An aquaculture method and system based on the internet of things

Abstract

The application provides a fishery breeding method and system based on the Internet of Things, and the method comprises the following steps: collecting environmental data in a fish pond, wherein the environmental data is used for at least representing water temperature, liquid content and harmful liquid content in the fish pond; reading historical feeding information of a fish group under the condition that the environmental data represents a normal environment, wherein the historical feeding information at least represents a feeding amount and a feeding area of the last time; generating next feeding data based on the historical feeding information, wherein the next feeding data at least comprises a next feeding amount and a target area of expected feeding; and scattering fish feed conforming to the next feeding amount at the target area based on the next feeding data. The technical scheme provided by the application can reduce the breeding cost and improve the survival rate of fry.

Description

Technical Field

[0001] This invention relates to the field of fisheries technology, and in particular to a fisheries aquaculture method and system based on the Internet of Things. Background Technology

[0002] Traditional aquaculture relies heavily on manual experience and requires a large number of personnel, resulting in high costs. Although relatively mature automated feeding systems have emerged, these systems only address the feeding of fish fry; other issues in the aquaculture process remain unresolved.

[0003] Therefore, a more complete aquaculture method is needed that can reduce aquaculture costs while increasing the survival rate of fish fry. Summary of the Invention

[0004] This invention provides an Internet of Things-based aquaculture method and system that can reduce aquaculture costs while increasing the survival rate of fish fry.

[0005] In view of this, the present invention provides an Internet of Things-based aquaculture method, the method comprising: collecting environmental data in a fishpond, the environmental data being used to characterize at least the water temperature, liquid content, and harmful liquid content in the fishpond; under the condition that the environmental data indicates a normal environment, reading historical feeding information of the fish population, the historical feeding information being used to characterize at least the most recent feeding amount and feeding area; generating next feeding data based on the historical feeding information, the next feeding data being used to generate at least the next feeding amount and the expected target feeding area; and, based on the next feeding data, sowing fish feed that conforms to the next feeding amount at the target area.

[0006] In one embodiment, the method further includes:

[0007] Identify the type and current activity status of fish fry in the fishpond, and invoke environmental deployment strategies based on the type and activity status;

[0008] The environmental data characterized by the environmental deployment strategy is compared with the collected environmental data, and the environmental data in the fishpond is adjusted based on the comparison results.

[0009] Record the activity trajectory of the fish fry in the regulated environment, and generate a fish fry farming report based on the activity trajectory.

[0010] In one implementation, invoking an environment deployment strategy based on the type and the activity state includes:

[0011] Based on the type of fish fry, determine the theoretical activity timetable of the fish fry;

[0012] Determine the timestamp corresponding to the current activity status of the fish fry, and query the theoretical activity status corresponding to the timestamp in the theoretical activity time table;

[0013] If the current activity state does not match the theoretical activity state, an environment deployment strategy that matches the theoretical activity state is invoked.

[0014] In one embodiment, adjusting the environmental data within the fishpond based on the comparison results includes at least one of the following:

[0015] Change the liquid content in the fishpond;

[0016] To raise or lower the water temperature of the fishpond;

[0017] Wastewater treatment was carried out on the fishpond.

[0018] In one implementation, generating a fish fry rearing report based on the activity trajectory includes:

[0019] The activity trajectory is segmented to obtain sub-trajectories for different time periods;

[0020] For any given time period, the regions covered by the sub-trajectory are clustered to obtain the representative location of the sub-trajectory;

[0021] Based on the representative positions of each sub-trajectory, a sequence of the fish fry's activity positions is formed, and the health status represented by the activity position sequence is predicted.

[0022] A fish fry farming report is generated based on the described health status.

[0023] In one implementation, clustering the regions covered by the sub-trajectories includes:

[0024] Collect discrete location points in the area covered by the sub-trajectory, and count the dwell time or number of dwell times at each discrete location point;

[0025] Based on the dwell time or the number of dwell times, weights are set for each discrete location point, and the discrete location points carrying weights are clustered.

[0026] In another aspect, the present invention provides an Internet of Things-based aquaculture system, the system comprising:

[0027] An environmental data acquisition unit is used to collect environmental data within the fishpond, wherein the environmental data is at least used to characterize the water temperature, liquid content, and harmful liquid content within the fishpond.

[0028] The historical feeding information reading unit is used to read the historical feeding information of the fish group when the environmental data indicates that the environment is normal. The historical feeding information at least indicates the amount of food fed and the feeding area of ​​the most recent feeding.

[0029] A feeding data generation unit is used to generate feeding data for the next feeding based on the historical feeding information. The feeding data for the next feeding includes at least the amount of food to be fed and the target area for feeding.

[0030] A feeding unit is used to distribute fish feed in the target area in accordance with the amount to be fed in the next feeding, based on the next feeding data.

[0031] In one embodiment, the system further includes:

[0032] An environment deployment unit is used to identify the type of fish fry in the fishpond and the current activity status of the fish fry, and to invoke an environment deployment strategy based on the type and the activity status.

[0033] An environmental adjustment unit is used to compare the environmental data characterized by the environmental deployment strategy with the collected environmental data, and to adjust the environmental data in the fishpond based on the comparison results.

[0034] The report generation unit is used to record the activity trajectory of the fish fry in the regulated environment and generate a fish fry farming report based on the activity trajectory.

[0035] In one embodiment, the report generation unit is specifically used to: segment the activity trajectory to obtain sub-trajectories for different time periods; cluster the areas covered by the sub-trajectory for any given time period to obtain representative positions of the sub-trajectory; form an activity position sequence of the fish fry based on the representative positions of each sub-trajectory, and predict the health status represented by the activity position sequence; and generate a fish fry farming report based on the health status.

[0036] In one implementation, the report generation unit is specifically used to collect each discrete location point in the area covered by the sub-trajectory, and count the dwell time or number of dwells at each discrete location point; based on the dwell time or the number of dwells, set the weight of each discrete location point, and cluster the discrete location points carrying the weights.

[0037] The technical solution provided by the present invention accurately and real-time monitors the main environmental parameters such as water temperature, liquid content, and harmful liquid content in the fish pond through the integration of intelligent perception, pervasive computing, image recognition, and ubiquitous network, and actively makes linkage control. Based on the monitored data, it regulates the fishery breeding environment and can dynamically generate the next feeding data in a timely manner according to the historical feeding data. At the same time, it updates the activity trajectory of the fry in a timely manner and generates a fry breeding report in a timely manner, which can reduce the artificial breeding cost while improving the survival rate of the fry.

[0038] The following will further describe the technical solution of the present invention in detail through the drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0040] Figure 1 It is a schematic diagram of the steps of a fishery breeding method based on the Internet of Things in an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the functional modules of a fishery breeding system based on the Internet of Things in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0043] Please refer to Figure 1 , an embodiment of the present application provides a fishery breeding method based on the Internet of Things. The method includes:

[0044] S1: Collect the environmental data in the fish pond, and the environmental data is at least used to characterize the water temperature, liquid content, and harmful liquid content in the fish pond;

[0045] S2: When the environmental data indicates that the environment is normal, read the historical feeding information of the fish group, and the historical feeding information is at least used to characterize the last feeding amount and feeding area;

[0046] S3: Generate the next feeding data based on the historical feeding information, and the next feeding data at least includes the next feeding amount and the target area to be fed;

[0047] S4: Based on the next feeding data, spread fish feed in line with the next feeding amount at the target area.

[0048] Historical feeding information can represent the total amount of feed and the feeding area in the previous feeding. Feeding in different areas can achieve different feeding effects. Based on historical feeding information, the area covered by fish feed in the fishpond after the last feeding can be calculated, thereby estimating the satiation status of the fish. Subsequently, by selecting different feeding areas and selectively distributing fish feed at preset amounts, it can be ensured that the fish fry in the fishpond are satiated within a certain period.

[0049] In one embodiment, the method further includes:

[0050] Identify the type and current activity status of fish fry in the fishpond, and invoke environmental deployment strategies based on the type and activity status;

[0051] The environmental data characterized by the environmental deployment strategy is compared with the collected environmental data, and the environmental data in the fishpond is adjusted based on the comparison results.

[0052] Record the activity trajectory of the fish fry in the regulated environment, and generate a fish fry farming report based on the activity trajectory.

[0053] Within the fishpond, multiple sensors can be deployed to collect real-time environmental data such as water temperature, liquid content, and harmful liquid content. Liquid content refers to the composition of various liquids in the fishpond, including water and nutrient solutions. Using object recognition algorithms, fish fry can be identified. Each fry carries an identification tag; by recognizing these tags, the type of fry can be determined, and the location and tracking of the same fry can be continuously monitored to obtain its activity status.

[0054] In one implementation, invoking an environment deployment strategy based on the type and the activity state includes:

[0055] Based on the type of fish fry, determine the theoretical activity timetable of the fish fry;

[0056] Determine the timestamp corresponding to the current activity status of the fish fry, and query the theoretical activity status corresponding to the timestamp in the theoretical activity time table;

[0057] If the current activity state does not match the theoretical activity state, an environment deployment strategy that matches the theoretical activity state is invoked.

[0058] During the actual control phase, different fish fry can correspond to different activity schedules. These schedules record the theoretical activity states of the fry and the corresponding environmental deployment strategies. If the current activity state of the fry does not match the theoretical activity state, the environment can be modified in advance to guide the fry into the theoretical activity state.

[0059] In one embodiment, adjusting the environmental data within the fishpond based on the comparison results includes at least one of the following:

[0060] Change the liquid content in the fishpond;

[0061] To raise or lower the water temperature of the fishpond;

[0062] Wastewater treatment was carried out on the fishpond.

[0063] In one implementation, generating a fish fry rearing report based on the activity trajectory includes:

[0064] The activity trajectory is segmented to obtain sub-trajectories for different time periods;

[0065] For any given time period, the regions covered by the sub-trajectory are clustered to obtain the representative location of the sub-trajectory;

[0066] Based on the representative positions of each sub-trajectory, a sequence of the fish fry's activity positions is formed, and the health status represented by the activity position sequence is predicted.

[0067] A fish fry farming report is generated based on the described health status.

[0068] In one implementation, clustering the regions covered by the sub-trajectories includes:

[0069] Collect discrete location points in the area covered by the sub-trajectory, and count the dwell time or number of dwell times at each discrete location point;

[0070] Based on the dwell time or the number of dwell times, weights are set for each discrete location point, and the discrete location points carrying weights are clustered.

[0071] The longer the dwell time and the more times the dwell time, the greater the weight of the discrete location point. Subsequently, a clustering algorithm with weights can be used to cluster each discrete location point, and the center location point after clustering can be used as the representative location of the region.

[0072] Based on the activity timeline of the fish fry, representative positions can be arranged to obtain an activity position sequence. In practical applications, machine learning can be applied to a large number of fish fry activity position sequences to train a predictive model capable of predicting health status. By inputting the real-time generated activity position sequences into this predictive model, accurate health status can be predicted. Subsequently, based on the health status, fish fry farming reports can be generated to ensure timely survival rates of the fish fry.

[0073] Please see Figure 2 In another aspect, the present invention provides an Internet of Things-based aquaculture system, the system comprising:

[0074] An environmental data acquisition unit is used to collect environmental data within the fishpond, wherein the environmental data is at least used to characterize the water temperature, liquid content, and harmful liquid content within the fishpond.

[0075] The historical feeding information reading unit is used to read the historical feeding information of the fish group when the environmental data indicates that the environment is normal. The historical feeding information at least indicates the amount of food fed and the feeding area of ​​the most recent feeding.

[0076] A feeding data generation unit is used to generate feeding data for the next feeding based on the historical feeding information. The feeding data for the next feeding includes at least the amount of food to be fed and the target area for feeding.

[0077] A feeding unit is used to distribute fish feed in the target area in accordance with the amount to be fed in the next feeding, based on the next feeding data.

[0078] In one embodiment, the system further includes:

[0079] An environment deployment unit is used to identify the type of fish fry in the fishpond and the current activity status of the fish fry, and to invoke an environment deployment strategy based on the type and the activity status.

[0080] An environmental adjustment unit is used to compare the environmental data characterized by the environmental deployment strategy with the collected environmental data, and to adjust the environmental data in the fishpond based on the comparison results.

[0081] The report generation unit is used to record the activity trajectory of the fish fry in the regulated environment and generate a fish fry farming report based on the activity trajectory.

[0082] In one embodiment, the report generation unit is specifically configured to segment the activity trajectory to obtain sub-trajectories for different time periods; for the sub-trajectory of any time period, cluster the area covered by the sub-trajectory to obtain the representative position of the sub-trajectory; form the activity position sequence of the fry according to the representative positions of each sub-trajectory, and predict the health state represented by the activity position sequence; generate a fry farming report according to the health state.

[0083] In one embodiment, the report generation unit is specifically configured to collect each discrete position point in the area covered by the sub-trajectory, and count the residence duration or residence times of each discrete position point; based on the residence duration or the residence times, set the weight of each discrete position point, and cluster the discrete position points with weights.

[0084] The technical solution provided by the present invention, through the integration of intelligent perception, pervasive computing, image recognition, and ubiquitous network, accurately and real-time monitors the main environmental parameters such as water temperature, liquid content, and harmful liquid content in the fish pond, and actively makes linkage control. Taking the monitoring data as a reference, it regulates the fishery farming environment, and can timely generate the next feeding data dynamically according to the historical feeding data. At the same time, it updates the activity trajectory of the fry in a timely manner and generates a fry farming report in a timely manner, which can reduce the artificial farming cost while improving the survival rate of the fry.

[0085] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A fish farming method based on the Internet of Things, characterized in that, The method includes: Collect environmental data within the fishpond, the environmental data being used at least to characterize the water temperature and liquid content within the fishpond, the liquid content including the content of harmful liquids; Under the condition that the environmental data represents a normal environment, the historical feeding information of the fish is read, and the historical feeding information at least represents the amount of food fed and the feeding area of ​​the most recent feeding. The next feeding data is generated based on the historical feeding information. The next feeding data includes at least the amount of food to be fed next time and the expected target area for feeding. Based on the next feeding data, fish feed of the appropriate amount for the next feeding is distributed in the target area; The method further includes: Identify the type and current activity status of fish fry in the fishpond, and invoke environmental deployment strategies based on the type and activity status; The environmental data characterized by the environmental deployment strategy is compared with the collected environmental data, and the environmental data in the fishpond is adjusted based on the comparison results. Record the activity trajectory of the fish fry in the regulated environment, and generate a fish fry farming report based on the activity trajectory; The fish fry farming report generated based on the activity trajectory includes: The activity trajectory is segmented to obtain sub-trajectories for different time periods; For any given time period, the regions covered by the sub-trajectory are clustered to obtain the representative location of the sub-trajectory; Based on the representative positions of each sub-trajectory, a sequence of the fish fry's activity positions is formed, and the health status represented by the activity position sequence is predicted. A fish fry rearing report is generated based on the described health status; Clustering the regions covered by the sub-trajectories includes: Collect discrete location points in the area covered by the sub-trajectory, and count the dwell time or number of dwell times at each discrete location point; Based on the dwell time or the number of dwell times, weights are set for each discrete location point, and the discrete location points carrying weights are clustered.

2. The method according to claim 1, characterized in that, The environment deployment strategy based on the type and the activity status includes: Based on the type of fish fry, determine the theoretical activity timetable of the fish fry; Determine the timestamp corresponding to the current activity status of the fish fry, and query the theoretical activity status corresponding to the timestamp in the theoretical activity time table; If the current activity state does not match the theoretical activity state, an environment deployment strategy that matches the theoretical activity state is invoked.

3. The method according to claim 1, characterized in that, Adjusting the environmental data within the fishpond based on the comparison results includes at least one of the following: Change the liquid content in the fishpond; To raise or lower the water temperature of the fishpond; Wastewater treatment was carried out on the fishpond.

4. An Internet of Things-based aquaculture system, characterized in that, The system includes: An environmental data acquisition unit is used to collect environmental data within a fishpond. The environmental data is used to characterize at least the water temperature and liquid content within the fishpond, and the liquid content includes the content of harmful liquids. The historical feeding information reading unit is used to read the historical feeding information of the fish group when the environmental data indicates that the environment is normal. The historical feeding information at least indicates the amount of food fed and the feeding area of ​​the most recent feeding. A feeding data generation unit is used to generate feeding data for the next feeding based on the historical feeding information. The feeding data for the next feeding includes at least the amount of food to be fed and the target area for feeding. A feeding unit is used to distribute fish feed in the target area in accordance with the amount of the next feeding, based on the next feeding data. The system also includes: An environment deployment unit is used to identify the type of fish fry in the fishpond and the current activity status of the fish fry, and to invoke an environment deployment strategy based on the type and the activity status. An environmental adjustment unit is used to compare the environmental data characterized by the environmental deployment strategy with the collected environmental data, and to adjust the environmental data in the fishpond based on the comparison results. The report generation unit is used to record the activity trajectory of the fish fry in the regulated environment and generate a fish fry farming report based on the activity trajectory; Specifically, the report generation unit is used to: segment the activity trajectory to obtain sub-trajectories for different time periods; cluster the areas covered by the sub-trajectory for any given time period to obtain representative positions of the sub-trajectory; form an activity position sequence of the fish fry based on the representative positions of each sub-trajectory, and predict the health status represented by the activity position sequence; and generate a fish fry farming report based on the health status. Specifically, the report generation unit is used to collect each discrete location point in the area covered by the sub-trajectory, and count the dwell time or number of dwells at each discrete location point; based on the dwell time or the number of dwells, set the weight of each discrete location point, and cluster the discrete location points with weights.

Images