Precision feeding method, system, equipment and medium for eel farming

Abstract

The present application provides a method, system, equipment and medium for accurately feeding eel feed. The method calculates the standard amount of feed fed in the current breeding pond and the data standard value corresponding to each second factor through the first factor data of at least one first factor, so that the eel feed feeding amount is standardized, so as to improve the calculation accuracy of the feed feeding amount. According to the second factor data and the factor weights corresponding to each second factor, the feeding amount influence ratio corresponding to each second factor is calculated, and then the current feeding amount ratio is weighted to calculate. It can comprehensively consider the influence of the external environment and internal factors on the eel feeding situation, and then the feed feeding amount can be controlled according to the state of the eels in the breeding pond. On the basis of the standard amount of feed feeding, the current feeding amount ratio is used to accurately increase or decrease the feeding amount, thereby improving the feeding accuracy of eel feed, reducing the instability caused by regular and quantitative feeding, and improving the eel breeding effect.

Description

Technical Field

[0001] The present application relates to the technical field of eel farming, and in particular to a method, system, equipment and medium for accurately feeding eel farming feed. Background Art

[0002] During eel farming, factors such as feeding time, frequency, feeding amount and breeding environment will have a great impact on eel growth and production output.

[0003] In the eel farming process, feed cost is the main farming cost. How to feed reasonably is the key to reducing farming costs and improving farming efficiency.

[0004] At present, in the process of eel farming, eels are generally fed at regular intervals and in fixed quantities according to the scale of farming and the growth period of the eels. This feeding method requires extremely high professional ability and experience, and is extremely unstable, resulting in poor feeding effect of eel feed.

[0005] Therefore, how to solve the low accuracy of feeding eel aquaculture feed has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The present application provides a method, system, equipment and storage medium for accurately feeding eel aquaculture feed, aiming to improve the accuracy of feeding eel aquaculture feed.

[0007] In a first aspect, the present application provides a method for accurately feeding eel aquaculture feed, the method comprising:

[0008] obtaining first factor data of at least one first factor and second factor data of at least one second factor;

[0009] Based on the first factor data, calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors;

[0010] Determining the feeding amount influence ratio corresponding to each second factor based on each second factor data and the data standard value corresponding to each second factor;

[0011] Based on the factor weights corresponding to the second factors, weighted calculation is performed on the feeding amount influence ratio corresponding to the second factors to obtain the current feeding amount ratio;

[0012] The target feed amount is calculated based on the feed standard amount and the current feed amount ratio.

[0013] In a second aspect, the present application further provides a precise feeding system for eel farming feed, the precise feeding system for eel farming feed comprising:

[0014] a data acquisition module, configured to acquire first factor data of at least one first factor and second factor data of at least one second factor;

[0015] A standard data calculation module is used to calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors based on the first factor data;

[0016] an influencing factor calculation module, configured to determine a feeding amount influence ratio corresponding to each second factor based on each second factor data and a data standard value corresponding to each second factor;

[0017] a feeding amount ratio calculation module, configured to perform weighted calculation on the feeding amount influence ratio corresponding to each of the second factors based on the factor weights corresponding to each of the second factors, to obtain a current feeding amount ratio;

[0018] The feeding amount calculation module is used to calculate the target feed feeding amount based on the feed feeding standard amount and the current feeding amount ratio.

[0019] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the above-mentioned method for precise feeding of eel farming feed are implemented.

[0020] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the above-mentioned method for precise feeding of eel farming feed are implemented.

[0021] The present application provides a method, system, equipment and storage medium for precise feeding of eel aquaculture feed. The method of the present application includes obtaining first factor data of at least one first factor and second factor data of at least one second factor; based on the first factor data, calculating the standard amount of feed fed in the current aquaculture pond and the data standard value corresponding to each second factor; based on each second factor data and the data standard value corresponding to each second factor, determining the feeding amount influence ratio corresponding to each second factor; based on the factor weight corresponding to each second factor, performing weighted calculation on the feeding amount influence ratio corresponding to each second factor to obtain the current feeding amount ratio; calculating the target feed feeding amount based on the feed feeding standard amount and the current feeding amount ratio. In the above manner, the present application calculates the standard amount of feed fed in the current aquaculture pond and the data standard value corresponding to each second factor through the first factor data of at least one first factor, so as to standardize the eel aquaculture feed feeding amount, so as to improve the calculation accuracy of the feed feeding amount. According to the second factor data and the factor weights corresponding to each second factor, the feeding amount influence ratio corresponding to each second factor is calculated, and then the current feeding amount ratio is weighted to calculate the effect of the external environment and internal factors on the eel feeding situation. Then, the feed feeding amount can be controlled according to the state of the eels in the breeding pond. On the basis of the standard feed feeding amount, the current feeding amount ratio can be used to accurately increase or decrease the feeding amount, thereby improving the feeding accuracy of eel breeding feed, reducing the instability caused by timed and quantitative feeding, and improving the eel breeding effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 This is a flow chart of a first embodiment of a method for precise feeding of eel aquaculture feed provided by this application;

[0024] Figure 2 This is a flow chart of a second embodiment of a method for precise feeding of eel aquaculture feed provided by this application;

[0025] Figure 3 This is a flow chart of a third embodiment of a method for precise feeding of eel aquaculture feed provided by this application;

[0026] Figure 4 This is a structural diagram of a first embodiment of a precise feeding system for eel farming provided by the present application;

[0027] Figure 5 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0028] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0031] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0032] Please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of a method for precise feeding of eel aquaculture feed provided in this application.

[0033] like Figure 1 As shown, the method for accurately feeding eel farming feed includes steps S101 to S105.

[0034] S101, obtaining first factor data of at least one first factor and second factor data of at least one second factor;

[0035] In one embodiment, the first factors include eel size, water temperature, stocking density, dissolved oxygen, total pond weight and water quality parameters, and the second factors include environmental parameters, feeding data of the previous day, selection data of the previous day and machine vision analysis data.

[0036] In one embodiment, different species of eels have different breeding environments and methods. Furthermore, the water temperature in the eel's living and growth environment also has certain requirements. Excessively high or low water temperatures can cause the fish to eat less or even stop eating. The water temperature in the breeding pond must be maintained within a certain temperature range to ensure the eel's survival rate and activity. Furthermore, to ensure sufficient oxygen and nutrition in the fish pond, the breeding density must be controlled. While ensuring sufficient dissolved oxygen, it is also necessary to avoid wasting space and reducing yields due to excessive density. The total weight of the eels in the pond affects the feeding rate, which is often affected by the size of the fish and the water temperature. Smaller fish have a higher feeding rate than larger ones.

[0037] In one embodiment, the second factor includes environmental parameters, feeding data from the previous day, selection data from the previous day, and machine vision analysis data. The machine vision analysis data may also include machine vision analysis data from the feeding station, algae analysis data in the aquaculture pond, and eel behavioral analysis data in the aquaculture pond.

[0038] In one embodiment, water quality parameters may include pH, ammonia nitrogen, nitrite, turbidity, etc. For eel growth, slightly alkaline water generally has slightly higher productivity than acidic water. The pH range for eel farming is 6.0-9.0, with an optimal range of 7.2-8.0. Pond water quality requirements include a dissolved oxygen content of at least 5 mg / L, a water transparency of approximately 40 cm, an ammonia nitrogen content below 2 ppm, and a nitrite content below 0.2 ppm.

[0039] In one embodiment, environmental parameters may include indoor environmental parameters, outdoor environmental parameters, and seasons, among others. Indoor environmental parameters may include temperature, humidity, light intensity, atmospheric pressure, O2, CO2, NH3, and the like, while outdoor environmental parameters may include temperature, humidity, light intensity, atmospheric pressure, rainfall, and the like. The previous day's feeding data may include the previous day's feeding amount, feeding status, and remaining feed, among others. The previous day's selection data may include whether selection was performed the previous day and the selection results, among others. The feeding station machine vision analysis data may include real-time feeding status and remaining feed, among others. The algae phase analysis data in the breeding pond may include changes in algae phase, among others. The eel behavioral analysis data in the breeding pond may track the behavioral dynamics of individual eels or the entire eel group over a certain period of time, and determine the dynamics of the eel group through behavioral analysis, thereby helping to determine whether feeding is necessary.

[0040] It is understandable that in aquaculture, good water color can not only promote the growth and development of aquatic animals, but also effectively improve feed utilization. During the breeding process, regulating the algae balance to create good water color can increase production and reduce incidence.

[0041] In one embodiment, algae are primary producers in aquatic ecosystems and have chlorophyll in their bodies, which can convert inorganic substances such as nitrogen and phosphorus in the water into organic substances for absorption by microorganisms, animals and plants in the water.

[0042] In one embodiment, algal balance refers to a balanced population of high-quality algae in the aquaculture water, with a reasonable proportion and a healthy circulation within the water. This balance results in a balanced population of beneficial microorganisms, strong water vitality, and excellent growth and health benefits for the aquatic animals. During the aquaculture process, more algae and a richer variety in the aquaculture water contribute to maintaining water diversity. Therefore, monitoring and analyzing algal biodiversity can help farmers understand the ecological environment within their aquaculture ponds and enable them to timely adjust and control the ecology, making the water environment more conducive to eel growth.

[0043] In one embodiment, the values ​​of the main and secondary factors in the eel farming process will have a great impact on the feeding of eels. For example, when the temperature is lower than 15 degrees, it is not suitable for feeding, when the dissolved oxygen is lower than 3, it is not suitable for feeding, and other conditions that are not suitable for feeding. Even if other factors meet the feeding conditions, feeding cannot be carried out, otherwise it will affect the eel production, cause feed waste, increase costs, and reduce profits.

[0044] S102: Calculate the standard amount of feed for the current aquaculture pond and the standard value of the data corresponding to each of the second factors based on the first factor data;

[0045] In one embodiment, the standard amount of feed for the current breeding pond can be determined based on the first factor data. For example, the amount of feed and the frequency of feed for the eel fry stage, different growth stages of eels, and mature eels can be calculated based on the water temperature, breeding density, and total weight of the pond.

[0046] In one embodiment, the standard feeding amount of feed represents the standard feeding ratio for one feeding of the eel species under the current size, current water temperature, current breeding density and current total weight of the eel in the pond.

[0047] In one embodiment, the growth stage of the eels in the breeding pond can be determined based on the average length of the eels in the breeding pond.

[0048] In one embodiment, the standard value of the second factor can be determined based on the different stages of the eels in the breeding pond. For example, the water quality requirements (such as the required dissolved oxygen level, the pH value that needs to be controlled within a certain range, the required nitrite level, etc.) for a certain species of eel at various growth stages (sizes) and within a certain stocking density range, the indoor environment requirements (such as oxygen level, light intensity, indoor temperature and humidity requirements, etc.), and the requirements for the aquatic ecological environment (algae requirements) can be determined. In addition, the previous day's feeding status may affect the current feeding status of the eels. The previous day's feeding status may include the feeding amount, feeding time, and the amount of food consumed by the eels, which can then be used to determine parameters such as the current feeding amount and feeding frequency.

[0049] S103: Determine the feeding amount influence ratio corresponding to each second factor based on the data of each second factor and the data standard value corresponding to each second factor;

[0050] In one embodiment, based on the second factor data corresponding to each second factor and the data standard value corresponding to each second factor under the current eel growth status in the breeding pond, the feeding amount influence ratio corresponding to each second factor can be calculated, that is, the degree of influence of each second factor on the feeding amount.

[0051] For example, the difference between the actual value corresponding to the second factor (i.e., the second factor data) and the corresponding data standard value can be calculated, and then the ratio between the difference and the data standard value can be calculated, and then the difference between 1 and the ratio can be used as the feeding amount influence ratio, that is:

[0052]

[0053] in, is the feeding amount influence ratio corresponding to the second factor, x is the second factor data corresponding to the second factor, and y is the standard value of the data corresponding to the second factor.

[0054] S104: Based on the factor weights corresponding to the second factors, weighted calculation is performed on the feeding amount influence ratio corresponding to the second factors to obtain a current feeding amount ratio;

[0055] In one embodiment, different factors have varying degrees of influence on eel growth at different stages. Therefore, different second factors should have different corresponding weights. For example, water quality and environmental parameters have a significant impact on eel growth and survival rate. However, these parameters can be manually controlled and are relatively stable, so they have less impact on the current feeding amount and can be assigned a smaller weight. However, the previous day's feeding status and selection process have a greater impact on the current feeding amount and can therefore be assigned a larger weight.

[0056] In one embodiment, based on the factor weights corresponding to the second factors, the feeding amount influence ratio of each factor is weighted and calculated to obtain a comprehensive current feeding amount ratio, that is:

[0057]

[0058] in, Indicates the current feeding ratio. represents the influence ratio of feeding amount corresponding to each second factor, and α, β, …, k represent the factor weights corresponding to each second factor.

[0059] S105: Calculate a target feed amount based on the standard feed amount and the current feed amount ratio.

[0060] In one embodiment, the standard feed amount and the current feed amount ratio are multiplied, and the product is used as the target feed amount.

[0061] The present embodiment provides a method for accurately feeding eel feed. The method calculates the standard feed amount of the current breeding pond and the data standard value corresponding to each second factor through the first factor data of at least one first factor, so that the eel feed amount is standardized to improve the calculation accuracy of the feed amount. According to the second factor data and the factor weights corresponding to each second factor, the feeding amount influence ratio corresponding to each second factor is calculated, and then the current feeding amount ratio is weighted to calculate. The influence of the external environment and internal factors on the eel feeding situation can be comprehensively considered, and the feed feeding amount can be controlled according to the state of the eels in the breeding pond. On the basis of the standard feed feeding amount, the current feeding amount ratio is used to accurately increase or decrease the feeding amount, thereby improving the feeding accuracy of the eel feed, reducing the instability caused by timed and quantitative feeding, and improving the eel breeding effect.

[0062] Please refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the method for precise feeding of eel farming feed provided in this application.

[0063] In this embodiment, based on the above Figure 1 In the embodiment shown, after step S105, the following steps are specifically further included:

[0064] S201, calculating a feed feeding amount threshold based on a preset feeding ratio threshold and the feed feeding standard amount;

[0065] In one embodiment, in order to reduce the amount of data processing, it is not necessary to calculate the feed amount in real time. A calculation cycle can be set, such as calculating once every two hours. However, it is not necessary to eat every time the target feed amount is calculated. The feeding frequency needs to be controlled to avoid feed waste and overeating caused by too high a feeding frequency.

[0066] In one embodiment, a preset feeding ratio threshold value, such as 0.8, can be set, and then the feed feeding amount threshold value is calculated based on the feed feeding standard amount corresponding to the current breeding pond, that is, the product of the preset feeding ratio threshold value and the feed feeding standard amount is used as the feed feeding amount threshold value.

[0067] In one embodiment, the feed feeding amount threshold may be the minimum feed feeding amount in the current breeding pond that does not affect the growth rate and survival rate of the eel group.

[0068] S202: When the target feed amount is greater than the feed amount threshold, generating a feeding instruction;

[0069] In one embodiment, a feed feeding amount threshold is compared with a target feed feeding amount to determine whether the current aquaculture pond needs to be fed. If the target feed feeding amount is greater than the feed feeding amount threshold, it indicates that the eels in the current aquaculture pond are likely to be hungry and need to be fed promptly. Therefore, when the target feed feeding amount is greater than the feed feeding amount threshold, a feeding instruction is generated.

[0070] S203: Based on the feeding instruction, control the feeding station to feed the current breeding pond according to the target feed feeding amount.

[0071] In one embodiment, according to the feeding instruction, the feeding station is controlled to proportion the feed amount according to the target feed amount and to feed the feed.

[0072] Furthermore, when the target feed amount is less than the feed amount threshold, the standard feeding interval duration is calculated based on the first factor data and the standard feed amount; the feeding amount difference is calculated based on the standard feed amount and the target feed amount; the feeding waiting time is calculated based on the standard feeding interval duration and the feeding amount difference; a countdown is performed based on the feeding waiting time, and at the end of the countdown, the target feed amount is recalculated.

[0073] In one embodiment, when the target feed amount is less than the feed amount threshold, it can be considered that the eels in the current breeding pond have not completely digested the last feed and are not currently in a hungry state. Therefore, feeding can be temporarily suspended.

[0074] In one embodiment, when calculating the standard feeding amount of feed, the feeding frequency can be calculated based on the first factor data and the standard feeding amount of feed, and then the standard feeding interval duration, that is, the interval duration between two feedings, is calculated. Then, based on the feeding amount difference between the standard feeding amount of feed and the target feed feeding amount, the waiting time for the next feeding is calculated, that is, the feeding waiting time is calculated based on the ratio of the feeding amount difference to the standard feeding amount of feed and the product of the standard feeding interval duration, so as to perform a countdown. At the end of the countdown, it is necessary to re-collect the first factor data and the second factor data, execute the above-mentioned feed feeding amount calculation process, and recalculate the target feed feeding amount.

[0075] Please refer to Figure 3 , Figure 3 This is a flow chart of the third embodiment of the method for precise feeding of eel aquaculture feed provided in this application.

[0076] In this embodiment, the machine vision analysis data includes feeding platform machine vision analysis data, algae phase analysis data and eel behavior analysis data; based on the above Figure 1 In the illustrated embodiment, step S101 specifically further includes:

[0077] S301, using a first image acquisition device, collecting images of eels eating and remaining feed at the feeding platform to obtain visual data of the feeding platform;

[0078] In one embodiment, the image acquisition device may be an image sensor device such as a camera or an infrared sensor.

[0079] In one embodiment, a first image acquisition device is used to capture images of eels eating in the feeding table area to obtain a video stream to facilitate analysis of the activity of the eels while eating; at the same time, images of the remaining feed in the feeding table can be captured to analyze the amount of feed eaten by the eels.

[0080] In one embodiment, a weight meter may be provided at the feeding station to more intuitively monitor the remaining amount of feed in the feeding station.

[0081] S302, using a second image acquisition device, acquiring an image of algae in the current culture pond to obtain visual data of the algae;

[0082] In one embodiment, the second image acquisition device may be a color camera that has undergone color calibration. The second image acquisition device captures images and videos of the algae in the current aquaculture pond for use in analyzing the water color of the current aquaculture pond. Furthermore, based on the water color and changes in the water color, changes in the algae distribution in the current aquaculture pond can be determined.

[0083] S303, using a third image acquisition device, collecting the eel behavior image in the current breeding pond to obtain eel behavior visual data;

[0084] In one embodiment, the third image acquisition device can be multiple multi-position and multi-angle cameras, covering the entire current breeding pond area, collecting behavioral image sets or video streams of the eel school in the current breeding pond, and can track the behavior of some individual eels, or collect the behavior of the entire eel school.

[0085] S304. Based on a machine vision analysis model, perform machine vision analysis on the feeding platform visual data, the algae phase visual data, and the eel behavior visual data to obtain the machine vision analysis data.

[0086] Furthermore, the machine vision analysis model includes a feeding platform visual analysis sub-model, an algae phase analysis sub-model and an eel behavior analysis sub-model.

[0087] The step S304 specifically includes: based on the feeding platform visual analysis sub-model, analyzing the feeding platform visual data to obtain the feeding platform machine vision analysis data; based on the algae phase analysis sub-model, analyzing the algae phase visual data to obtain the algae phase analysis data; based on the eel behavior analysis sub-model, analyzing the eel behavior visual data to obtain the eel behavior analysis data.

[0088] It can be understood that machine vision is the application of image analysis technology in factory automation. It uses optical systems, industrial digital cameras and image processing tools to simulate human visual capabilities and make corresponding decisions, and ultimately execute these decisions by commanding a specific device.

[0089] In one embodiment, the feeding table visual analysis sub-model is used to analyze the feeding status, feeding amount and remaining amount of eels in the feeding table area, which can help analyze the current feeding situation of eels in the breeding pond, the current hunger level of the eel group, and whether the target feed feeding amount is accurate.

[0090] In one embodiment, if the target feed amount is too much or too little, it is necessary to redistribute the factor weights corresponding to the first factor and the second factor according to the remaining feed amount, and adjust the factor weights so that the next target feed amount calculation result is more accurate.

[0091] In one embodiment, if the target feed feeding amount can just meet the feeding needs of the eels in the current breeding pond, it means that the calculation result is accurate.

[0092] In one embodiment, the algae phase analysis sub-model analyzes the water color of the current aquaculture pond, analyzes the algae distribution and changes in the algae distribution, and then determines the growth status of the eels in the current aquaculture pond. For example, if the algae phase analysis sub-model indicates a significant decrease in the algae distribution in the current aquaculture pond, it may be due to insufficient feed, causing the eels to consume a large amount of algae. In this case, the feed intake needs to be increased. If the algae phase analysis sub-model indicates a significant increase in the algae distribution in the current aquaculture pond, it may be due to excessive feed or changes in the nutritional environment within the aquaculture pond. In this case, the feed intake needs to be reduced or manually adjusted.

[0093] In one embodiment, under normal circumstances, the survival (living) status of aquatic animals can be evaluated, monitored, and measured from both behavioral and physiological perspectives. Behavior is more qualitative, while physiology is more quantitative. However, compared to physiological methods, behavioral methods are more practical and operational, because the measurement of physiological indicators often requires sampling of aquatic animal tissues and blood, which is more cumbersome and requires a high level of technical skills. The behavioral method is a non-invasive technical means that causes almost no harm to aquatic animals. It is more intuitive and can make qualitative or even quantitative judgments in a shorter period of time, allowing fishery practitioners to take appropriate measures to respond in a timely manner.

[0094] In one embodiment, the behavioral study of eels is to analyze their growth status based on their different behaviors, track the behaviors of some individual eels or eel groups through a visual analysis sub-model, and judge the current status of the eel group in the breeding pond. For example, in a state of general hunger, most eels may be less active, swim slowly or be stationary, or most eels may exhibit aggressive hunting behaviors. At this time, it can be determined that the eel group needs to be fed to avoid attacks between eels.

[0095] Furthermore, before step S304, the method specifically includes: based on the image acquisition device, collecting the feeding table data, algae phase data and behavior data of the eel in different states to obtain the initial data for model training; based on the expert prior knowledge, classifying and labeling the initial data for model training to obtain the model training data, wherein the model training data includes a subset of the feeding table visual data, a subset of the algae phase visual data and a subset of the eel behavior visual data; based on the model training data, training the pre-trained model to obtain the machine vision analysis model.

[0096] In one embodiment, an image acquisition device can be used to collect behavioral data, feeding table data, and algae phase data of eels in different states in a breeding pond, such as the behavioral data and eating status of eels in a full state, and the behavioral data and eating status of eels in a hungry state; or the algae phase change data during the growth process of eels from fingerlings to mature eels, that is, algae phase data corresponding to different growth stages, etc., as initial data for model training.

[0097] In one embodiment, based on expert prior knowledge, the initial model training data is classified and labeled. For example, it can be divided into behavioral data, feeding station data, and algae phase data. The behavioral data can then be further subdivided. For example, the behavioral data can be further subdivided into data on changes in eel behavior from a full state to a hungry state, behavioral data / individual behavioral data of eels in a full state, behavioral data / individual behavioral data of eels in a hungry state, and group behavioral data / individual behavioral data of eels at different growth stages in a full / hungry state. This results in subsets of visual data for the feeding station, algae phase, and eel behavior.

[0098] In one embodiment, the pre-trained model can be a model structure such as a convolutional neural network or a deep learning neural network. The pre-trained model is trained respectively using a subset of visual data from a feeding table, a subset of visual data from an algae phase, and a subset of visual data from an eel behavior to generate multiple machine vision analysis sub-models, which are used to analyze the feeding table analysis data, algae phase analysis data, and eel behavior analysis data of the eel group in the breeding pond.

[0099] See also Figure 4 , Figure 4 It is a structural schematic diagram of the first embodiment of a precise feeding system for eel farming feed provided in the present application, and the precise feeding system for eel farming feed is used to execute the aforementioned precise feeding method for eel farming feed.

[0100] like Figure 4 As shown, the precise feeding system 400 for eel farming feed includes: a data acquisition module 401, a standard data calculation module 402, an influencing factor calculation module 403, a feeding amount ratio calculation module 404 and a feeding amount calculation module 405.

[0101] A data acquisition module 401 is configured to acquire first factor data of at least one first factor and second factor data of at least one second factor;

[0102] The standard data calculation module 402 is used to calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors based on the first factor data;

[0103] An influencing factor calculation module 403 is configured to determine a feeding amount influence ratio corresponding to each second factor based on each second factor data and a data standard value corresponding to each second factor;

[0104] A feeding amount ratio calculation module 404 is configured to perform weighted calculation on the feeding amount influence ratio corresponding to each second factor based on the factor weight corresponding to each second factor, to obtain a current feeding amount ratio;

[0105] The feeding amount calculation module 405 is used to calculate the target feed amount based on the feed feeding standard amount and the current feeding amount ratio.

[0106] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the aforementioned embodiment of the precise feeding method for eel farming feed, and will not be repeated here.

[0107] The system provided by the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer device shown.

[0108] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0109] See Figure 5 The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0110] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any one of the methods for accurately feeding eel aquaculture feed.

[0111] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0112] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the precise feeding methods for eel farming feed.

[0113] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0114] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0115] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0116] obtaining first factor data of at least one first factor and second factor data of at least one second factor;

[0117] Based on the first factor data, calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors;

[0118] Determining the feeding amount influence ratio corresponding to each second factor based on each second factor data and the data standard value corresponding to each second factor;

[0119] Based on the factor weights corresponding to the second factors, weighted calculation is performed on the feeding amount influence ratio corresponding to the second factors to obtain the current feeding amount ratio;

[0120] The target feed amount is calculated based on the feed standard amount and the current feed amount ratio.

[0121] In one embodiment, after calculating the target feed amount based on the feed standard amount and the current feed amount ratio, the processor is further configured to:

[0122] Calculating a feed feeding amount threshold based on a preset feeding ratio threshold and the feed feeding standard amount;

[0123] When the target feed amount is greater than the feed amount threshold, generating a feeding instruction;

[0124] Based on the feeding instruction, the feeding station is controlled to feed the current breeding pond according to the target feed feeding amount.

[0125] In one embodiment, after calculating the feed feeding amount threshold based on the preset feeding ratio threshold and the feed feeding standard amount, the processor is further configured to implement:

[0126] When the target feed amount is less than the feed amount threshold, calculating a standard feeding interval duration based on the first factor data and the feed feeding standard amount;

[0127] Calculating a feeding amount difference based on the standard feeding amount of the feed and the target feeding amount of the feed;

[0128] Calculating the feeding waiting time based on the feeding standard interval time and the feeding amount difference;

[0129] A countdown is performed based on the feeding waiting time, and when the countdown ends, the target feed amount is recalculated.

[0130] In one embodiment, the first factors include eel size, water temperature, stocking density, dissolved oxygen, total pond weight and water quality parameters, and the second factors include environmental parameters, feeding data of the previous day, selection data of the previous day and machine vision analysis data.

[0131] In one embodiment, the machine vision analysis data includes feeding platform machine vision analysis data, algae phase analysis data, and eel behavior analysis data;

[0132] When implementing the acquiring of the second factor data of at least one second factor, the processor is configured to implement:

[0133] Based on the first image acquisition device, images of eels eating and images of remaining feed on the feeding platform are acquired to obtain visual data of the feeding platform;

[0134] Based on the second image acquisition device, an image of the algae phase of the current cultivation pond is acquired to obtain visual data of the algae phase;

[0135] Based on the third image acquisition device, the eel behavior image in the current breeding pond is collected to obtain eel behavior visual data;

[0136] Based on a machine vision analysis model, machine vision analysis is performed on the feeding platform visual data, the algae phase visual data, and the eel behavior visual data to obtain the machine vision analysis data.

[0137] In one embodiment, the machine vision analysis model includes a feeding platform visual analysis sub-model, an algae phase analysis sub-model, and an eel behavior analysis sub-model;

[0138] When the processor implements the machine vision analysis model to respectively perform machine vision analysis on the feeding platform visual data, the algae visual data, and the eel behavior visual data to obtain the machine vision analysis data, it is used to implement:

[0139] Analyzing the visual data of the feeding platform based on the visual analysis sub-model of the feeding platform to obtain the machine vision analysis data of the feeding platform;

[0140] Analyzing the algae phase visual data based on the algae phase analysis sub-model to obtain the algae phase analysis data;

[0141] Based on the eel behavior analysis sub-model, the eel behavior visual data is analyzed to obtain the eel behavior analysis data.

[0142] In one embodiment, before implementing the machine vision analysis model to perform machine vision analysis on the feeding platform visual data, the algae visual data, and the eel behavior visual data, and obtaining the machine vision analysis data, the processor is further configured to implement:

[0143] Using an image acquisition device, we collected data on the feeding platform, algae phase, and behavior of eels in different states to obtain initial data for model training.

[0144] Based on expert prior knowledge, the initial model training data is classified and labeled to obtain model training data, wherein the model training data includes a subset of visual data of the feeding platform, a subset of visual data of the algae phase, and a subset of visual data of the eel behavior;

[0145] Based on the model training data, the pre-trained model is trained to obtain the machine vision analysis model.

[0146] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the methods for accurately feeding eel farming feed provided in the embodiments of the present application.

[0147] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device.

[0148] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for accurately feeding eel feed, characterized in that: The method comprises: Obtaining first factor data of at least one first factor and second factor data of at least one second factor; the first factors include eel size, water temperature, stocking density, dissolved oxygen, total pond weight, and water quality parameters; the second factors include environmental parameters, feeding data from the previous day, selection data from the previous day, and machine vision analysis data; the machine vision analysis data includes feeding platform machine vision analysis data, algae phase analysis data, and eel behavior analysis data; Based on the first factor data, calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors; Determining the feeding amount influence ratio corresponding to each second factor based on each second factor data and the data standard value corresponding to each second factor; at least comprising the following steps: calculating the difference between the second factor data and the data standard value corresponding to it; calculating the ratio between the difference and the data standard value, and then using the difference between 1 and the ratio as the feeding amount influence ratio; the feeding amount influence ratio calculation formula is as follows: ； in, is the feeding amount influence ratio corresponding to the second factor, x is the second factor data corresponding to the second factor, and y is the standard value of the data corresponding to the second factor; Based on the factor weights corresponding to the second factors, weighted calculation is performed on the feeding amount influence ratio corresponding to the second factors to obtain the current feeding amount ratio; Multiply the standard feeding amount and the current feeding amount ratio, and use the product as the target feed feeding amount.

2. The eel farming feed precision feeding method according to claim 1, wherein After calculating the target feed amount based on the feed standard amount and the current feed amount ratio, the method further includes: Calculating a feed feeding amount threshold based on a preset feeding ratio threshold and the feed feeding standard amount; When the target feed amount is greater than the feed amount threshold, generating a feeding instruction; Based on the feeding instruction, the feeding station is controlled to feed the current breeding pond according to the target feed feeding amount.

3. The eel farming feed precision feeding method according to claim 2, characterized in that, After calculating the feed feeding amount threshold based on the preset feeding ratio threshold and the feed feeding standard amount, the method further includes: When the target feed amount is less than the feed amount threshold, calculating a standard feeding interval duration based on the first factor data and the feed feeding standard amount; Calculating a feeding amount difference based on the standard feeding amount of the feed and the target feeding amount of the feed; Calculating the feeding waiting time based on the feeding standard interval time and the feeding amount difference; A countdown is performed based on the feeding waiting time, and when the countdown ends, the target feed amount is recalculated.

4. The eel farming feed precision feeding method according to claim 1, characterized in that, The obtaining of second factor data of at least one second factor includes: Based on the first image acquisition device, images of eels eating and images of remaining feed on the feeding platform are acquired to obtain visual data of the feeding platform; Based on the second image acquisition device, an image of the algae phase of the current cultivation pond is acquired to obtain visual data of the algae phase; Based on the third image acquisition device, the eel behavior image in the current breeding pond is collected to obtain eel behavior visual data; Based on a machine vision analysis model, machine vision analysis is performed on the feeding platform visual data, the algae phase visual data, and the eel behavior visual data to obtain the machine vision analysis data.

5. The method for accurately feeding eel aquaculture feed according to claim 4, wherein: The machine vision analysis model includes a feeding platform visual analysis sub-model, an algae phase analysis sub-model, and an eel behavior analysis sub-model; The method of performing machine vision analysis on the feeding platform visual data, the algae phase visual data, and the eel behavior visual data based on the machine vision analysis model to obtain the machine vision analysis data includes: Analyzing the visual data of the feeding platform based on the visual analysis sub-model of the feeding platform to obtain the machine vision analysis data of the feeding platform; Analyzing the algae phase visual data based on the algae phase analysis sub-model to obtain the algae phase analysis data; Based on the eel behavior analysis sub-model, the eel behavior visual data is analyzed to obtain the eel behavior analysis data.

6. The method for accurately feeding eel aquaculture feed according to claim 5, characterized in that: The method further comprises performing machine vision analysis on the feeding platform visual data, the algae visual data, and the eel behavior visual data based on a machine vision analysis model, and obtaining the machine vision analysis data. Using an image acquisition device, we collected data on the feeding platform, algae phase, and behavior of eels in different states to obtain initial data for model training. Based on expert prior knowledge, the initial model training data is classified and labeled to obtain model training data, wherein the model training data includes a subset of visual data of the feeding platform, a subset of visual data of the algae phase, and a subset of visual data of the eel behavior; Based on the model training data, the pre-trained model is trained to obtain the machine vision analysis model.

7. A precise feeding system for eel farming, characterized in that: The eel farming feed precision feeding system comprises: a data acquisition module, configured to acquire first factor data of at least one first factor and second factor data of at least one second factor; the first factors including eel size, water temperature, stocking density, dissolved oxygen, total pond weight, and water quality parameters; and the second factors including environmental parameters, feeding data from the previous day, selection data from the previous day, and machine vision analysis data; the machine vision analysis data including feeding station machine vision analysis data, algae phase analysis data, and eel behavior analysis data; A standard data calculation module is used to calculate the standard amount of feed for the current aquaculture pond and the data standard value corresponding to each of the second factors based on the first factor data; The influencing factor calculation module is used to determine the feeding amount influence ratio corresponding to each second factor based on each second factor data and the data standard value corresponding to each second factor; at least the following steps are included: calculating the difference between the second factor data and the corresponding data standard value; calculating the ratio between the difference and the data standard value, and then using the difference between 1 and the ratio as the feeding amount influence ratio; the feeding amount influence ratio calculation formula is as follows: ； in, is the feeding amount influence ratio corresponding to the second factor, x is the second factor data corresponding to the second factor, and y is the standard value of the data corresponding to the second factor; a feeding amount ratio calculation module, configured to perform weighted calculation on the feeding amount influence ratio corresponding to each of the second factors based on the factor weights corresponding to each of the second factors, to obtain a current feeding amount ratio; The feeding amount calculation module is used to multiply the standard feeding amount of feed and the current feeding amount ratio, and use the product as the target feeding amount of feed.

8. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method for precise feeding of eel farming feed according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method for accurately feeding eel farming feed according to any one of claims 1 to 6 are implemented.

Images