Specifically, an environmental characteristic matrix is ​​generated based on environmental characteristics: in this matrix, each column represents a plant, and each row represents a sample or an area; for example: an environmental characteristic matrix (mxm, m rows xm columns), in which the horizontal direction represents the plants, and the m value is determined by the number of plant species; the vertical direction represents whether the corresponding plant exists, 0 represents the absence of the plant, 1 represents the presence of the plant, 2 represents the presence of a large number of the plant, and so on; in this way, the composition of the plant community in the target waters can be quantitatively described, thereby reflecting the ecological environmental characteristics of the waters.

[0041] Generate a fish morphology matrix based on at least one fish morphology feature: construct a matrix according to the pixel values ​​in the grayscale image, each element of the matrix represents the brightness value of a pixel; for example: fish morphology matrix (mxm), wherein the size of the matrix can be determined according to the resolution of the image, for example, an image with a resolution of 100×100 will generate a 100×100 matrix.

[0042] In an embodiment of the present application, before inputting at least one fish morphological feature and environmental feature into the machine learning model, it also includes: obtaining a training data set and a verification data set, wherein the training data set and the verification data set both include fish data and environmental data; training the machine learning model using the training data set, and verifying the machine learning model using the verification data set until a preset stop condition is met.

[0043] Among them, the preset stopping condition can be that the accuracy of the machine learning model reaches 90%, which can be set according to actual needs without specific limitation.

[0044] It can be understood that the embodiments of the present application can obtain a training data set and a verification data set, use the training data set to train the machine learning model, and use the verification data set to verify the machine learning model until the preset stop condition is met, so as to improve the accuracy of matching fish and environment.

[0045] In step S104, fish species matching the target water area are determined according to the matching results.

[0046] It can be understood that the embodiments of the present application can determine the fish that match the target waters based on the matching results, so as to make corresponding breeding suggestions, greatly improving the efficiency of fish breeding and the sustainability of the ecosystem.

[0047] In an embodiment of the present application, the fish that matches the target waters is determined based on the matching results, including: if the fish matches the environment, fish farming suggestions are provided; if the fish does not match the environment, fish species suitable for the specific environment are recommended, or the best farming environment is selected for the specific fish species.

[0048] It can be understood that the embodiments of the present application can provide fish farming suggestions when the fish and the environment match; if the fish and the environment do not match, it can recommend fish species suitable for the specific environment, or select the best farming environment for the specific fish species, and give corresponding suggestions to enhance the user experience.

[0049] Specifically, fish farming advice is provided if the fish and environment are compatible:

[0050] 1. Stocking density recommendations: Based on the growth habits of fish and the carrying capacity of the current environment, appropriate stocking density is recommended to avoid disease transmission and slow growth caused by overcrowding.

[0051] 2. Feed type and feeding strategy: Based on the feeding characteristics of fish, recommend suitable feed types and give reasonable feeding frequency and amount.

[0052] 3. Water quality management: Provide water quality monitoring and adjustment suggestions, such as the maintenance range of key water quality parameters such as pH value, dissolved oxygen content, and ammonia nitrogen level.

[0053] 4. Disease prevention: Provide preventive measures for common diseases according to the fish species, including vaccination, regular disinfection, etc.

[0054] 5. Environmental improvement: Propose to increase or adjust the plant species or structure in the water body to optimize the living environment of fish.

[0055] If the fish and environment are not matched, then recommend fish species suitable for the specific environment:

[0056] 1. Analyze the characteristics of the current environment, such as water temperature, light, nutrient concentration and other factors, and recommend fish species that are suitable for these environmental conditions.

[0057] The growth performance of different fish species in the current environment can be predicted based on machine learning models, and the most suitable species can be selected.

[0058] 2. Choose the best breeding environment for a specific fish species:

[0059] If a specific fish species is already available but the current environment is not suitable, then an environment more suitable for the growth of this fish can be found or created. This process may involve modifying the existing environment, such as changing the temperature, flow rate or adding specific nutrients to the water; or it may recommend breeding in a different geographical location or water type to achieve the best breeding results.

[0060] According to the fish data processing method based on machine learning proposed in the embodiment of the present application, at least one fish morphological feature in the fish data and the environmental feature of the environmental data are extracted, and at least one fish morphological feature and the environmental feature are input into the machine learning model. The machine learning model outputs the matching result between the fish and the environment, and the fish matching the target water area is determined based on the matching result, so as to accurately predict the adaptability of the fish in the current water environment, so as to make corresponding breeding suggestions, greatly improving the efficiency of fish breeding and the sustainability of the ecosystem.

[0061] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0062] A memory 301 , a processor 302 , and a computer program stored in the memory 301 and executable on the processor 302 .

[0063] When the processor 302 executes the program, the fish data processing method based on machine learning provided in the above embodiment is implemented.

[0064] Furthermore, the electronic device further comprises:

[0065] The communication interface 303 is used for communication between the memory 301 and the processor 302 .

[0066] The memory 301 is used to store computer programs that can be run on the processor 302 .

[0067] The memory 301 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0068] If the memory 301, the processor 302 and the communication interface 303 are implemented independently, the communication interface 303, the memory 301 and the processor 302 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0069] Optionally, in a specific implementation, if the memory 301, the processor 302 and the communication interface 303 are integrated on a chip, the memory 301, the processor 302 and the communication interface 303 can communicate with each other through an internal interface.

[0070] The processor 302 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0071] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the above-mentioned fish data processing method based on machine learning is implemented.

[0072] An embodiment of the present application also provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the above-mentioned fish data processing method based on machine learning is implemented.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0074] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0075] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0076] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0077] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

Claims

1. A fish data processing method based on machine learning, characterized in that: The following steps are involved: Obtain fish data and environmental data of target waters; Extracting at least one fish morphological feature from the fish data and an environmental feature from the environmental data; Inputting the at least one fish morphological feature and the environmental feature into a machine learning model, the machine learning model outputting a matching result between the fish and the environment, wherein the machine learning model generates a fish morphological matrix based on the at least one fish morphological feature and generates an environmental feature matrix based on the environmental feature, and determines the matching result between the fish and the environment according to the similarity between the fish morphological matrix and the environmental feature matrix; The fish species matching the target water area are determined according to the matching result.

2. The fish data processing method based on machine learning according to claim 1, characterized in that: The machine learning model includes an input layer, a feature extraction layer, a matching layer and an output layer, wherein: The input layer extracts at least one fish morphological feature and environmental feature of the input; The feature extraction layer extracts the plant species corresponding to the fish and the environment from the morphological features of the fish and the environmental features; The matching layer determines a matching result according to the fish and the plant species corresponding to the environment; The output layer outputs the matching result between the fish and the environment.

3. The fish data processing method based on machine learning according to claim 2, characterized in that: The feature extraction layer includes multiple convolution layers, wherein each convolution layer performs a convolution operation on the at least one word vector to obtain the fish species corresponding to the fish morphological features and the environmental features and the plant species corresponding to the environment, and the multiple convolution layers extract the plant species suitable for the survival of each fish layer by layer; the matching layer determines the matching result by comparing the plant species for the survival of each fish with the plant species corresponding to the environment.

4. The fish data processing method based on machine learning according to claim 1, characterized in that: Before inputting the at least one fish morphological feature and the environmental feature into the machine learning model, the method further includes: Acquire a training data set and a verification data set, wherein the training data set and the verification data set both include fish data and environmental data; The machine learning model is trained using the training data set, and the machine learning model is verified using the verification data set until a preset stopping condition is met.

5. The fish data processing method based on machine learning according to claim 1, characterized in that: The step of obtaining the environmental data of the target water area includes: Extract water samples from target water areas; Analyze the genetic sequences of water samples to determine the types of plants currently present in the environment; Environmental data of the target water area is generated according to the plant species.

6. The fish data processing method based on machine learning according to claim 1, characterized in that: The obtaining of fish data comprises: Identify the external morphological features of different fish; The external morphological feature image is converted into a grayscale image, and corresponding fish data is generated according to the grayscale image.

7. The fish data processing method based on machine learning according to claim 1, characterized in that: Determining fish that match the target water area according to the matching result includes: If the fish in question is a good match for the environment, fish farming advice is provided; If the fish species do not match the environment, recommend fish species that are suitable for the specific environment, or choose the best breeding environment for the specific fish species.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fish data processing method based on machine learning as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, it is used to implement the fish data processing method based on machine learning as described in any one of claims 1-7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the fish data processing method based on machine learning as described in any one of claims 1-7 is implemented.

Images