Automatic feeding method for shrimp culture, related equipment and system

Abstract

The invention relates to an automatic feeding method, related equipment and system for shrimp culture, and the method comprises the steps: receiving processing information transmitted by an auxiliary monitoring device, and analyzing the processing information to obtain a health analysis result and feed stock information; according to the health analysis result and feed stock information, if the health analysis result indicates that the health information is normal, the feeding machine receives a first feeding instruction sent by a server; and if the health analysis result indicates that the health information is abnormal, displaying warning information corresponding to the health analysis result by using a terminal. According to the automatic feeding method for shrimp culture provided by the embodiment of the invention, the feeding strategy can be adjusted in real time according to the health state of shrimps, so that the feeding requirement of'small-amount and multi-meal 'is met, and the problem of excessive or too little feeding is solved.

Description

Technical Field

[0001] The present application relates to the technical field of shrimp farming, and in particular to an automatic feeding method, related equipment and system for shrimp farming. Background Art

[0002] Accurately understanding the distribution, growth, health, and behavioral characteristics of aquatic animals has become a basic task for smart fisheries and precision farming. In the existing technology, although the automatic feeding system can implement the "small amount and multiple meals" feeding strategy, the automatic feeding system cannot adjust the feeding amount in real time according to the health status of the shrimp, and there is a problem of overfeeding and water pollution.

[0003] This section merely provides background information related to the present application and is not necessarily prior art. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the embodiment of the present application provides an automatic feeding method for shrimp farming, which can adjust the feeding strategy in real time according to the health status of the shrimp to meet the feeding needs of "small amounts and multiple meals" and solve the problem of overfeeding or underfeeding.

[0005] The first aspect of the embodiment of the present application provides an automatic feeding method for shrimp farming, comprising the following steps:

[0006] receiving the processed information sent by the auxiliary monitoring device, and parsing the processed information to obtain health analysis results and feed inventory information;

[0007] According to the health analysis result and the feed inventory information, if the health analysis result indicates that the health information is normal, the feeding machine receives a first feeding instruction sent by the server;

[0008] If the health analysis result indicates that the health information is abnormal, a warning message corresponding to the health analysis result is displayed using a terminal.

[0009] In one embodiment, the first feeding instruction includes a first sub-instruction, a second sub-instruction, and a third sub-instruction with decreasing feeding amounts in sequence;

[0010] The feed inventory information includes a feed presence state and a feed absence state;

[0011] The feed existence state includes that the feed remaining is less than the set value and the feed remaining is greater than the set value;

[0012] Wherein, if the feed inventory information indicates that there is no feed, the first sub-instruction is executed;

[0013] If the feed status is that the remaining feed is less than the set value, the second sub-instruction is executed;

[0014] If the feed existence status is that the remaining feed is greater than the set value, the third sub-instruction is executed.

[0015] In one embodiment, the first feeding instruction further includes a fourth sub-instruction;

[0016] After receiving the processing information sent by the auxiliary monitoring device, the method further includes:

[0017] A historical data set of feed inventory information is obtained, and a fourth sub-instruction is sent to the feeding machine in combination with the historical data set, current feed inventory information and health analysis results.

[0018] In one embodiment, the processed information includes video information and picture information, and the health analysis result includes at least one of the following: average movement speed, average acceleration, individual size, appearance of shrimp shell, intestine and gills.

[0019] In one embodiment, parsing the processed information to obtain health analysis results and feed inventory information specifically includes:

[0020] Calculate the average movement speed and average acceleration of the shrimp through the video information, and determine whether the average movement speed and average acceleration are greater than a set value. If so, determine that the health information is normal; if not, determine that the health information is abnormal;

[0021] Extracting the image information of the shrimp from the picture information, and performing recognition processing on the image information of the shrimp using an image recognition model, wherein the image recognition model is a model for recognizing the health status of shrimp obtained by training healthy shrimp;

[0022] The output is processed by an image recognition model to obtain information about the individual size of the shrimp, the appearance of its shell, its intestines, and its gills.

[0023] In one embodiment, parsing the processed information to obtain health analysis results and feed inventory information specifically includes:

[0024] The shrimp net image of the picture information is extracted, and the shrimp net image is converted into a number of pixels. The pixels are compared by a judgment model, and the judgment model is shrimp net RGB and feed RGB. If the RBG of the pixel is similar to the feed RGB, the current pixel is a feed pixel. If the RBG of the pixel is similar to the shrimp net RGB, the current pixel is a non-existent feed pixel. The feed stock information is the ratio of the pixel with feed to a set of several pixels.

[0025] In one embodiment, while receiving the processing information sent by the auxiliary monitoring device, the method further includes:

[0026] receiving environmental monitoring information sent by the auxiliary monitoring device to request a second feeding instruction corresponding to the environmental monitoring information;

[0027] The environmental monitoring information includes at least one of the following: water pH value, dissolved oxygen, nitrogen and oxygen concentration, water temperature, air temperature and air pressure.

[0028] A second aspect of an embodiment of the present application provides a feeding machine having a wireless communication module, which establishes a communication connection with a server through the wireless communication module, and is used to execute any of the above-mentioned automatic feeding methods for shrimp farming.

[0029] A third aspect of an embodiment of the present application provides an auxiliary monitoring device, which has a wireless communication module and establishes a communication connection with a server through the wireless communication module.

[0030] A fourth aspect of an embodiment of the present application provides a shrimp farming feeding system, comprising: a feeding machine, an auxiliary monitoring device and a server; wherein the feeding machine executes any of the above-mentioned shrimp farming automatic feeding methods.

[0031] The technical solution provided by this application may have the following beneficial effects:

[0032] The automatic feeding method for shrimp farming provided by the present application, after the auxiliary monitoring device sends the corresponding information to the server, the server will parse the processing information in the background, if the health analysis result obtained by the analysis indicates that the health information is normal, then the first feeding instruction is matched according to the current feed inventory information, and the first feeding instruction is sent to the feeding machine, and the feeding machine executes the first feeding instruction to perform the feed feeding work; if the analyzed health analysis result indicates that the health information is abnormal, the warning information matching the health analysis result is displayed through the user's terminal to remind the user to confirm on site. The present invention realizes real-time data collection and comprehensive analysis through the interaction between the cloud server, the auxiliary monitoring device and the feeding machine. When applied to the "small amount and multiple meals" intelligent feeding plan, it can significantly improve the breeding efficiency, reduce the risk of water pollution caused by excessive feeding, reduce breeding costs, and improve breeding benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail the exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0034] Figure 1 It is a schematic diagram of the process of the automatic feeding method for shrimp farming in Example 1 of the present application;

[0035] Figure 2This is another schematic diagram of the process of the automatic feeding method for shrimp farming in Example 2 of the present application;

[0036] Figure 3 This is another schematic diagram of the process of the automatic feeding method for shrimp farming in Example 3 of the present application;

[0037] Figure 4 This is another schematic diagram of the process of the automatic feeding method for shrimp farming in Example 4 of the present application;

[0038] Figure 5 This is another schematic diagram of the process of the automatic feeding method for shrimp farming in Example 5 of the present application;

[0039] Figure 6 It is a logical structure diagram of the shrimp farming and feeding system in Example 6 of the present application. DETAILED DESCRIPTION

[0040] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0041] In practical applications, the "small amount and multiple meals" feeding strategy required by shrimp can usually be achieved through an automatic feeding system. However, this feeding strategy cannot adapt to the growth status, eating conditions and health status of shrimp, and there are problems such as excessive feeding leading to overeating or water pollution. In view of this, the embodiments of the present application provide an automatic feeding method, related equipment and system for shrimp farming, which are described in detail through multiple embodiments below.

[0042] Example 1

[0043] The automatic feeding method for shrimp farming provided in Example 1 of the present application is described in detail in Figure 1 , the method comprises the following steps:

[0044] 101. The server receives the processing information sent by the auxiliary monitoring device, and parses the processing information to obtain health analysis results and feed inventory information;

[0045] In actual applications, the method of feeding feed is generally carried out in the direction of manual or mechanical scattering. The auxiliary monitoring device is set in the area where the feed is scattered, and falls into the shrimp net when the feed is scattered. Shrimp has autonomous feeding and swimming ability, and can actively find feed when hungry, so that the feed in the shrimp net can be eaten normally by the shrimp. Based on the habits of shrimp, after the auxiliary monitoring device lifts the shrimp net, a certain number of shrimp can be captured, and the image of the shrimp is obtained through the camera module on the auxiliary monitoring device. When in use, the auxiliary monitoring device is started within the set time according to the feeding strategy of small amounts and multiple meals or according to the user's request instruction. After receiving the instruction, the auxiliary monitoring device takes a video of the shrimp in the water body and takes a picture of the shrimp in the shrimp net after lifting the shrimp net, generates processing information and sends it to the server. After receiving the processing information, the server will parse the processing information in the background, and generate a feeding response strategy based on the health analysis results and feed inventory information according to the health information.

[0046] Among them, the shrimp trap is photographed by the auxiliary monitoring device, and the feed in the shrimp trap at this time is the feed fed last time (i.e. the current feed inventory information)

[0047] Among them, the server in the embodiment of the present application may include a mobile phone, a wearable device, a computer, and a smart mobile device, etc.

[0048] Exemplarily, the server, the auxiliary monitoring device and the feeding machine are connected via a communication connection, such as a Bluetooth connection, a WiFi connection or a data connection of other wireless communication protocols, which is not specifically limited here.

[0049] 102. The server receives, based on the health analysis result and the feed inventory information, a first feeding instruction sent by the server if the health analysis result indicates that the health information is normal;

[0050] After the server generates the health analysis results and feed inventory information, it issues the first feeding instruction or warning information according to the health analysis results. When the feeding machine receives the first feeding instruction, it can perform the feeding work and scatter the feed on the shrimp pond. When the health analysis results indicate that the health information of the shrimp is abnormal, it is not suitable to feed at this time. The server sends a warning message to the user, and the user conducts manual verification.

[0051] The first feeding instruction is a feeding strategy made in combination with the current shrimp health analysis results and the current feed inventory information, so that the feeding amount this time can meet the shrimp's feeding requirements.

[0052] Specifically, the server determines whether the last feeding strategy meets the shrimp's eating needs based on the parsed feed stock information. For example, when there is no feed left in the shrimp net, it indicates that the shrimp may be hungry, but the specific hunger level of the shrimp is unknown. Therefore, when generating the corresponding feeding strategy based on the feed stock information, it is necessary to determine the current health status of the shrimp in combination with the shrimp health analysis results so as to achieve accurate feeding; if there is feed left in the shrimp net, the corresponding feeding strategy is generated based on the remaining feed and the shrimp health analysis results.

[0053] 103. If the health analysis result indicates that the health information is abnormal, using a terminal to display a warning message corresponding to the health analysis result.

[0054] Generally speaking, the health status of shrimp can be judged from the color and shape of its shell, intestines, gills, etc., such as the color of the shell, the fullness of the intestines, the gloss of the shell, the color of the gills, and the color of the liver.

[0055] Specifically, if the health analysis result indicates an abnormality, for example, if the health analysis result indicates that the shrimp has red, white or black spots on its body, the terminal will display a warning message of "shrimp body lesions". For another example, if the health analysis result indicates that the shrimp's digestive tract is clean and free of excrement, the terminal will display a warning message of "the shrimp may be hungry or sick" to remind the user to deal with it in time; for another example, if the health analysis result indicates that the shrimp is not active enough, the terminal will display a warning message of "the shrimp is not active enough" to remind the user to observe whether the environmental conditions such as water pH, dissolved oxygen, nitrogen and oxygen concentration and water temperature are within the appropriate range.

[0056] When the health analysis result is abnormal, the situation is no longer suitable for feeding shrimps. The server can send a feeding suspension instruction to the feeder, and the feeder stops working. Based on the abnormality of the health information, the server sends a corresponding warning message to the user's mobile terminal, reminding the user to go to the site to observe the details. After the user confirms, the server sends a "continue to execute the feeding strategy" instruction to the server through the terminal or enters the feeding instruction on site.

[0057] In this embodiment, after the auxiliary monitoring device sends the corresponding information to the server, the server will parse the processed information in the background. If the health analysis result obtained by the analysis indicates that the health information is normal, the first feeding instruction is matched according to the current feed inventory information, and the first feeding instruction is sent to the feeding machine, and the feeding machine executes the first feeding instruction to perform the feed feeding work; if the analyzed health analysis result indicates that the health information is abnormal, the user's terminal displays a warning message matching the health analysis result to remind the user to confirm on site. The present invention realizes real-time data collection and comprehensive analysis through the interaction between the cloud server, the auxiliary monitoring device and the feeding machine. When applied to the "small amount and multiple meals" intelligent feeding plan, it can significantly improve the breeding efficiency, reduce the risk of water pollution caused by excessive feeding, reduce breeding costs, and improve breeding benefits.

[0058] Example 2

[0059] The following Example 2 describes the feeding conditions of the "first feeding instruction" in the automatic feeding method for shrimp farming of the present application. Please refer to Figure 2 , specifically including:

[0060] 201. A first feeding instruction includes a first sub-instruction, a second sub-instruction and a third sub-instruction, wherein the feeding amount decreases in sequence;

[0061] Specifically, the first feeding instruction can set three sub-instructions of different feed feeding amounts according to the feed inventory information, for example, the first sub-instruction corresponds to the normal feeding amount, the second sub-instruction corresponds to 80% to 100% of the normal feeding amount, and the third sub-instruction corresponds to 50% to 80% of the normal feeding amount. In specific implementation, the specific feeding amount of each sub-instruction can be adjusted according to the specific information of the feed inventory information and the health analysis results of the shrimp.

[0062] 202. The feed inventory information includes a feed presence state and a feed absence state;

[0063] The feed existence state includes that the feed remaining is less than the set value and the feed remaining is greater than the set value;

[0064] Specifically, the auxiliary monitoring device can lift the shrimp net through the lifting mechanism 5 minutes before the next feeding, and then use the camera module to capture the image of the shrimp net to obtain the current feed inventory information.

[0065] If the current feed inventory information is in the feed state, it means that the last feeding was excessive, and the second or third sub-instruction should be executed in combination with the health analysis results. If the current feed inventory information is in the feed state, it means that the shrimp may be hungry, and the cloud server executes the first sub-instruction in combination with the health analysis results.

[0066] When the feed inventory information indicates that there is feed, a targeted feeding instruction is required based on the remaining amount of feed. Specifically, when the remaining feed in the shrimp net is less than the set value, the server sends a second sub-instruction to the feeding machine, and the feeding machine receives the second sub-instruction and executes the feeding action;

[0067] When the remaining feed is greater than the set value, the server sends a third sub-instruction, and the feeder performs the feeding action according to the third sub-instruction.

[0068] For example, the set value in this embodiment can be set to a range of 15% to 50% of the last feed amount based on basic information such as the shrimp species, body shape, and growth cycle.

[0069] In this embodiment, by monitoring the feed inventory information in the shrimp trap and combining it with the shrimp health analysis results, a more accurate small-meal and multiple-meal feeding strategy is output, which can ensure that the feeding can meet the growth of the shrimp and reduce the pollution of water quality by excessive feed.

[0070] Example 3

[0071] In practical applications, after shrimps are infected with a disease, their food intake may gradually decrease. At this time, the feeding strategy given by the current feed inventory information may be excessive. In view of this, this embodiment 3 provides a corresponding design scheme, please refer to Figure 3 ,include:

[0072] 301. The server receives the processing information sent by the auxiliary monitoring device, and parses the processing information to obtain health analysis results and feed inventory information;

[0073] This step may be the same as or similar to step 101 and will not be described in detail here.

[0074] 302. The server receives, based on the health analysis result and the feed inventory information, a first feeding instruction sent by the server if the health analysis result indicates that the health information is normal;

[0075] This step may be the same as or similar to step 102 and will not be described in detail here.

[0076] 303. If the health analysis result indicates that the health information is abnormal, displaying warning information corresponding to the health analysis result using a terminal;

[0077] This step may be the same as or similar to step 103 and will not be described in detail here.

[0078] 304. The first feeding instruction includes a first sub-instruction, a second sub-instruction and a third sub-instruction of which the feeding amount decreases in sequence;

[0079] This step may be the same or similar to step 201 and will not be described in detail here.

[0080] 305. The feed inventory information includes a feed presence state and a feed absence state;

[0081] The feed existence state includes that the feed remaining is less than the set value and the feed remaining is greater than the set value;

[0082] This step may be the same as or similar to step 202 and will not be described in detail here.

[0083] 306. The server obtains a historical data set of feed inventory information, and sends a fourth sub-instruction to the feeding machine in combination with the historical data set, current feed inventory information and health analysis results.

[0084] Specifically, the server obtains a historical data set of feed inventory information within 2 to 3 days, analyzes the historical data set, obtains the actual food intake of the shrimp during this period, and then adjusts the feeding amount of the shrimp this time to execute the fourth sub-instruction.

[0085] In this embodiment, the fourth sub-instruction is a special feeding strategy. Compared with the first, second and third sub-instructions, the amount of feed fed is less. During specific operations, technical personnel can collaborate to dynamically adjust the feeding strategy of the fourth sub-instruction.

[0086] Furthermore, if the feed fed this time is in a state of no feed when the feed inventory information is monitored, the feeding amount is gradually increased until the normal feeding strategy is restored, that is, the first sub-instruction, the second sub-instruction and the third sub-instruction are executed.

[0087] In this embodiment, statistical analysis can also be performed on the historical data set of feed inventory information and the historical health analysis results to generate a detailed evaluation report. Based on the first feeding instruction, the feeding strategy is automatically optimized to achieve a more efficient shrimp farming strategy.

[0088] Example 4

[0089] The following Example 4 describes the "health information" and "health analysis results" in the automatic feeding method for shrimp farming of the present application. Please refer to Figure 4 , specifically including:

[0090] 401. The processed information includes video information and picture information, and the health analysis result includes at least one of the following: average movement speed, average acceleration, individual size, appearance of shrimp shell, intestine and gills;

[0091] Specifically, the auxiliary monitoring device can be used to shoot videos on the water body or on the shrimp trap, and to shoot pictures on the shrimp trap. The auxiliary monitoring device sends the acquired video information and picture information to the server, which analyzes the specific content of the video information and picture information in the background and generates corresponding health analysis results.

[0092] 402. The server calculates the average movement speed and average acceleration of the shrimp through the video information, and determines whether the average movement speed and average acceleration are greater than a set value. If so, it is determined that the health information is normal; if not, it is determined that the health information is abnormal;

[0093] Analyze the movement trajectory of the shrimp through video information, calculate the average movement speed and acceleration, and determine whether the average movement speed and the acceleration are greater than a set value. If so, determine that the health information is normal; if not, determine that the health information is abnormal;

[0094] In practical applications, the movement speed of shrimp varies depending on factors such as its species, environment, age, health status, and whether it is stimulated. In order to facilitate understanding of the inventive concept of the present application, for example, the average movement speed of shrimp in the water is set to 5m / s and the acceleration is 20m / s. 2 This is achieved through the disturbance device on the auxiliary monitoring device. When the shrimp is hungry and weak or has a disease, its physical signs are weak and it cannot move at the average speed and average acceleration. As a result, when the server is parsing the video information, it can use the shrimp's movement speed and acceleration as one of the factors to determine the shrimp's health.

[0095] 403. The server extracts the image information of the shrimp from the picture information, and performs recognition processing on the image information of the shrimp using an image recognition model, wherein the image recognition model is a model obtained by training healthy shrimps and used to recognize the health status of shrimps.

[0096] Analyzing the body color, gloss and digestive tract through image information, and analyzing the body color of the shrimp, the gloss of the shrimp shell and the intestine using a color histogram;

[0097] Determining that the body color and gloss are within the range of the body color and gloss of healthy shrimp, if so, determining that the health information is normal; if not, determining that the health information is abnormal;

[0098] Determine whether the fullness of the intestine is greater than a set value. If so, determine that the health information is abnormal; if not, determine that the health information is normal.

[0099] The body color of normal shrimp is translucent green. The young shrimp is transparent, with firm eyes and clean appendages. The liver and intestines can be clearly seen. As the breeding cycle increases, the shrimp body color changes from transparent to transparent green and the color deepens. Under stress and pathological conditions, the shrimp's body color will change. The health of the shrimp can be judged based on the changes in the shrimp's physique. Generally speaking, the colors of shrimp body lesions include red body, white body, black spots, white muscle turbidity, yellow body, etc. After the auxiliary monitoring device captures the shrimp with the shrimp net, it takes a picture of it through the camera module and sends the picture information to the server. The server will determine the shrimp's body color, gloss and digestive tract fullness based on the RGB color components in the background, and then determine whether the shrimp is healthy.

[0100] 404. Extract the shrimp net image of the picture information, convert the shrimp net image into a number of pixels, and compare the pixels through a judgment model, the judgment model is shrimp net RGB and feed RGB, if the RBG of the pixel is similar to the feed RGB, then the current pixel is a feed pixel, if the RBG of the pixel is similar to the shrimp net RGB, then the current pixel is a non-existent feed pixel, and the feed inventory information is the ratio of the feed pixel to a set of a number of pixels.

[0101] Example 5

[0102] On the basis of the above embodiments 1 to 4, in order to improve the results of accurate feeding of shrimp, on the basis of the above specific embodiments, the embodiment of the present application designs a method for detecting the environment to improve the feeding effect of shrimp and ensure the breeding efficiency. Please refer to Figure 5 , specifically:

[0103] 501. The server receives the processing information sent by the auxiliary monitoring device, and parses the processing information to obtain health analysis results and feed inventory information;

[0104] This step may be the same or similar to step 101 or 301 and will not be described in detail here.

[0105] 502. The server receives, based on the health analysis result and the feed inventory information, a first feeding instruction sent by the server if the health analysis result indicates that the health information is normal;

[0106] This step may be the same as or similar to step 102 or 302 and will not be described in detail here.

[0107] 503. If the health analysis result indicates that the health information is abnormal, displaying warning information corresponding to the health analysis result using a terminal;

[0108] This step may be the same as or similar to step 203 or 303 and will not be described in detail here.

[0109] 504. The server receives the environmental monitoring information sent by the auxiliary monitoring device to request a second feeding instruction corresponding to the environmental monitoring information;

[0110] The environmental monitoring information includes at least one of the following: water pH value, dissolved oxygen, nitrogen and oxygen concentration, water temperature, air temperature and air pressure.

[0111] Specifically, the suitable temperature for breeding is 18℃~32℃; the suitable salinity is 0~5ppt; the dissolved oxygen requirement is above 5mg / L; the ammonia nitrogen is 0.2mL / L; the optimum pH value of the breeding water is 6.5~8.5. If the detected environmental monitoring information data exceeds the shrimp breeding range, the server will display the corresponding warning information on the user's mobile terminal after receiving the environmental monitoring information, informing the user to deal with the corresponding environmental problems in time to ensure that the shrimp breeding conditions can be maintained in a suitable range, thereby improving the breeding efficiency.

[0112] Furthermore, environmental data can be combined with the shrimp’s health status and eating habits for comprehensive analysis to generate detailed environmental assessment reports and automatically optimize feeding strategies.

[0113] Example 6

[0114] The present application also provides a shrimp farming feeding system for executing the shrimp farming automatic feeding method in each of the above embodiments. Figure 6 , the system comprises:

[0115] The auxiliary monitoring device 601 has a wireless communication module for establishing a communication connection with the server 603 in the above embodiment.

[0116] The feeding machine 602 has a wireless communication module, and the feeding machine 602 interacts with the server 603 to execute any one of the automatic feeding methods for shrimp farming in the above embodiments.

[0117] The server 603 interacts with the feeding machine 602 and the auxiliary monitoring device 601 to execute any one of the automatic feeding methods for shrimp farming in the above embodiments.

[0118] 604, specifically a shrimp trap used for holding feed and catching shrimps.

[0119] The steps to be performed by the shrimp farming and feeding system in the embodiments of the present application have been described in detail in each embodiment of the above method, and will not be repeated here.

[0120] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of the various embodiments have their own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the specification are not necessarily required for the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0121] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flow chart, and the combination of the boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the embodiments described. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An automatic feeding method for shrimp farming, characterized in that: The following steps are involved: receiving the processed information sent by the auxiliary monitoring device, and parsing the processed information to obtain health analysis results and feed inventory information; According to the health analysis result and the feed inventory information, if the health analysis result indicates that the health information is normal, the feeding machine receives a first feeding instruction sent by the server; If the health analysis result indicates that the health information is abnormal, a warning message corresponding to the health analysis result is displayed using a terminal.

2. The automatic feeding method for shrimp farming according to claim 1, characterized in that: The first feeding instruction includes a first sub-instruction, a second sub-instruction and a third sub-instruction with decreasing feeding amounts in sequence; The feed inventory information includes a feed presence state and a feed absence state; The feed existence state includes that the feed remaining is less than the set value and the feed remaining is greater than the set value; Wherein, if the feed inventory information indicates that there is no feed, the first sub-instruction is executed; If the feed status is that the remaining feed is less than the set value, the second sub-instruction is executed; If the feed existence status is that the remaining feed is greater than the set value, the third sub-instruction is executed.

3. The automatic feeding method for shrimp farming according to claim 2, characterized in that: The first feeding instruction also includes a fourth sub-instruction; After receiving the processing information sent by the auxiliary monitoring device, the method further includes: A historical data set of feed inventory information is obtained, and a fourth sub-instruction is sent to the feeding machine in combination with the historical data set, current feed inventory information and health analysis results.

4. The automatic feeding method for shrimp farming according to claim 1, characterized in that: The processed information includes video information and picture information, and the health analysis result includes at least one of the following: average movement speed, average acceleration, individual size, appearance of shrimp shell, intestine and gills.

5. The automatic feeding method for shrimp farming according to claim 4, characterized in that: The analyzing the processing information to obtain the health analysis result and the feed inventory information specifically includes: Calculate the average movement speed and average acceleration of the shrimp through the video information, and determine whether the average movement speed and average acceleration are greater than a set value. If so, determine that the health information is normal; if not, determine that the health information is abnormal; Extracting the image information of the shrimp from the picture information, and performing recognition processing on the image information of the shrimp through an image recognition model, wherein the image recognition model is a model for recognizing the health status of shrimp obtained by training healthy shrimp; The output is processed by an image recognition model to obtain information about the individual size of the shrimp, the appearance of its shell, its intestines, and its gills.

6. The automatic feeding method for shrimp farming according to claim 5, characterized in that: The analyzing the processing information to obtain health analysis results and feed inventory information specifically includes: The shrimp net image of the picture information is extracted, and the shrimp net image is converted into a number of pixels. The pixels are compared by a judgment model, and the judgment model is shrimp net RGB and feed RGB. If the RBG of the pixel is similar to the feed RGB, the current pixel is a feed pixel. If the RBG of the pixel is similar to the shrimp net RGB, the current pixel is a pixel without feed. The feed stock information is the ratio of the pixel with feed to a set of several pixels.

7. The automatic feeding method for shrimp farming according to claim 1, characterized in that: While receiving the processing information sent by the auxiliary monitoring device, the method further includes: receiving environmental monitoring information sent by the auxiliary monitoring device to request a second feeding instruction corresponding to the environmental monitoring information; The environmental monitoring information includes at least one of the following: water pH value, dissolved oxygen, nitrogen and oxygen concentration, water temperature, air temperature and air pressure.

8. A feeding machine, characterized in that: A wireless communication module is provided, through which a communication connection is established with a server, so as to execute the automatic feeding method for shrimp farming as claimed in any one of claims 1 to 7.

9. An auxiliary monitoring device, characterized in that: A wireless communication module is provided, through which a communication connection is established with a server.

10. A shrimp farming feeding system, characterized in that: include: A feeding machine, an auxiliary monitoring device and a server; wherein the feeding machine executes the automatic feeding method for shrimp farming as claimed in any one of claims 1 to 7.

Images