Electronic fishing management system and method based on artificial intelligence fish school number monitoring

Abstract

The invention discloses an electronic fishing management system and method based on artificial intelligence fish school quantity monitoring, the system comprises an Internet of Things monitoring module, a quantity storage module, a quantity expectation configuration module, an AI analysis module, a user interaction module and a fishing activity storage module, and the method comprises the following steps: S1, counting the quantity of fish schools in a water area through the AI analysis module; s2, carrying out a fishing experiment to obtain the influence condition of the number of fish schools; s3, constructing a fishing influence model through an AI analysis module; s4, configuring the expected number of fish schools; s5, the user applies for fishing through the interaction module, and fishing position information and time length information are provided; s6, whether fishing can be carried out or not is judged through the fishing influence model and a quantity storage module, and if yes, the fishing activity is stored in a fishing activity storage module. According to the method, the accuracy of fish school quantity statistics and analysis prediction under different water area conditions is improved, and digital management of fishing for local water conservancy departments is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of population quantity prediction, and in particular to an electronic fishing management system and method based on artificial intelligence fish quantity monitoring. Background Art

[0002] At present, some local waters have many risks of illegal fishing, insufficient law enforcement and supervision capabilities, and a lack of scientific statistical methods for the recovery of aquatic species populations. Fishing management is the best means of aquatic biological supervision at this stage. Its advantage is that it can intervene in the aquatic ecosystem in a relatively gentle way, while promoting public participation and the improvement of environmental awareness.

[0003] In fishing management, the technology of evaluating fish and population changes is very important. Among the existing technologies, the fish detection method based on machine vision can effectively classify and locate fish targets, detect the biodiversity of fish, and provide important data support for the detection and maintenance of fish ecosystems. It can not only help managers to scientifically formulate fishing regulations to maintain ecological balance and sustainable use of fish resources, but also promptly discover and respond to the sharp decline in fish numbers caused by environmental changes, and ensure the continuity of convenient fishing for fish schools.

[0004] Existing underwater target detection technology, especially fish monitoring, mainly relies on two major technical system methods. One is the acoustic camera detection method (such as sonar system), and the other is the detection method based on optical camera. The convolutional neural network is used to train and analyze the collected images to obtain statistical results of the number of fish schools. It can not only identify fish, but also try to estimate the population size. However, the optical system of this method is easily affected by water turbidity and light conditions, which affects the monitoring effect.

[0005] When it comes to predicting fish populations, the main approach on the market is often to conduct trend estimation analysis on the quantity after accumulating long-term observation data and forming periodic statistical results. Although this can reveal the trend of quantity changes, it ignores the immediate impact of dynamic factors such as short-term human activities on the distribution and quantity of fish, and the accuracy of the prediction needs to be improved.

[0006] To this end, this application specifically proposes an electronic fishing management system and method based on artificial intelligence fish population monitoring, constructs an optimal fish population statistics method based on artificial intelligence and Internet of Things device statistics, improves the accuracy of statistics under different water conditions, and at the same time conducts online management of fishing activities in the waters through population population prediction to solve the above-mentioned technical problems. Summary of the invention

[0007] The main purpose of the present invention is to provide an electronic fishing management system and method based on artificial intelligence fish population monitoring, a method for counting the number of fish in water areas based on CNN optical image + sonar image adaptive analysis and statistics, and to predict the number of fish in water areas based on the system, thereby providing scientific guidance for water fishing management to solve the technical problems raised in the background technology.

[0008] The present invention adopts the following technical solutions to solve the above technical problems:

[0009] The electronic fishing management system based on artificial intelligence fish population monitoring includes an Internet of Things monitoring module, a quantity storage module, a quantity expectation configuration module, an AI analysis module, a user interaction module, and a fishing activity storage module, among which:

[0010] The Internet of Things monitoring module, which consists of underwater sonar equipment, underwater optical cameras, and wireless data transmission devices, is used to collect data related to the number of underwater fish schools and send it to the data storage module for processing through existing data transmission devices;

[0011] A quantity storage module is used to store data in a local database and a cloud server, and to read, write, and manage the data, wherein the data includes the number of fish schools, fishing activities, and quantity configuration;

[0012] The expected number configuration module is used to set and manage the parameters of the number of fish in the water area, fishing activity rules and expected fish numbers;

[0013] AI analysis module, which processes, analyzes and predicts data based on artificial intelligence technology, is used to obtain fish population information from system storage data and perform specified prediction and analysis tasks;

[0014] The user interaction module includes an operation interface for interaction, operation and feedback with the system, which is used to provide designated task functions for corresponding users through the management end and the user end. The designated task functions include fish population configuration, AI intelligent analysis, fishing activity application, fishing activity management, and historical data viewing;

[0015] The fishing activity storage module is mainly used to store data related to fishing activities, including fishing locations, fishing times, fish caught and quantity. It is used to record the impact of fishing activities on the number of fish schools and provide data support for the supervision of fishing activities.

[0016] Preferably, the predictive analysis task in the AI ​​analysis module includes evaluating the results of shooting by the optical camera and the acoustic camera, and increasing the quantity weight of the optical camera when the specified optical conditions are met, so as to achieve accurate estimation of the number of fish.

[0017] The electronic fishing management system and method based on artificial intelligence fish population monitoring are used to build the above-mentioned electronic fishing management system based on artificial intelligence fish population monitoring and execute the corresponding operation process, including the following specific implementation steps:

[0018] S1. Build an IoT monitoring module underwater, count the number of fish in the water area through the AI ​​analysis module, and store the fish data in the quantity storage module, where the fish data includes the number, longitude and latitude of the water area, and depth of the water area;

[0019] S2. Conduct fishing experiments and store the impact on the number of fish in a quantity storage module, wherein the impact on the number of fish includes the number of fish at each monitoring point and the longitude and latitude of the fishing point;

[0020] S3. construct a fishing impact model through the AI ​​analysis module, and store the model in the AI ​​analysis module;

[0021] S4. Configure the expected number of fish and store it in the expected number configuration module;

[0022] S5. Apply for fishing through the user interaction module and provide fishing location information and duration information;

[0023] S6. Determine whether fishing is possible through the fishing impact model and the quantity storage module. If so, store the fishing activity in the fishing activity storage module.

[0024] Preferably, the specific operation steps of counting the number of fish schools in the water area in step S1 include:

[0025] The weighted average method is used to count the number of fish, and the number of fish in the water area is preset as Q0, and its expression is:

[0026]

[0027] The water area needs to be divided into multiple unit water areas manually in advance. One optical camera and one acoustic camera are placed in each unit water area. i represents the unit water area number, W represents the unit water area number. i Indicates the number of optical devices in the current water area, O i Indicates the total number of fish activities per day per unit water area of ​​the current optical device, V i Indicates the total number of daily fish activities per unit area of ​​the current acoustic device.

[0028] Preferably, the number of optical devices in the current water area is scored as W i It is calculated by the color, contrast and clarity of the picture. i The specific method for obtaining includes the following steps:

[0029] L1. Collect 500 images from cameras in different waters at different times;

[0030] L2. 20 raters are preset to manually rate the images. The scores range from 0.1 to 1 and are divided into 10 levels with a step size of 0.1. The higher the score, the more consistent the image is with human visual perception and the better the visual quality. For each image, the highest and lowest scores are removed, and the average score given by the remaining 18 observers is recorded as the valid score.

[0031] L3. Use VGG16 Net to extract the 4096-dimensional features of the image and the corresponding quality scores that conform to human visual perception and send them to the random forest model for training;

[0032] L4. After the model training is completed, all images are sent to the VGG16 Net deep neural network to extract features, and the final score is output through the random forest to obtain the score evaluation W i .

[0033] Preferably, the method for obtaining the impact of the number of fish in step S2 includes:

[0034] The location where the optical and acoustic equipment is placed is set as the monitoring point. The spatial distance l of fishing, the fishing time t, and the number of fish before fishing Q are calculated through the fishing point and the monitoring points of all unit waters. before And the number of fish after fishing Q after And through multiple experiments, multiple sets of sampling data were obtained to obtain the impact of fishing activities on the number of fish schools at different spatial distances.

[0035] Preferably, the fishing impact model in step S3 includes a fish population prediction model, and the method for constructing the fish population prediction model includes:

[0036] S31. Linear regression is used to construct a fishing activity prediction model, where Q before As training parameters X, Q after As the prediction parameter Y;

[0037] S32. Since the data set is small, cross-validation is adopted to obtain the fish population prediction model:

[0038] Y=X-wt / l

[0039] Among them, w represents the influencing factor of the number of fishing activities calculated by linear regression, t represents the fishing time, and l represents the spatial distance between the fishing location and the unit water area monitoring point.

[0040] Preferably, the expected quantity in step S4 is set to Q expectIn the step S5, the fishing location information is set as longitude and latitude information, and the determination method in the step S6 includes:

[0041] S61. By calculating the longitude and latitude, we get the distance set L of all points = {l1, ..., l n};

[0042] S62. Substituting the distance set data of the points into the fish population prediction model, the expected result set of fish population Q = {q1, ..., q n};

[0043] S63. Compare the number of fish in set Q with Q expect , if both are greater than Q expect , then the fishing activity will be automatically approved; if it is less than , then the fishing activity will be automatically rejected.

[0044] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0045] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0046] It can be seen from the above technical solutions that the present invention provides an electronic fishing management system and method based on artificial intelligence fish population monitoring. Compared with the prior art, the present invention has the following advantages:

[0047] 1. The present invention integrates underwater monitoring technology and data analysis algorithms to provide a more accurate quantitative statistical method and a more accurate prediction capability of the number of fish in waters, thereby improving the accuracy of statistics and analytical predictions under different water conditions, facilitating the digital management of fishing for local water conservancy departments, and promoting the sustainable management and protection of fishery resources. It supports the ban on fishing in waters through scientific means and reduces the cost of manual review.

[0048] 2. The present invention deploys Internet of Things devices in water areas and integrates artificial intelligence analysis technology to achieve intelligent statistics, intelligent monitoring and high-precision prediction of the number of fish schools. In addition, the accuracy of data collection and statistics is improved by combining image and acoustic detection methods.

[0049] 3. The present invention uses image quality parameters such as brightness for evaluation and scoring, thereby changing the scores of image and acoustic detection results, performing weighted statistics according to the scoring results, and dynamically adjusting the weights of image and acoustic data. It can obtain more accurate fish population statistics, greatly improve the accuracy of subsequent fish population prediction results, and facilitate the rational management of fishing in different waters.

[0050] 4. The present invention constructs a fishing impact model through fishing activities, systematically evaluates the impact of fishing activities on fish schools in surrounding waters, facilitates the reasonable digital management of fishing in fish schools in different waters, and helps maintain the ecological balance of the waters.

[0051] 5. The present invention can set the expected number of fish schools through seasonal system configuration, achieve scientific control of the total number of fish schools in the water area, divide the seasonal time for fishing bans, and achieve more accurate population control.

[0052] 6. The present invention sets underwater cameras and sonar IoT devices in the water area and combines them with intelligent image analysis technology to perform fine sampling and counting of fish schools, build accurate fish population models and water area ecological models, and effectively improve the accuracy of fish population statistics.

[0053] 7. The present invention establishes a fishing impact model by analyzing the spatial distribution of fishing activities. It not only predicts the impact of fishing on fish activities in various regions, but also reduces the time cost of manual review of fishing applications, realizes the digital application and approval process of fishing activities, and greatly improves management efficiency.

[0054] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. Of course, it is not necessary to achieve all of the advantages described above simultaneously for any product implementing the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0056] Figure 1 A schematic diagram of the overall modules for building a system and performing corresponding operations for the method of the present invention;

[0057] Figure 2 It is a schematic diagram of the overall process of the method of the present invention. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0059] In the embodiment, see Figure 1 to Figure 2 .

[0060] like Figure 1 As shown, an electronic fishing management system based on artificial intelligence fish population monitoring proposed in an embodiment of the present invention includes an Internet of Things monitoring module, a quantity storage module, a quantity expectation configuration module, an AI analysis module, a user interaction module, and a fishing activity storage module. Through the preferred fish population monitoring and statistical means, indicators such as the fish population are monitored, and scientific guidance is provided on the fishing location, frequency, etc., so as to carry out fine management of fishing and maintain the benign development of the water ecology, wherein:

[0061] (1) Internet of Things monitoring module, mainly composed of underwater sonar equipment, underwater optical camera, wireless data transmission device, etc., used to collect data related to the number of underwater fish schools and send it to the data storage module for processing through the data transmission device;

[0062] At this time, the module can perform fine sampling and counting of fish schools by setting up underwater cameras and sonar IoT devices in the waters, and combining intelligent image analysis technology to build an accurate fish population model and water ecological model, effectively improving the accuracy of fish population statistics.

[0063] (2) Quantity storage module, which mainly involves data storage and management. Data is stored in the local database and cloud server, and can read, write and manage data such as fish population, fishing activities, and quantity configuration;

[0064] (3) Quantity expectation configuration module, which is used to set and manage the parameters of the number of fish schools in the water area, fishing activity rules and the expected number of fish schools. Users can use this module to configure and define the expected number of fish schools and adjust and optimize the system;

[0065] At this time, the module can set the expected number of fish schools through seasonal system configuration, so as to achieve scientific control of the total number of fish schools in the water area, and divide the seasonal time for fishing bans, such as increasing the expected number in the breeding season, so as to achieve more accurate population control;

[0066] (4) AI analysis module, which processes, analyzes and predicts data based on artificial intelligence technologies such as CNN, is used to obtain information on the number of fish schools from the system storage data and perform specified tasks such as prediction analysis. The prediction analysis tasks include evaluating the results of optical cameras and acoustic cameras, and increasing the weight of the optical camera when the specified optical conditions are met (when the optical conditions are good), thereby achieving accurate estimation of the number of fish schools;

[0067] At this time, the module can fish for the impact on fish activity in each area;

[0068] (5) User interaction module, including an operation interface for interacting with, operating and providing feedback on the system, which is used to provide designated task functions for corresponding users through the management terminal and the user terminal. The designated task functions include fish population configuration, AI intelligent analysis, fishing activity application, fishing activity management, historical data viewing, etc.;

[0069] (6) Fishing activity storage module, mainly used to store data related to fishing activities, including fishing locations, fishing times, fish caught and the number of fish caught, etc. These data can be used to record the impact of fishing activities on the number of fish, thereby providing data support for the supervision of fishing activities;

[0070] At this time, through the fishing management system, anglers can apply for fishing and carry out fishing activities after approval, reducing the time cost required for offline registration and realizing online fishing activity management and control.

[0071] In summary, the system integrates underwater monitoring technology and data analysis algorithms to provide a more accurate quantitative statistics method and a more accurate prediction capability of the number of fish in waters, which improves the accuracy of statistics and analytical predictions under different water conditions, facilitates the digital management of fishing for local water conservancy departments, promotes the sustainable management and protection of fishery resources, supports fishing bans in waters through scientific means, and reduces manual review costs.

[0072] On the other hand, the present invention also discloses an electronic fishing management system and method based on artificial intelligence fish population monitoring, which is used to build the above-mentioned electronic fishing management system based on artificial intelligence fish population monitoring and execute the corresponding operation process, and constructs an optimal fish population statistics method based on artificial intelligence and Internet of Things equipment statistics, which can perform adaptive analysis and statistics of fish population based on CNN optical image + sonar image, improve the accuracy of statistics under different water conditions, and at the same time, digitally manage fishing activities in waters through population population prediction, support fishing bans in waters through scientific means, and reduce manual review costs.

[0073] like Figure 2 As shown, the specific implementation steps include the following:

[0074] S1. Build an IoT monitoring module underwater, count the number of fish in the water area through IoT devices and AI analysis modules such as CNN, store the fish data in the quantity storage module, realize intelligent statistics of the number of fish in the water area, and predict the number of fish. The fish data includes the number, longitude and latitude of the water area, and depth of the water area;

[0075] In a specific embodiment, the specific operation steps of counting the number of fish schools in a water area include:

[0076] Since optical cameras are greatly affected by lighting conditions, a weighted average method is used to count the number of fish. The number of fish in this water area is preset as Q0, and its expression is:

[0077]

[0078] The water area needs to be divided into multiple unit water areas manually in advance. One optical camera and one acoustic camera are placed in each unit water area. i represents the unit water area number, W represents the unit water area number. i Indicates the number of optical devices in the current water area, O i Indicates the total number of fish activities per day per unit water area of ​​the current optical device, V i Indicates the total number of daily fish activities per unit water area for the current acoustic equipment;

[0079] At this time, the deployment of IoT devices in the waters and the integration of artificial intelligence analysis technology have achieved intelligent statistics, intelligent monitoring and high-precision prediction of the number of fish schools. In addition, the combination of image and acoustic detection methods has improved the accuracy of data collection and statistics.

[0080] Furthermore, the number of optical devices in the current water area is evaluated by scoring W i It is calculated by the color, contrast, and clarity of the picture. Here we refer to the underwater image quality evaluation method based on deep regression forest. i The specific method for obtaining includes the following steps:

[0081] L1. First, about 500 images were collected in the area. To ensure robustness, these images were taken by cameras in different waters at different times.

[0082] L2. 20 raters are preset to manually rate the images. The scores range from 0.1 to 1 and are divided into 10 levels with a step size of 0.1. The higher the score, the more consistent the image is with human visual perception and the better the visual quality. For each image, the highest and lowest scores are removed, and the average score given by the remaining 18 observers is recorded as the valid score.

[0083] L3. Use VGG16 Net to extract the 4096-dimensional features of the image and the corresponding quality scores that conform to human visual perception and send them to the random forest model for training;

[0084] L4. After the model training is completed, all images are sent to the VGG16 Net deep neural network to extract features, and the final score is output through the random forest to obtain the score evaluation W i ;

[0085] Therefore, by using image quality parameters such as brightness for evaluation and scoring, the scores of image and acoustic detection results are changed, weighted statistics are performed according to the scoring results, and the weights of image and acoustic data are dynamically adjusted. More accurate fish population statistics can be obtained, which is convenient for the subsequent construction of fish population models and water area models, that is, obtaining the total number of daily fish activities in different areas of the water area and the total number of fish in the water area, which greatly improves the accuracy of subsequent fish population prediction results and facilitates the reasonable management of fishing in different water areas.

[0086] S2. Conduct fishing experiments and store the impact on the number of fish in the quantity storage module, where the impact on the number of fish includes the number of fish at each monitoring point and the longitude and latitude of the fishing point;

[0087] In a specific embodiment, the method for obtaining the impact of the number of fish schools includes:

[0088] The location where the optical and acoustic equipment is placed is set as the monitoring point. The spatial distance l of fishing, the fishing time t, and the number of fish before fishing Q are calculated through the fishing point and the monitoring points of all unit waters. before And the number of fish after fishing Q aftet And through multiple experiments, multiple sets of sampling data were obtained to obtain the impact of fishing activities on the number of fish at different spatial distances;

[0089] S3. construct a fishing impact model through the AI ​​analysis module, and store the model in the AI ​​analysis module;

[0090] In a specific embodiment, the fishing impact model includes a fish population prediction model, and the method for constructing the fish population prediction model includes:

[0091] S31. Linear regression is used to construct a fishing activity prediction model, where Q before As training parameters X, Q after As the prediction parameter Y;

[0092] S32. Since the data set is small, cross-validation is adopted to obtain the fish population prediction model:

[0093] Y=X-wt / l

[0094] Among them, w represents the influencing factor of the number of fishing activities calculated by linear regression, t represents the duration of fishing, and l represents the spatial distance between the fishing location and the monitoring point of the unit water area;

[0095] At this time, by fishing in different areas, since the fishing spots are relatively fixed, we can derive a spatial impact model of fishing, that is, the impact of anglers on the total number of daily fish activities in different water areas; by calculating the average number of fish caught per unit time in different areas, we can obtain the impact factor of fishing, which can achieve a more accurate prediction result of the number of fish;

[0096] It should also be noted that the distance ratio in the actual scene may not be the same as here. This is only for illustration and the actual situation shall prevail.

[0097] At this time, by analyzing the spatial distribution of fishing activities, a fishing impact model was constructed to systematically evaluate the impact of fishing activities on fish stocks in surrounding waters. This not only predicted the impact of fishing on fish activities in various regions, but also realized the digital application and approval process for fishing activities, greatly improving management efficiency, facilitating the reasonable digital management of fishing in different waters, and helping to maintain the ecological balance of the waters.

[0098] S4. Configure the expected number of fish and store it in the expected number configuration module, where the expected number is set to Q expect ;

[0099] S5. The user applies for fishing through the interactive module and provides fishing location information and duration information, where the fishing location information is set to latitude and longitude information;

[0100] S6. Determine whether fishing can be carried out through the fishing impact model and the quantity storage module. If so, store the fishing activity in the fishing activity storage module;

[0101] In a specific embodiment, the determination method includes:

[0102] S61. By calculating the longitude and latitude, we get the distance set L of all points = {l1, ..., l n};

[0103] S62. Substituting the distance set data of the points into the fish population prediction model, the expected result set of fish population Q = {q1, ..., q n};

[0104] S63. Compare the number of fish in set Q with Q expect , if both are greater than Q expect , then the fishing activity will be automatically approved; if it is less than, then the fishing activity will be automatically rejected;

[0105] At this time, the allowed fishing areas and number of people are calculated based on the natural growth of fish in the water area and the minimum number requirements of fish, replacing the traditional manual review method, thereby reducing the time cost of manual review of fishing activities.

[0106] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0107] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0108] In another embodiment provided in the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the electronic fishing management methods based on artificial intelligence fish population monitoring in the above-mentioned embodiments.

[0109] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

[0110] The embodiment of the present application also provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus.

[0111] Memory, used to store computer programs;

[0112] The processor is used to implement the above-mentioned electronic fishing management method based on artificial intelligence fish population monitoring when executing the program stored in the memory.

[0113] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0114] The communication interface is used for communication between the above electronic device and other devices.

[0115] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0116] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0117] It should also be noted that electronic devices also include terminal devices, which can also be called terminals, user equipment (UE), mobile stations (MS), mobile terminals (MT), etc. Terminal devices can be mobile phones, smart TVs, wearable devices, tablet computers (Pad), computers with wireless transceiver functions, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the terminal devices.

[0118] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0120] In addition, it should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0121] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or schemes that A and B meet at the same time. In addition, in the embodiments of the present invention, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

Claims

1. An electronic fishing management system based on artificial intelligence fish population monitoring, characterized in that: It includes IoT monitoring module, quantity storage module, quantity expectation configuration module, AI analysis module, user interaction module and fishing activity storage module, among which: The Internet of Things monitoring module, which consists of underwater sonar equipment, underwater optical cameras, and wireless data transmission devices, is used to collect data related to the number of underwater fish schools and send it to the data storage module for processing through existing data transmission devices; A quantity storage module is used to store data in a local database and a cloud server, and to read, write, and manage the data, wherein the data includes the number of fish schools, fishing activities, and quantity configuration; The expected number configuration module is used to set and manage the parameters of the number of fish in the water area, fishing activity rules and expected fish numbers; AI analysis module, which processes, analyzes and predicts data based on artificial intelligence technology, is used to obtain fish population information from system storage data and perform specified prediction and analysis tasks; The user interaction module includes an operation interface for interaction, operation and feedback with the system, which is used to provide the corresponding user with designated task functions through the management terminal and the user terminal; The fishing activity storage module is mainly used to store data related to fishing activities, including fishing locations, fishing times, fish caught and quantity. It is used to record the impact of fishing activities on the number of fish schools and provide data support for the supervision of fishing activities.

2. The electronic fishing management system based on artificial intelligence fish population monitoring as claimed in claim 1, characterized in that: The predictive analysis tasks in the AI ​​analysis module include evaluating the results of the optical camera and the acoustic camera, and increasing the number weight of the optical camera when the specified optical conditions are met, so as to achieve accurate estimation of the number of fish.

3. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 1, characterized in that: The designated task functions include fish population configuration, AI intelligent analysis, fishing activity application, fishing activity management, and historical data viewing.

4. An electronic fishing management system and method based on artificial intelligence fish population monitoring, characterized in that: The electronic fishing management system based on artificial intelligence fish population monitoring as described in claim 2 above and the corresponding operation process are used to build the electronic fishing management system based on artificial intelligence fish population monitoring as described in claim 2 above and execute the corresponding operation process, including the following specific implementation steps: S1. Build an IoT monitoring module underwater, count the number of fish in the water area through the AI ​​analysis module, and store the fish data in the quantity storage module, where the fish data includes the number, longitude and latitude of the water area, and depth of the water area; S2. Conduct fishing experiments and store the impact on the number of fish in a quantity storage module, wherein the impact on the number of fish includes the number of fish at each monitoring point and the longitude and latitude of the fishing point; S3. construct a fishing impact model through the AI ​​analysis module, and store the model in the AI ​​analysis module; S4. Configure the expected number of fish and store it in the expected number configuration module; S5. Apply for fishing through the user interaction module and provide fishing location information and duration information; S6. Determine whether fishing is possible through the fishing impact model and the quantity storage module. If so, store the fishing activity in the fishing activity storage module.

5. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 4, characterized in that: The specific operation steps of counting the number of fish schools in the water area in step S1 include: The weighted average method is used to count the number of fish, and the number of fish in the water area is preset as Q0, and its expression is: The water area needs to be divided into multiple unit water areas manually in advance. One optical camera and one acoustic camera are placed in each unit water area. i represents the unit water area number, W represents the unit water area number. i Indicates the number of optical devices in the current water area, O i Indicates the total number of fish activities per day per unit water area of ​​the current optical device, V i Indicates the total number of daily fish activities per unit area of ​​the current acoustic device.

6. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 5, characterized in that: The current water area optical equipment quantity score evaluation W i It is calculated by the color, contrast and clarity of the picture. i The specific method for obtaining includes the following steps: L1. Collect 500 images from cameras in different waters at different times; L2. 20 raters are preset to manually rate the images. The scores range from 0.1 to 1 and are divided into 10 levels with a step size of 0.

1. The higher the score, the more consistent the image is with human visual perception and the better the visual quality. For each image, the highest and lowest scores are removed, and the average score given by the remaining 18 observers is recorded as the valid score. L3. Use VGG16 Net to extract the 4096-dimensional features of the image and the corresponding quality scores that conform to human visual perception and send them to the random forest model for training; L4. After the model training is completed, all images are sent to the VGG16 Net deep neural network to extract features, and the final score is output through the random forest to obtain the score evaluation W i .

7. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 4, characterized in that: The method for obtaining the impact of the number of fish in step S2 includes: The location where the optical and acoustic equipment is placed is set as the monitoring point. The spatial distance l of fishing, the fishing time t, and the number of fish before fishing Q are calculated through the fishing point and the monitoring points of all unit waters. before And the number of fish after fishing Q after And through multiple experiments, multiple sets of sampling data were obtained to obtain the impact of fishing activities on the number of fish schools at different spatial distances.

8. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 7, characterized in that: The fishing impact model in step S3 includes a fish population prediction model, and the method for constructing the fish population prediction model includes: S31. Linear regression is used to construct a fishing activity prediction model, where Q before As training parameters X, Q after As the prediction parameter Y; S32. Since the data set is small, cross-validation is adopted to obtain the fish population prediction model: Y=X-wt / l Among them, w represents the influencing factor of the number of fishing activities calculated by linear regression, t represents the fishing time, and l represents the spatial distance between the fishing location and the unit water area monitoring point.

9. The electronic fishing management system and method based on artificial intelligence fish population monitoring as claimed in claim 8, characterized in that: The expected quantity in step S4 is set to Q expect In the step S5, the fishing location information is set as longitude and latitude information, and the determination method in the step S6 includes: S61. By calculating the longitude and latitude, we get the distance set L of all points = {l1, ..., l n }; S62. Substituting the distance set data of the points into the fish population prediction model, the expected result set of fish population Q = {q1, ..., q n }; S63. Compare the number of fish in set Q with Q expect , if both are greater than Q expect , then the fishing activity will be automatically approved; if it is less than , then the fishing activity will be automatically rejected.

Images