Method and device for verifying the target of aquatic product breeding living body in agricultural insurance, equipment and medium

Abstract

The application belongs to the technical field of artificial intelligence, and is suitable for the financial field, and discloses a method, device, equipment and medium for verifying the target of aquatic farming living bodies, which comprises the following steps: acquiring a bionic underwater robot of the aquatic farming living bodies, and deploying the bionic underwater robot in the farming water area of the aquatic farming living bodies; synchronously collecting visual data and acoustic detection data of the aquatic farming living bodies through the bionic underwater robot, and fusing the collected visual data and acoustic detection data; inputting the fused visual data and acoustic detection data into a pre-trained deep learning model for feature extraction, and performing individual detection and species identification on the aquatic farming living bodies based on the extracted features; and generating a verification report containing the individual quantity and species information of the aquatic farming living bodies according to the results of the individual detection and species identification of the aquatic farming living bodies. The efficiency of verifying the target of the aquatic farming living bodies is effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence technology and is applicable to the financial field. In particular, it relates to a method, device, equipment and medium for verifying the target of agricultural insurance aquaculture live animals. Background Technology

[0002] With the deepening of digital transformation in agricultural insurance, utilizing intelligent technologies to achieve accurate verification and risk management for aquaculture insurance has become a key direction for the industry to improve operational efficiency and control underwriting and claims risks. Especially in aquaculture live animal insurance, represented by fish, how to conduct accurate, efficient, and traceable quantity verification and condition assessment of the insured objects directly affects the rationality of underwriting pricing and the fairness of claims settlement.

[0003] Currently, this type of insurance business still faces significant technical bottlenecks in practice. On the one hand, the pre-insurance inspection stage mainly relies on manual inspection and written records, such as visual estimation, sampling and weighing, or data reported by fish farmers to determine the number and species of fish. However, this method is difficult to achieve objective and dynamic confirmation of the insured, and there is a risk of information asymmetry. On the other hand, in the claims process after an accident, especially when fish die due to disease, natural disasters, or sudden changes in water quality, there is a lack of reliable technical means to accurately and non-invasively verify the number of deaths and the number of survivors on-site. In addition, existing technical solutions for fish population statistics also have obvious limitations. For example, the method of estimating by sampling is not representative enough and has a large error; while equipment that uses channels or pipes to drive fish to specific areas for centralized shooting and identification, although introducing automation, still requires physical driving or restraint of the fish, which is not only costly and inefficient, but may also cause stress, injury, or even death to the fish.

[0004] Therefore, how to improve the efficiency of verifying live aquaculture specimens under agricultural insurance is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and medium for verifying live aquatic animals covered by agricultural insurance, in order to solve the technical problem of how to improve the efficiency of verifying live aquatic animals covered by agricultural insurance.

[0006] In a first aspect, the present invention provides a method for verifying the ownership of live aquaculture specimens under agricultural insurance, comprising: A biomimetic underwater robot is used to acquire live aquatic organisms and to deploy the biomimetic underwater robot in the aquaculture area where the live aquatic organisms are raised. The biomimetic underwater robot simultaneously collects visual and acoustic detection data from live aquatic organisms and then fuses the collected visual and acoustic detection data. A pre-trained deep learning model is obtained, and the fused visual data and acoustic detection data are input into the pre-trained deep learning model for feature extraction. Based on the extracted features, individual detection and species identification are performed on the aquaculture live organisms. Based on the results of individual detection and species identification of live aquatic organisms, a verification report containing information on the number and species of the live aquatic organisms is generated.

[0007] Secondly, the present invention provides a device for verifying the ownership of live aquatic animals covered by agricultural insurance, comprising: The acquisition module is used to acquire a biomimetic underwater robot for live aquaculture organisms and deploy the biomimetic underwater robot in the aquaculture waters of the live aquaculture organisms. The fusion module is used to simultaneously collect visual and acoustic detection data of live aquatic animals using a biomimetic underwater robot, and then fuse the collected visual and acoustic detection data. The extraction module is used to acquire a pre-trained deep learning model, input the fused visual data and acoustic detection data into the pre-trained deep learning model for feature extraction, and perform individual detection and species identification on the aquaculture live organisms based on the extracted features. The generation module is used to generate a verification report containing information on the number and species of the live aquatic organisms based on the results of individual detection and species identification.

[0008] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned method for verifying the target of agricultural insurance aquaculture live animals.

[0009] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for verifying the target of agricultural insurance aquaculture.

[0010] The aforementioned method, apparatus, equipment, and medium for verifying live aquaculture products under agricultural insurance, in which a biomimetic underwater robot can be obtained from a client and deployed in the aquaculture area, allows for the simultaneous collection of visual and acoustic data from the live aquaculture products. This data is then fused with the visual and acoustic data. A pre-trained deep learning model is then created, and the fused visual and acoustic data are input into this model for feature extraction. Based on the extracted features, individual detection and species identification of the live aquaculture products are performed. A verification report containing the number and species information of the live aquaculture products is generated based on the results of the individual detection and species identification. In this invention, by deploying a biomimetic underwater robot in the aquaculture area, efficient monitoring of live aquaculture products can be achieved, reducing human intervention and improving monitoring accuracy. By inputting the fused visual and acoustic detection data into a pre-trained deep learning model for feature extraction, high-precision individual detection and species identification of live aquatic animals can be achieved, effectively improving the efficiency of verifying live aquatic animals for agricultural insurance. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram illustrating an application environment of the method for verifying live aquatic animals covered by agricultural insurance in one embodiment of the present invention.

[0013] Figure 2 This is a flowchart illustrating a method for verifying live aquatic animals covered by agricultural insurance in one embodiment of the present invention.

[0014] Figure 3 yes Figure 2 A schematic diagram of a specific implementation method for step S10.

[0015] Figure 4 yes Figure 2 A flowchart illustrating a specific implementation of step S20.

[0016] Figure 5 yes Figure 2 A flowchart illustrating a specific implementation of step S30.

[0017] Figure 6This is a schematic diagram of a device for verifying the target of agricultural insurance aquaculture live animals in one embodiment of the present invention.

[0018] Figure 7 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

[0019] Figure 8 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The method for verifying the value of live aquaculture animals covered by agricultural insurance provided in this embodiment of the invention can be applied to, for example... Figure 1 In the application environment, Figure 1 This is a schematic diagram illustrating an application environment of the method for verifying live aquatic organisms under agricultural insurance, according to an embodiment of the present invention. The client communicates with the server via a network. The server can obtain a biomimetic underwater robot for the live aquatic organisms from the client and deploy the robot in the aquaculture area. The robot simultaneously collects visual and acoustic data from the aquatic organisms and fuses the collected data. A pre-trained deep learning model is then obtained, and the fused visual and acoustic data are input into the model for feature extraction. Based on the extracted features, individual detection and species identification of the aquatic organisms are performed. Based on the results of the individual detection and species identification, a verification report containing the number and species information of the aquatic organisms is generated. In this invention, by deploying a biomimetic underwater robot in the aquaculture area, efficient monitoring of the aquatic organisms can be achieved, reducing human intervention and improving monitoring accuracy. By inputting the fused visual and acoustic detection data into a pre-trained deep learning model for feature extraction, high-precision individual detection and species identification of live aquatic animals can be achieved, effectively improving the efficiency of verifying live aquatic animals for agricultural insurance purposes. The invention will now be described in detail through specific embodiments.

[0022] Please see Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for verifying the value of live aquaculture products under agricultural insurance, as provided in an embodiment of the present invention. The method specifically includes the following steps: S10: Obtain a biomimetic underwater robot from live aquaculture animals and deploy the biomimetic underwater robot in the aquaculture area. Specifically, in this embodiment of the invention, the biomimetic underwater robot can move flexibly in the underwater environment, has strong adaptability, and can more comprehensively monitor the status of live aquaculture animals. By deploying the robot for monitoring, the reliance on manual operation is reduced, thereby reducing labor costs and safety risks, especially in complex or dangerous waters. The biomimetic underwater robot can work continuously in the aquaculture area, realizing real-time monitoring of live aquaculture animals and timely capturing information such as water quality changes and animal behavior. Specifically, such as... Figure 3 The above, Figure 3 yes Figure 2 A schematic diagram of a specific implementation of step S10, which specifically includes the following steps S11-S12: S11: Obtain environmental parameters and aquaculture information of the aquaculture area, and determine the target cruise mode of the biomimetic underwater robot based on these parameters and information. Specifically, in this embodiment of the invention, by acquiring environmental parameters such as water temperature, pH value, and dissolved oxygen, as well as aquaculture information such as species, density, and feeding method, the biomimetic underwater robot can adjust its target cruise mode according to specific circumstances. Formulating a cruise plan based on the actual environment and aquaculture conditions helps to effectively utilize the robot's working time in the water, avoid unnecessary energy consumption, and improve operational efficiency. By acquiring environmental parameters in real time, the robot can dynamically adjust its cruise mode and respond promptly to environmental changes. For example, changes in water temperature may affect the behavior of the aquatic organisms, and the robot can adjust its monitoring strategy immediately.

[0023] S12: Based on the target cruise mode, control the bionic underwater robot to dive to a preset depth in the aquaculture area with a preset movement posture. Specifically, in this embodiment of the invention, by utilizing the target cruise mode, the bionic underwater robot can autonomously select the most suitable movement posture and depth for diving, reducing human intervention and improving the level of automation. Based on the target cruise mode, the bionic underwater robot enters a specific depth with a preset movement posture for monitoring. This automated monitoring method not only improves the efficiency of data collection but also provides reliable data support for subsequent claims. If aquaculture losses are caused by environmental factors, insurance companies can quickly assess the loss based on the collected data, thereby accelerating the claims process.

[0024] In one embodiment of the present invention, before acquiring the biomimetic underwater robot from live aquatic organisms and deploying the biomimetic underwater robot in the aquaculture area, the method further includes: S01: acquiring appearance image information of the live aquatic organisms in the aquaculture area, and equipping the biomimetic underwater robot with a corresponding biomimetic appearance skin based on the appearance image information. Specifically, in this embodiment of the present invention, by acquiring appearance images of live aquatic organisms, an appearance skin similar to that of the aquaculture species can be designed for the biomimetic underwater robot. This biomimetic design can improve the robot's stealth and reduce interference with the live aquatic organisms, thereby making monitoring work more efficient. The biomimetic appearance skin can be customized according to the characteristics of aquaculture species in different waters, enabling the robot to adapt to the needs of different environments and aquaculture species.

[0025] S20: Visual and acoustic detection data of live aquaculture organisms are simultaneously collected using a biomimetic underwater robot, and the collected visual and acoustic data are fused. Specifically, in this embodiment of the invention, simultaneous collection of visual and acoustic data allows for analysis of the aquaculture environment from multiple dimensions, improving the richness and effectiveness of the data and contributing to a more comprehensive understanding of the underwater ecosystem. Fusing visual and acoustic detection data enhances the completeness and accuracy of the information. This fusion can effectively improve the accuracy of individual detection and species identification. In the underwater environment, the propagation characteristics of light and sound are affected by various factors. Fusing different types of data helps to offset these interferences and improve the reliability of monitoring results. Specifically, such as... Figure 4 The above, Figure 4 yes Figure 2 A schematic flowchart of a specific implementation of step S20 includes the following steps S21-S23: S21: The bionic underwater robot acquires continuous image frames of the aquaculture organisms using its image sensor, obtaining a visual data stream of the aquaculture organisms. Specifically, in this embodiment of the invention, by continuously acquiring image frames, the bionic underwater robot can achieve real-time monitoring of the aquaculture organisms. The visual data stream can be used to analyze the appearance characteristics of the aquaculture organisms, such as color and shape, and thus assess their health status. Through image analysis, the behavioral patterns of the aquaculture organisms can be observed, helping to determine whether they are in a normal growth state or whether they are being disturbed by external factors.

[0026] S22: Acoustic echo signals from live aquatic organisms in the aquaculture area are collected using the acoustic sensors of the biomimetic underwater robot to obtain an acoustic detection data stream of the live aquatic organisms. Specifically, in this embodiment of the invention, acoustic detection can provide effective information about the aquatic environment, including water flow velocity, bottom structure, and other biological activities. This helps to comprehensively understand the aquaculture environment. The acoustic sensors can provide effective data in low-light or turbid waters, supplementing the shortcomings of visual data streams, thereby improving the comprehensiveness and accuracy of monitoring.

[0027] S23: The visual data stream and acoustic detection data stream of the aquatic organisms are timestamped and then fused. Specifically, in this embodiment of the invention, by fusing the visual data stream and the acoustic detection data stream, two different types of information can be integrated, providing a more comprehensive and accurate analysis of the aquaculture status. Timestamp alignment ensures consistency between different data sources, making the analysis results more reliable and reducing errors caused by time delays.

[0028] S30: Obtain a pre-trained deep learning model, and input the fused visual data and acoustic detection data into the pre-trained deep learning model for feature extraction. Based on the extracted features, perform individual detection and species identification on the live aquatic organisms. Specifically, in this embodiment of the invention, the pre-trained deep learning model can accurately extract important features through visual data and acoustic detection data. Through the deep learning model, automatic detection and species identification of live aquatic organisms can be achieved, reducing human error and improving detection efficiency and consistency. Specifically, as shown... Figure 5 The above, Figure 5 yes Figure 2 A schematic flowchart of a specific implementation of step S30 includes the following steps S31-S34: S31: The fused visual and acoustic detection data of the live aquatic organisms are input into a pre-trained target detection model to extract the morphological features, initial position information, and bounding box information of the live aquatic organisms. Specifically, in this embodiment of the invention, the morphological features, initial position information, and bounding box information of the live aquatic organisms can be quickly extracted using a pre-trained target detection model. This automated processing greatly improves the efficiency of data analysis, and the extracted initial position information and bounding box information provide a reliable foundation for subsequent tracking and counting, ensuring the accuracy of monitoring.

[0029] S32: A multi-target tracking algorithm is used to correlate the bounding box information of live aquatic organisms across frames, generating their motion trajectories. Specifically, in this embodiment of the invention, the multi-target tracking algorithm can dynamically track multiple live aquatic organisms. The generation of motion trajectories helps analyze the behavioral patterns of live aquatic organisms, providing a basis for optimizing aquaculture strategies. For example, in agricultural insurance scenarios, insurance companies can obtain the motion trajectories and quantity statistics of live aquatic organisms, promptly identifying anomalies such as disease transmission or environmental changes, and helping farmers take measures to reduce risks.

[0030] S321: Obtain the bounding box information of the current frame of the live aquatic organism, and match the bounding box information of the current frame with the location information and appearance features of the tracking target established based on historical frames. Specifically, in this embodiment of the invention, matching the bounding box information of the current frame with the location information and appearance features of historical frames enhances the dynamic tracking capability of live aquatic organisms and helps to continuously understand their location and behavioral changes. Through an effective matching algorithm, tracking errors caused by motion, occlusion, or other factors can be reduced, improving the accuracy of monitoring.

[0031] S322: Update the successfully matched current frame bounding box to the corresponding tracking target, and generate the motion trajectory of the live aquatic organism based on the association result. Specifically, in this embodiment of the invention, updating the successfully matched bounding box information to the corresponding tracking target helps to generate a more accurate motion trajectory.

[0032] S33: Based on the generated movement trajectories of the aquaculture live animals, a deduplication count is performed on the aquaculture live animals in the aquaculture area to obtain the statistical result of the number of aquaculture live animals. Specifically, in this embodiment of the invention, the deduplication count function ensures a more accurate statistical count of the number of aquaculture live animals, avoiding errors caused by repeated calculations. For example, in agricultural insurance scenarios, the identified aquaculture live animal species and quantity statistics will become strong evidence for insurance claims, helping insurance companies quickly determine the cause of loss, shorten the claims processing time, and improve customer satisfaction.

[0033] S34: The extracted morphological features of the aquatic organisms are matched with a pre-set aquatic organism feature database to identify the species of aquatic organisms. Specifically, in this embodiment of the invention, based on morphological feature matching, the species of aquatic organisms can be accurately identified, as different species of aquatic organisms have different growth requirements. For example, in agricultural insurance scenarios, when a loss occurs, the identified species and quantity statistics of aquatic organisms will become strong evidence for insurance claims, helping insurance companies quickly determine the cause of the loss, shorten the claims processing time, and improve customer satisfaction.

[0034] S40: Based on the results of individual detection and species identification of live aquatic organisms, generate a verification report containing information on the number and species of the live aquatic organisms. Specifically, in this embodiment of the invention, the verification report provides detailed information about the live aquatic organisms, such as the number and species. Through automatically generated verification reports, insurance companies can obtain information on aquaculture more quickly, reduce the time required for manual review, and improve regulatory efficiency.

[0035] S41: Based on the statistical results of the number of aquatic live organisms and the identified species of aquatic live organisms, determine the total number of aquatic live organisms and the number of each category in the aquaculture area. Specifically, in this embodiment of the invention, by statistically analyzing the total number of individuals and the number of each category, a comprehensive understanding of the status of aquatic live organisms in the aquaculture area can be obtained. Determining the number of different species of aquatic live organisms helps in the rational allocation of resources, such as feed, oxygen, and water quality management. By statistically analyzing the species and number of aquatic live organisms, managers can more easily identify potential disease risks. For example, in an agricultural insurance scenario, suppose an aquaculture farmer finds a large number of fish dead after a storm. By statistically analyzing the total number of aquatic live organisms and the number of each category, the insurance company can accurately assess the scale of the loss, which provides an important basis for subsequent claims processing.

[0036] S42: Based on a preset report template, generate a verification report containing the total number of live aquatic organisms and the number of each category within the aquaculture area. Specifically, in this embodiment of the invention, using a preset report template to generate the verification report ensures a consistent report format. The generated verification report details the number and types of live aquatic organisms before the loss, enabling insurance companies to quickly assess the extent of the loss.

[0037] As can be seen, in the above-described scheme, specifically in this invention, by deploying a biomimetic underwater robot in the aquaculture area where live aquatic organisms are raised, efficient monitoring of these organisms can be achieved, reducing human intervention and improving monitoring accuracy. By inputting the fused visual and acoustic detection data into a pre-trained deep learning model for feature extraction, high-precision individual detection and species identification of live aquatic organisms can be realized, effectively improving the efficiency of verifying agricultural insurance claims for live aquatic organisms.

[0038] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0039] In one embodiment, a device for verifying the ownership of live aquatic animals covered by agricultural insurance is provided. This device corresponds one-to-one with the method for verifying the ownership of live aquatic animals covered by agricultural insurance described in the above embodiments. For example... Figure 6As shown, Figure 6 This is a schematic diagram of a device for verifying the value of live aquatic animals under agricultural insurance according to an embodiment of the present invention. The device includes an acquisition module 61, a fusion module 62, an extraction module 63, and a generation module 64. Detailed descriptions of each functional module are as follows: Acquisition module 61 is used to acquire a biomimetic underwater robot for live aquaculture animals and deploy the biomimetic underwater robot in the aquaculture waters of the live aquaculture animals; The fusion module 62 is used to simultaneously collect visual data and acoustic detection data of live aquatic animals through a biomimetic underwater robot, and to fuse the collected visual data with the acoustic detection data. The extraction module 63 is used to acquire a pre-trained deep learning model, and input the fused visual data and acoustic detection data into the pre-trained deep learning model for feature extraction, and perform individual detection and species identification on the aquaculture live animals based on the extracted features. The generation module 64 is used to generate a verification report containing information on the number and species of the aquatic live organisms based on the results of individual detection and species identification of the aquatic live organisms.

[0040] In one embodiment, the acquisition module 61 is specifically used for: Collect images of the appearance of live aquatic animals in the aquaculture area, and equip the biomimetic underwater robot with a corresponding biomimetic skin based on the appearance images.

[0041] In one embodiment, the acquisition module 61 is further configured to: The environmental parameters and aquaculture information of the aquaculture area are obtained, and the target cruise mode of the biomimetic underwater robot is determined based on the environmental parameters and aquaculture information of the aquaculture area. Based on the target cruise mode, the bionic underwater robot is controlled to dive into the aquaculture area at a preset depth with a preset motion posture.

[0042] In one embodiment, the fusion module 62 is specifically used for: The image sensor of the biomimetic underwater robot acquires continuous image frames of live aquatic organisms to obtain a visual data stream of the live aquatic organisms. The acoustic echo signals of the aquatic animals in the aquaculture area are collected by the acoustic sensors of the biomimetic underwater robot to obtain the acoustic detection data stream of the aquatic animals. The visual data stream and acoustic detection data stream of the aquatic organisms are time-stamp aligned, and the time-stamp aligned visual data stream and acoustic detection data stream are then fused.

[0043] In one embodiment, the extraction module 63 is specifically used for: The fused visual data and acoustic detection data of the aquatic live organisms are input into a pre-trained target detection model to extract the morphological features, initial position information and bounding box information of the aquatic live organisms; The bounding box information of live aquatic animals is correlated across frames using a multi-target tracking algorithm to generate the motion trajectory of the live aquatic animals. Based on the movement trajectory of the generated aquatic life, the number of aquatic life in the aquaculture area is counted to remove duplicates, and the statistical results of the number of aquatic life are obtained. The extracted morphological features of live aquatic organisms are matched with a pre-set feature database of live aquatic organisms to identify the species of live aquatic organisms.

[0044] In one embodiment, the extraction module 63 is further configured to: Obtain the bounding box information of the current frame of the live aquatic organism, and match the bounding box information of the current frame with the location information and appearance features of the tracking target established based on historical frames; The bounding box of the current frame that is successfully matched is updated to the corresponding tracking target, and the motion trajectory of the live aquatic organism is generated based on the association result.

[0045] In one embodiment, the generation module 64 is specifically used for: Based on the statistical results of the number of live aquatic organisms and the identified types of live aquatic organisms, the total number of live aquatic organisms in the aquaculture area and the number of each category are determined. Based on the preset report template, a verification report is generated that includes the total number of live aquatic organisms and the number of each category in the aquaculture area.

[0046] This invention provides a device for verifying live aquatic animals for agricultural insurance purposes. By deploying a biomimetic underwater robot in the aquaculture area, it enables efficient monitoring of live aquatic animals, reducing human intervention and improving monitoring accuracy. By inputting fused visual and acoustic detection data into a pre-trained deep learning model for feature extraction, it achieves high-precision individual detection and species identification of live aquatic animals, effectively improving the efficiency of verifying live aquatic animals for agricultural insurance purposes.

[0047] Specific limitations regarding the verification device for live aquaculture products covered by agricultural insurance can be found in the above-mentioned limitations on the verification method for live aquaculture products covered by agricultural insurance, and will not be repeated here. Each module in the aforementioned verification device for live aquaculture products covered by agricultural insurance can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0048] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, Figure 7 This is a schematic diagram of a computer device according to an embodiment of the present invention. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a server-side method for verifying the target of agricultural insurance aquaculture live animals.

[0049] In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as follows: Figure 8 As shown, Figure 8 This is another schematic diagram of a computer device according to an embodiment of the present invention. The computer device includes a processor, memory, network interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the client-side functions or steps of a method for verifying the target of agricultural insurance aquaculture live animals.

[0050] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: A biomimetic underwater robot is used to acquire live aquatic organisms and to deploy the biomimetic underwater robot in the aquaculture area where the live aquatic organisms are raised. The biomimetic underwater robot simultaneously collects visual and acoustic detection data from live aquatic organisms and then fuses the collected visual and acoustic detection data. A pre-trained deep learning model is obtained, and the fused visual data and acoustic detection data are input into the pre-trained deep learning model for feature extraction. Based on the extracted features, individual detection and species identification are performed on the aquaculture live organisms. Based on the results of individual detection and species identification of live aquatic organisms, a verification report containing information on the number and species of the live aquatic organisms is generated.

[0051] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: A biomimetic underwater robot is used to acquire live aquatic organisms and to deploy the biomimetic underwater robot in the aquaculture area where the live aquatic organisms are raised. The biomimetic underwater robot simultaneously collects visual and acoustic detection data from live aquatic organisms and then fuses the collected visual and acoustic detection data. A pre-trained deep learning model is obtained, and the fused visual data and acoustic detection data are input into the pre-trained deep learning model for feature extraction. Based on the extracted features, individual detection and species identification are performed on the aquaculture live organisms. Based on the results of individual detection and species identification of live aquatic organisms, a verification report containing information on the number and species of the live aquatic organisms is generated.

[0052] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0053] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0055] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for verifying the ownership of live aquaculture products under agricultural insurance, characterized in that, include: A biomimetic underwater robot is used to acquire live aquatic organisms and to deploy the biomimetic underwater robot in the aquaculture area where the live aquatic organisms are raised. The biomimetic underwater robot simultaneously collects visual and acoustic detection data from live aquatic organisms and then fuses the collected visual and acoustic detection data. A pre-trained deep learning model is obtained, and the fused visual data and acoustic detection data are input into the pre-trained deep learning model for feature extraction. Based on the extracted features, individual detection and species identification are performed on the aquaculture live organisms. Based on the results of individual detection and species identification of live aquatic organisms, a verification report containing information on the number and species of the live aquatic organisms is generated.

2. The method for verifying live aquaculture specimens under agricultural insurance according to claim 1, characterized in that, Before acquiring the biomimetic underwater robot for aquaculture and deploying the biomimetic underwater robot in the aquaculture area of ​​the aquaculture organisms, the method further includes: Collect images of the appearance of live aquatic animals in the aquaculture area, and equip the biomimetic underwater robot with a corresponding biomimetic skin based on the appearance images.

3. The method for verifying the value of live aquaculture animals under agricultural insurance according to claim 2, characterized in that, The biomimetic underwater robot for acquiring live aquatic organisms and deploying the biomimetic underwater robot in the aquaculture area includes: The environmental parameters and aquaculture information of the aquaculture area are obtained, and the target cruise mode of the biomimetic underwater robot is determined based on the environmental parameters and aquaculture information of the aquaculture area. Based on the target cruise mode, the bionic underwater robot is controlled to dive into the aquaculture area at a preset depth with a preset motion posture.

4. The method for verifying live aquaculture specimens under agricultural insurance according to claim 1, characterized in that, The process involves simultaneously acquiring visual and acoustic data of live aquatic organisms using image and acoustic sensors from a biomimetic underwater robot, and then fusing the acquired visual and acoustic data. The image sensor of the biomimetic underwater robot acquires continuous image frames of live aquatic organisms to obtain a visual data stream of the live aquatic organisms. The acoustic echo signals of the aquatic animals in the aquaculture area are collected by the acoustic sensors of the biomimetic underwater robot to obtain the acoustic detection data stream of the aquatic animals. The visual data stream and acoustic detection data stream of the aquatic organisms are time-stamp aligned, and the time-stamp aligned visual data stream and acoustic detection data stream are then fused.

5. The method for verifying the value of live aquaculture animals under agricultural insurance according to claim 1, characterized in that, The process of acquiring a pre-trained deep learning model, inputting the fused visual and acoustic detection data of the aquatic organisms into the pre-trained deep learning model for feature extraction, and performing individual detection and species identification of the aquatic organisms based on the extracted features includes: The fused visual data and acoustic detection data of the aquatic live organisms are input into a pre-trained target detection model to extract the morphological features, initial position information and bounding box information of the aquatic live organisms; The bounding box information of live aquatic animals is correlated across frames using a multi-target tracking algorithm to generate the motion trajectory of the live aquatic animals. Based on the movement trajectory of the generated aquatic life, the number of aquatic life in the aquaculture area is counted to remove duplicates, and the statistical results of the number of aquatic life are obtained. The extracted morphological features of live aquatic organisms are matched with a pre-set feature database of live aquatic organisms to identify the species of live aquatic organisms.

6. The method for verifying the value of live aquaculture animals under agricultural insurance according to claim 5, characterized in that, The step of generating the motion trajectory of aquatic animals by cross-frame association of bounding box information using a multi-target tracking algorithm includes: Obtain the bounding box information of the current frame of the live aquatic organism, and match the bounding box information of the current frame with the location information and appearance features of the tracking target established based on historical frames; The bounding box of the current frame that is successfully matched is updated to the corresponding tracking target, and the motion trajectory of the live aquatic organism is generated based on the association result.

7. The method for verifying the value of live aquaculture animals under agricultural insurance according to claim 6, characterized in that, The process of generating a verification report containing information on the number and species of live aquatic organisms based on individual detection and species identification results includes: Based on the statistical results of the number of live aquatic organisms and the identified types of live aquatic organisms, the total number of live aquatic organisms in the aquaculture area and the number of each category are determined. Based on the preset report template, a verification report is generated that includes the total number of live aquatic organisms and the number of each category in the aquaculture area.

8. A device for verifying the ownership of live aquaculture products under agricultural insurance, characterized in that, Includes the following steps: The acquisition module is used to acquire a biomimetic underwater robot for live aquaculture organisms and deploy the biomimetic underwater robot in the aquaculture waters of the live aquaculture organisms. The fusion module is used to simultaneously collect visual and acoustic detection data of live aquatic animals using a biomimetic underwater robot, and then fuse the collected visual and acoustic detection data. The extraction module is used to acquire a pre-trained deep learning model, input the fused visual data and acoustic detection data into the pre-trained deep learning model for feature extraction, and perform individual detection and species identification on the aquaculture live organisms based on the extracted features. The generation module is used to generate a verification report containing information on the number and species of the live aquatic organisms based on the results of individual detection and species identification.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for verifying the target of agricultural insurance aquaculture live animals as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for verifying the target of agricultural insurance aquaculture live animals as described in any one of claims 1 to 7.

Images