Breeding data intelligent processing method

Abstract

The invention provides an intelligent cultivation data processing method, and relates to a data processing technology, the method comprises the steps: obtaining a shielding region and an open region in a cultivation region, controlling a mobile collection device to go to the open region for inspection, and obtaining region inspection data corresponding to the open region; identifying a target object in the area inspection data, obtaining an identification point location of the target object, and taking the identification point location as a target point location of the open area; position information of the breeding positioning device is obtained, when it is determined that the position information is in the shielding area, the corresponding position information serves as a staying position, and a target point location of the shielding area is determined according to the staying duration of the staying position; the dynamic collection path and the dynamic recovery path are generated according to the positioning information of the breeding end and the target point location, the dynamic collection path and the dynamic recovery path are sent to the breeding end, the position of the target object is rapidly determined, and the manual searching time is shortened.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a method for intelligently processing breeding data. Background Art

[0002] With the development of modern agricultural technology, free-range poultry farming is becoming more and more common in large open areas. The free-range model allows poultry to move freely, improving animal welfare and product quality. However, this free movement also brings new challenges, such as the difficulty in locating the egg-laying position of poultry, which in turn increases the workload and complexity of collecting eggs. Due to the wide variety and uneven distribution of vegetation in the breeding area, poultry may lay eggs in open areas or in shaded areas with dense vegetation, which brings considerable difficulties to manual collection.

[0003] Currently, many farms rely on manual inspections to find eggs. However, this method is not only time-consuming and labor-intensive, but also prone to missing eggs due to vegetation obstruction or worker fatigue.

[0004] Therefore, how to determine the location where poultry lay eggs in areas blocked by vegetation, and then optimize the egg collection path, reduce manual search time, and improve breeding efficiency has become an urgent problem that needs to be solved. Summary of the invention

[0005] The embodiment of the present invention provides an intelligent processing method for breeding data, which can determine the location where poultry lay eggs in an area blocked by vegetation, thereby optimizing the egg collection path, reducing manual search time, and improving breeding efficiency.

[0006] A first aspect of an embodiment of the present invention provides a method for intelligently processing aquaculture data, comprising: Acquire the shielded area and the open area in the breeding area, control the mobile collection device to inspect the open area, and obtain the area inspection data corresponding to the open area; Identify the target object in the area inspection data, obtain the identification point of the target object, and use the identification point as the target point of the open area; Acquire the location information of the breeding positioning device, and when it is determined that the location information is in the shielded area, use the corresponding location information as the stay position, and determine the target point of the shielded area according to the stay time of the stay position; A dynamic collection path and a dynamic recovery path are generated according to the positioning information of the breeding end and the target point, and the dynamic collection path and the dynamic recovery path are sent to the breeding end.

[0007] Optionally, in a possible implementation manner of the first aspect, identifying the target object in the area inspection data, obtaining the identification point of the target object, and using the identification point as the target point of the open area includes: Identify the target object in the area inspection data, obtain the position information of the target object as an identification point, and use the identification point as the target point of the open area.

[0008] Optionally, in a possible implementation of the first aspect, the acquiring the position information of the breeding positioning device, and determining that the position information is in the shielded area, using the corresponding position information as the stay position, and determining the target point of the shielded area according to the stay time of the stay position, includes: Acquire the position information of the breeding positioning device, and when it is determined that the position information is in the shielded area, use the corresponding position information as the stay position; Retrieving multiple stay time periods corresponding to each of the stay locations, and obtaining the duration of each of the stay time periods as the stay duration; When it is determined that the stay duration is greater than or equal to the preset stay duration, the corresponding stay duration is used as the stay duration, and the stay location with the stay duration is used as the point to be verified; Receive verification information of the point to be verified from the breeding end, and determine the corresponding point to be verified as the target point of the shielded area based on the verification information, as well as the verified number of targets at the target point of the shielded area.

[0009] Optionally, in a possible implementation of the first aspect, the method further includes: Retrieving an open target image corresponding to the target point in the open area in the area inspection data, identifying a closed contour of the target object in the open target image based on OpenCV, and determining the number of identified target points in the open area according to the closed contour; According to the verified number of target points in the shielded area and the length of stay, a prediction ratio is obtained, and a collection interval period corresponding to the target points in the shielded area is obtained, and based on the prediction ratio and the collection interval period, a predicted number of target points in the shielded area is obtained; The target point of the open area and the target point of the shielded area are updated to the breeding area, and the identified number is updated to the target point of the corresponding open area, and the predicted number is updated to the target point of the corresponding shielded area, to generate a point update map; Counting the predicted quantity and the identified quantity in the point update map to obtain the total collection quantity corresponding to the breeding area; The standard carrying quantity of the target carrier is obtained, and the carrying quantity of the target carrier is obtained according to the ratio of the total collection quantity to the standard carrying quantity, and the carrying quantity is sent to the breeding end.

[0010] Optionally, in a possible implementation manner of the first aspect, identifying a closed contour of the target object in the open target image based on OpenCV, and determining the number of identified target points in the open area according to the closed contour includes: Based on OpenCV, a closed contour of a target object in the open target image is identified, and a target pixel value of the target object is retrieved, and a binarization process is performed on the open target image based on the target pixel value to obtain a quantity recognition image; The number of contours with black pixels in the closed contours in the number recognition image is counted to obtain the number of target points in the open area.

[0011] Optionally, in a possible implementation manner of the first aspect, obtaining a prediction ratio according to the verified number of target points in the shielded area and the length of stay, and obtaining a collection interval period corresponding to the target points in the shielded area, and obtaining a predicted number of target points in the shielded area based on the prediction ratio and the collection interval period, includes: Counting the duration of stay of the target point in the shielded area to obtain the historical cumulative duration corresponding to the target point in the shielded area; According to the ratio of the verification quantity to the historical cumulative duration, a prediction ratio is obtained, and a current collection interval corresponding to the target point in the shielded area is obtained; Obtain the current accumulated duration corresponding to the target point in the shielded area within the current collection interval; Based on the product of the current cumulative time and the predicted ratio, the predicted number of target points in the shielded area is obtained.

[0012] Optionally, in a possible implementation manner of the first aspect, generating a dynamic collection path and a dynamic recovery path according to the positioning information of the breeding end and the target point, and sending the dynamic collection path and the dynamic recovery path to the breeding end, includes: Acquire the positioning information of the breeding end as the starting point, update the starting point to the point update map, and obtain a path planning map; Counting the target points in the path planning map to obtain a set of target points corresponding to the path planning map; Generate a dynamic collection path and a collection direction in the dynamic collection path according to the starting point and the target point set; The cumulative number of target objects corresponding to the target points in the dynamic collection path is counted sequentially based on the collection direction until the cumulative number is greater than or equal to the standard carrying capacity, and the corresponding target points are used as recycling points; Determine the end point in the dynamic collection path as the return point based on the collection direction; Counting the recycling points in the path planning graph to obtain a set of recycling points corresponding to the path planning graph; Generate a dynamic recovery path according to the return point and the recovery point set; The dynamic collection path and the dynamic recovery path in the path planning diagram are sent to the breeding end.

[0013] Optionally, in a possible implementation manner of the first aspect, generating a dynamic acquisition path and an acquisition direction in the dynamic acquisition path according to the starting point and the target point set includes: Determine a target point in the target point set that is closest to the starting point as a connecting point, connect the starting point in the path planning graph with the connecting point, and obtain a sub-collection path; The direction from the starting point to the connection point along the sub-collection path is used as the collection direction; Deleting the connection point in the target point set and using the connection point as the current starting point; Repeat the above steps until the target point set is an empty set, and then generate a dynamic acquisition path.

[0014] Optionally, in a possible implementation manner of the first aspect, generating a dynamic recovery path according to the return point and the recovery point set includes: Determine a recycling point in the recycling point set that is closest to the return point as a connection point, connect the return point in the path planning graph with the connection point, and obtain a sub-recycling path; The direction from the return point to the connection point along the sub-recovery path is used as the recovery direction; Deleting the connection point in the collection point set, and using the connection point as the current return point; Repeat the above steps until the collection point set is an empty set, and then generate a dynamic collection path.

[0015] Optionally, in a possible implementation of the first aspect, the method further includes: Retrieving attribute information corresponding to the breeding positioning device, and dividing the breeding positioning device into a first positioning device and a second positioning device based on the attribute information; Acquire first location information of the first positioning device and second location information of the second positioning device; When it is determined that the first location information and the second location information are at the same location point, the corresponding location point is used as an interaction point; Counting the linkage time duration when the first positioning device and the second positioning device stay at the interaction point at the same time, and when it is determined that the linkage time duration is greater than or equal to the preset interaction time duration, using the first positioning device at the corresponding interaction point as the third positioning device, and using the current time as the classification time; Taking the classification time as the starting time, the target points passed by the third positioning device are sequentially counted based on the preset classification time as the target object selection points.

[0016] According to a second aspect of the present invention, an electronic device is provided, comprising: a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the first aspect of the present invention and various methods that may be involved in the first aspect.

[0017] According to a third aspect of an embodiment of the present invention, a storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the first aspect of the present invention and various methods that may be involved in the first aspect.

[0018] The beneficial effects of the present invention are as follows: 1. The present invention can determine the location where poultry lay eggs in areas blocked by vegetation, thereby optimizing the egg collection path, reducing manual search time, and improving breeding efficiency. First, the present invention divides the breeding area into a shielded area and an open area through intelligent division, and patrols and collects data in the open area through a mobile collection device, so as to obtain regional inspection data for target object identification, determine the target point in the open area, and reduce the search time for personnel. At the same time, the location information of the breeding positioning device can be analyzed to determine the length of stay at the corresponding stop position in the shielded area, so as to determine the target point in the shielded area, reduce the time for personnel to search for the target object in the shielded area, and improve the collection efficiency. Finally, the present invention can generate a dynamic collection path and a dynamic recovery path according to the positioning information and target point of the breeding end, so that the breeding personnel can collect the target object according to the guidance of the path, thereby improving the breeding efficiency.

[0019] 2. The present invention uses a mobile acquisition device to inspect open areas and obtain accurate regional inspection data. Using image recognition technology, the present invention can identify targets in the inspection data and accurately obtain the identification points of the targets. This method significantly improves the accuracy of egg positioning in open areas. At the same time, the present invention can track the position and residence time of poultry by installing a positioning device on poultry in densely covered areas. When poultry stay in a certain covered area for a long time, the position can be marked as a point to be verified, and the target point (egg-laying position) can be predicted in combination with historical data, which effectively solves the problem of missing eggs caused by vegetation obstruction, so as to optimize the egg collection path in the covered area later and reduce the time and labor intensity of manual collection.

[0020] 3. The present invention can plan the path according to the positioning information and target points of the breeding end, generate dynamic collection paths and recycling paths, enable the breeding staff to complete the collection of the target object with the minimum time cost, and guide the breeding staff to efficiently complete the egg collection. Among them, the present invention can connect the nearest target points in real time by analyzing the positioning information, mark the collection direction, and generate a dynamic collection path, which can not only optimize the walking path and reduce the collection time, but also provide the breeding staff with target quantity information by updating the target points and their numbers in the open area and the shielded area in real time, combining historical data for prediction, so as to help the breeding staff reasonably plan the number of carriers, reduce the extra round-trip time caused by insufficient carriers during the collection process, and reasonably arrange the collection and determine the recycling points according to the number of eggs. By connecting the marked recycling points, a dynamic recycling path is obtained to ensure full-load recycling and reduce the number of round trips of personnel, thereby realizing intelligent management of egg collection and improving the overall operation efficiency of the farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a method for intelligent processing of aquaculture data provided by the present invention; Figure 2 A schematic diagram of a recycling point provided by the present invention; Figure 3 A schematic diagram of the hardware structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0024] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0025] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0026] It should be understood that in the present invention, "plurality" refers to two or more than two. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0027] It should be understood that in the present invention, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based only on A, but B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.

[0028] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0029] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0030] like Figure 1 As shown, the present invention provides a method for intelligent processing of aquaculture data, comprising: S1, obtaining the shielded area and the open area in the breeding area, controlling the mobile data collection device to inspect the open area, and obtaining the area inspection data corresponding to the open area.

[0031] It should be noted that when breeders raise poultry in the free-range area, the free-range area is large, the poultry activity trajectory is not fixed, and the vegetation coverage in the free-range area is complex. Some areas are open bare land, and some areas are mostly covered with vegetation such as trees and shrubs. As a result, the egg-laying position of the poultry cannot be determined, which increases the search time for breeders to collect eggs. In addition, due to the obstruction of vegetation, breeders may miss eggs in some positions during the manual search and collection of eggs. At the same time, when the egg-laying position is determined by a mobile drone, the drone will also be blocked by vegetation and cannot intuitively detect the egg-laying position of poultry in the vegetation-covered area. Therefore, the breeding area can be obtained and divided into a shielded area and an open area according to the vegetation coverage, so that different implementation methods can be adopted for the shielded area and the open area in the future to determine the egg-laying position of the poultry, thereby reducing the egg collection time of breeders.

[0032] It can be understood that by obtaining map information corresponding to the breeding area, the shielded area and open area within the breeding area can be determined, wherein the breeding area is the geographical area where poultry is raised, the shielded area is the area within the breeding area that is blocked by vegetation, and the open area is the area within the breeding area that is not blocked by vegetation. The mobile collection device is a device that can be used for mobile collection, such as a drone, and the regional inspection data is the data information collected corresponding to the open area during the inspection, such as captured images and videos.

[0033] Through the above implementation, the present invention can obtain regional inspection data, so as to subsequently determine the target points corresponding to the egg-laying positions of farmed animals in open areas based on the regional inspection data, which is convenient for subsequent personnel to collect and reduce searching time.

[0034] S2, identifying the target object in the area inspection data, and obtaining the identification point of the target object, and using the identification point as the target point of the open area.

[0035] It is understandable that target object identification is performed on the regional inspection data collected by the mobile collection device in order to determine the location points with target objects, so as to facilitate the subsequent generation of paths according to the target points, guide the collection of breeding personnel, and save time.

[0036] Among them, the target object is the eggs produced by farmed animals, such as chicken eggs, duck eggs, etc. The identification point is the location point corresponding to the identification target object, such as the location of the egg, and the target point is the geographical location point of the target object in the corresponding area.

[0037] Through the above implementation, the present invention can determine the location points of target objects in an open area, so as to subsequently generate corresponding collection paths and reduce the collection time of personnel.

[0038] In some embodiments, the specific implementation of step S2 (the step of identifying the target object in the area inspection data, obtaining the identification point of the target object, and using the identification point as the target point of the open area) includes: S21, identifying a target object in the area inspection data, and obtaining position information of the target object as an identification point, and using the identification point as a target point in the open area.

[0039] It can be understood that according to existing image processing technologies such as CNN, RNN and other algorithms, the target objects in the regional inspection data are identified, and the geographic coordinates of the target objects in the current regional inspection data are obtained through the positioning system installed on the mobile acquisition device, so that the location information of the target object can be used as an identification point, and the identification point can be used as the target point in the open area, so that a path can be generated according to the target point later, which is convenient for personnel to collect eggs.

[0040] S3, obtaining the position information of the breeding positioning device, and when determining that the position information is in the shielded area, using the corresponding position information as the stay position, and determining the target point of the shielded area according to the stay time of the stay position.

[0041] It should be noted that in order to determine the possible egg-laying positions of the farmed poultry, a farming positioning device can be installed on the poultry, so that the position where the poultry stays for a long time can be determined based on the farming positioning device, and then the target point where the poultry lays eggs can be obtained, so as to subsequently generate a path and facilitate collection by farmers.

[0042] It can be understood that the breeding positioning device is a device for locating the position of the breeding objects, the position information is the geographical coordinate information of the position, the stop position is the position where the poultry stays in the shielding area, and the stay time is the length of time it stays at the stop position.

[0043] It is not difficult to understand that when it is determined that poultry stays in the same location for a long time, it may be laying eggs at that location. Therefore, the target point in the shielded area can be determined by the length of stay, so that the corresponding target points can be connected to generate a path for personnel collection.

[0044] In some embodiments, the specific implementation of step S3 (obtaining the location information of the breeding positioning device, determining that the location information is in the shielded area, using the corresponding location information as the stay position, and determining the target point of the shielded area according to the stay time of the stay position) includes: S31, obtaining the position information of the breeding positioning device, and when it is determined that the position information is in the shielding area, using the corresponding position information as the stop position.

[0045] It is understandable that when the corresponding position coordinates are determined to belong to the shielded area based on the acquired position information, the position information can be used as the staying position to subsequently determine the staying time of the staying position and determine the target point for poultry to lay eggs in the shielded area.

[0046] S32, retrieve multiple stay time periods corresponding to each of the stay positions, and obtain the duration of each of the stay time periods as the stay duration.

[0047] It should be noted that, since poultry constantly walk in the breeding area during their activities and may stop at a resting position to eat, there may be multiple resting time periods at each resting position. Therefore, in order to determine the location where the poultry stays for a long time, the duration corresponding to the resting time period can be used as the resting time, so that the point to be verified can be judged later based on the resting time.

[0048] Among them, the stay time period is the time period corresponding to each stay position. For example, the chicken stays at position 1 from 7:00 to 8:00, and after an interval of 5 hours, it also stays at position 1 from 14:00 to 14:10. Then, multiple stay time periods at position 1 (7:00-8:00, 14:00-14:10) can be obtained, and the corresponding stay times are 1 hour and 10 minutes respectively.

[0049] S33, when it is determined that the stay duration is greater than or equal to the preset stay duration, the corresponding stay duration is used as the stay duration, and the stay position with the stay duration is used as the point to be verified.

[0050] It can be understood that the preset stay duration is a preset stay duration, the stay duration is a stay duration greater than the preset stay duration, and the point to be verified is a stay location with a stay duration.

[0051] It is not difficult to understand that animals may pass through the same location repeatedly during their activities, but some of them are only location points in the activity trajectory, while some stay for a longer time. The corresponding location points may be the egg-laying locations. Therefore, the location where eggs may be found can be judged based on the length of the stay time, and the stay location with a long stay time can be used as the point to be verified so that we can go to the corresponding point for verification and collection later.

[0052] S34, receiving verification information of the point to be verified from the breeding end, and determining the corresponding point to be verified as the target point of the shielded area based on the verification information, and the verified number of targets at the target point of the shielded area.

[0053] It can be understood that after the point to be verified is transmitted to the breeder for viewing, the breeder can go to the corresponding location point for viewing, and transmit the corresponding quantity to the server through the breeding end. Thus, when it is determined that the verification information has a target object and a corresponding quantity, the point to be verified corresponding to the verification information can be used as the target point in the shielded area, and at the same time, the number of the target object at the target point can be determined.

[0054] Among them, the breeding end is the information terminal corresponding to the breeder, such as the breeder’s mobile phone, and the verification number is the number of target objects at the target point in the shielded area. For example, when the number of eggs at position No. 1 in the bushes is 5, the corresponding verification number is 5.

[0055] It should be noted that due to the large number of target objects, the corresponding containers may not be able to hold all the target objects during the collection process. Therefore, the number of target objects of teammates at each target point can be automatically identified and counted to obtain the total number, reminding the breeders to carry the number of containers when collecting the target objects, so as to reduce the round-trip time for personnel to fetch the containers. Therefore, it also includes: A1, retrieve the open target image corresponding to the target point in the open area in the area inspection data, identify the closed contour of the target object in the open target image based on OpenCV, and determine the number of identified target points in the open area according to the closed contour.

[0056] It can be understood that the open target image is an image of the area corresponding to the target point in the open area, the closed contour is the edge contour corresponding to the target object in the open target image, and the recognition number is the number of recognized closed contours.

[0057] It is not difficult to understand that by performing target object recognition on the open target image corresponding to the target point in the open area in the regional inspection data, the number of recognitions of the corresponding target points can be obtained, so as to perform subsequent quantity statistics and determine the number of carried objects.

[0058] It is worth mentioning that the target object can also be identified directly in the open target image through existing technology. For example, the image of eggs can be recognized by using existing deep learning algorithm technology to identify the eggs in the open target image.

[0059] In some embodiments, the specific implementation of step A1 (identifying the closed contour of the target object in the open target image based on OpenCV, and determining the number of identified target points in the open area according to the closed contour) includes: A11, based on OpenCV, identify the closed contour of the target object in the open target image, and retrieve the target pixel value of the target object, and binarize the open target image based on the target pixel value to obtain a quantity recognition image.

[0060] It can be understood that the image processing technology OpenCV can be used to identify the closed contour of the target object in the open target image, and then the target pixel value corresponding to the target object can be retrieved. When the pixel value in the closed contour belongs to the target pixel value, the corresponding target pixel value can be binarized into a black pixel value for subsequent identification of the quantity. When the pixel value in the closed contour does not belong to the target pixel value, the corresponding pixel value can be processed into white, so that a quantity recognition image can be obtained, so as to subsequently count the identification quantity corresponding to the target point.

[0061] The target pixel value is the pixel value corresponding to the target object, and the quantity recognition image is an image for recognizing the quantity of the target object, that is, an image obtained by binarizing the open target image.

[0062] It is worth mentioning that the binarization of the image is to set the grayscale value of the pixel on the image to 0 or 255, that is, to present the entire image with an obvious visual effect of only black and white, so that the number of target objects at the target point can be more clearly identified based on the subsequent distinction between the two obvious black and white pixels.

[0063] A12, counting the number of contours with black pixels in the closed contours in the number recognition image, and obtaining the number of recognized target points in the open area.

[0064] It is understandable that by counting the number of contours with black pixels in the closed contours in the quantity recognition image, the number of target points recognized in the open area can be obtained. It is not difficult to understand that when there are black pixels in the closed contour, it can be said that the contour corresponds to the edge contour of the target object.

[0065] Through the above implementation, the present invention can identify the number of target points in the open area, so as to subsequently sum the number of target points corresponding to the shielded area, thereby facilitating the prompting of the number of containers carried by the breeder.

[0066] A2, according to the verified number of target points in the shielded area and the length of stay, obtain the predicted ratio, and obtain the collection interval period corresponding to the target points in the shielded area, and based on the predicted ratio and the collection interval period, obtain the predicted number of target points in the shielded area.

[0067] It can be understood that since the target points in the shielded area cannot be collected and identified by the mobile collection device, the number of target points in the shielded area can be predicted based on the historical verification data and the length of stay of the corresponding points. Therefore, the prediction ratio can be obtained based on the verification number and the length of stay of the target points, and the predicted number of target points in the shielded area can be predicted through the prediction ratio and the collection interval period.

[0068] It is not difficult to understand that the collection interval is the interval time period from the current moment to the last person obtaining the verification quantity. For example, when the breeder collected 5 eggs at the target point at 8:00 on May 2, the current moment is 8:00 on May 7, so the collection interval corresponding to the target point is from 8:00 on May 2 to 8:00 on May 7.

[0069] The predicted ratio is a ratio coefficient of the number of target objects at the predicted corresponding target point, and the predicted number is the number of target objects at the predicted target point in the shielded area.

[0070] In some embodiments, the specific implementation of step A2 (obtaining a predicted ratio according to the verified number of target points in the shielded area and the length of stay, obtaining a collection interval corresponding to the target points in the shielded area, and obtaining a predicted number of target points in the shielded area based on the predicted ratio and the collection interval) includes: A21, counting the duration of stay of the target point in the shielded area to obtain a historical cumulative duration corresponding to the target point in the shielded area.

[0071] It can be understood that the historical cumulative duration is the total duration of the stay time in the collection interval period in which the number of target objects in the target point has been determined, that is, the sum of the stay time in the historical time period.

[0072] Through the above implementation, the present invention can obtain the historical cumulative time corresponding to the target point, so as to obtain the prediction ratio according to the verification quantity later.

[0073] A22, obtaining a predicted ratio according to the ratio of the verification quantity to the historical cumulative duration, and acquiring a current collection interval corresponding to the target point in the shielded area.

[0074] It can be understood that the predicted ratio is obtained based on the ratio of the verification number in the historical period to the historical cumulative time, and then the current collection interval of the target point in the shielded area can be obtained, so as to subsequently count the length of time that poultry stay at the target point in the current collection interval, thereby predicting the number of target objects at the corresponding target point at the current moment.

[0075] For example, when the historical cumulative duration is 5 hours and the number of verifications is 5, it can be determined based on the ratio of the number of verifications to the historical cumulative duration that one hour of stay can produce one target object.

[0076] A23, obtaining the current accumulated duration corresponding to the target point in the shielded area within the current collection interval.

[0077] It can be understood that the current cumulative duration is the sum of the corresponding stay durations of the target points in the shielded area during the current collection interval.

[0078] For example, if the current collection interval is from 8:00 on May 2 to 8:00 on May 7, the length of time that the breeding positioning device stays at the corresponding target point between 8:00 on May 2 and 8:00 on May 7 can be accumulated, wherein the method for determining the length of stay is consistent with the above steps S31-S33, which will not be repeated here.

[0079] A24, based on the product of the current cumulative time and the predicted ratio, obtain the predicted number of target points in the shielded area.

[0080] It is understandable that after determining the current cumulative duration, the current cumulative duration and the predicted ratio can be multiplied to obtain the predicted number of target points in the shielded area, so as to subsequently determine the number of target loads that the breeders need to carry.

[0081] A3, updating the target points of the open area and the target points of the shielded area to the breeding area, updating the identified quantity to the corresponding target points of the open area, updating the predicted quantity to the corresponding target points of the shielded area, and generating a point update map.

[0082] It can be understood that in order to more intuitively display the location points and quantity of target objects, the target points corresponding to the open area and the shielded area can be updated in the image of the breeding area, and the identified quantity can be updated at the target point corresponding to the open area, and the predicted quantity can be updated at the target point corresponding to the shielded area, thereby obtaining a point update map with target points and quantities.

[0083] Among them, the point update map is a display image of the breeding area with target points and the number of target objects.

[0084] A4, counting the predicted quantity and the identified quantity in the point update map to obtain the total collection quantity corresponding to the breeding area.

[0085] It can be understood that the total collection quantity is the total number of collection targets, that is, the sum of the predicted quantity and the recognized quantity in the point update map.

[0086] Through the above implementation, the present invention can determine the total number of target objects in the breeding area, so as to subsequently calculate the number of carrying target objects, thereby reducing the time for repeatedly taking the carrying objects for breeding.

[0087] A5, obtaining the standard carrying quantity of the target carrier, obtaining the carrying quantity of the target carrier according to the ratio of the total collection quantity to the standard carrying quantity, and sending the carrying quantity to the breeding end.

[0088] It can be understood that the target carrier is an item that holds the target object, such as a basket or box for holding eggs. The standard carrying quantity is the quantity that the target carrier can hold. For example, a basket can hold 50 eggs, and the corresponding standard carrying quantity is 50. The carrying quantity is the number of target carriers required to collect the target objects in the breeding area, that is, the ratio of the total collection quantity to the standard carrying quantity. For example, when the total collection quantity in the breeding area is counted as 120 eggs, the carrying quantity can be calculated as 3.

[0089] It is not difficult to understand that when calculating the ratio of the total collection quantity and the standard carrying quantity, the ratio result needs to be rounded up so that the remaining target objects that are not enough to fill a target carrying object can be dropped. For example, when there are 120 eggs, two baskets can carry 100, then you need to carry another one in order to collect the remaining 20.

[0090] S4, generating a dynamic collection path and a dynamic recovery path according to the positioning information of the breeding end and the target point, and sending the dynamic collection path and the dynamic recovery path to the breeding end.

[0091] It should be noted that since there are many target points in the breeding area and their distribution is relatively messy, in order to reduce the collection time of breeding personnel, the positioning information of the breeding end can be obtained, and the target points can be reasonably sorted to generate dynamic collection paths and dynamic recovery paths, so as to guide breeding personnel to complete the collection of target objects with a shorter path and reduce the time for personnel to walk and collect.

[0092] It can be understood that the positioning information is the geographical location information corresponding to the positioning of the breeding end, the dynamic collection path is the walking path for collecting the target objects, and the dynamic recovery path is the walking path for recovering the collected target objects.

[0093] In some embodiments, the specific implementation of step S4 (generating a dynamic collection path and a dynamic recovery path according to the positioning information of the breeding end and the target point, and sending the dynamic collection path and the dynamic recovery path to the breeding end) includes: S41, obtaining the positioning information of the breeding end as the starting point, updating the starting point to the point update map, and obtaining a path planning map.

[0094] It can be understood that the location point corresponding to the customized information of the breeding end is used as the starting point, so that the corresponding starting point can be updated in the point update map to obtain the path planning map, so as to facilitate the subsequent generation of the corresponding dynamic collection path and dynamic recovery path according to the path planning map.

[0095] The starting point is the location point where collection starts, and the path planning map is a map image with point information for path planning.

[0096] S42, counting the target points in the path planning map to obtain a set of target points corresponding to the path planning map.

[0097] It is understandable that each target point is statistically aggregated so that each position point in the target point set can be subsequently sorted, thereby generating a reasonable collection path and reducing the time for personnel to collect the target object.

[0098] The target point set is a set containing the coordinates of each target point.

[0099] S43: Generate a dynamic collection path and a collection direction in the dynamic collection path according to the starting point and the target point set.

[0100] It can be understood that the starting point and the target point are arranged and connected to generate a corresponding dynamic collection path and the collection direction of the path walking, so that they can be sent to the breeding end later to guide personnel to collect and reduce personnel path planning time. At the same time, it can also reduce the risk of missing the target object at the target point.

[0101] The collection direction is the walking direction that guides personnel to collect target objects.

[0102] In some embodiments, the specific implementation of step S43 (generating a dynamic acquisition path and an acquisition direction in the dynamic acquisition path according to the starting point and the target point set) includes: S431, determining a target point in the target point set that is closest to the starting point as a connecting point, connecting the starting point in the path planning graph with the connecting point, and obtaining a sub-collection path.

[0103] It is understandable that the target point closest to the breeder is determined as the connection point so as to be connected with the starting point to obtain the sub-collection path and guide the person to the location to be reached next.

[0104] The connection point is the target point closest to the starting point, and the sub-collection path is the line segment path between the starting point and the connection point.

[0105] S432: taking a direction from the starting point to the connection point along the sub-collection path as a collection direction.

[0106] It can be understood that the acquisition direction is the direction from the starting point to the connection point along the sub-acquisition path.

[0107] Through the above implementation, the collection direction can be obtained and displayed in the corresponding path planning map, so that subsequent personnel can clearly understand the direction of their own walking path, which is convenient for collecting target objects.

[0108] S433, deleting the connection point in the target point set, and taking the connection point as the current starting point.

[0109] It can be understood that the connection point that has been determined to be connected in the target point set is deleted, and the connection point is used as the current starting point, so that the target point closest to the current starting point can be selected from the target point set for connection, so as to realize the planned connection of all target points and obtain a dynamic collection path for subsequent guidance and prompts to the breeding personnel.

[0110] S434, repeat the above steps until the target point set is an empty set, and generate a dynamic acquisition path.

[0111] It can be understood that the above steps of generating sub-collection paths, collection directions and determining the current starting point are repeated until all target points in the target point set are connected, thereby obtaining a dynamic collection path for subsequent path reference for the collection of target objects by the breeders.

[0112] S44, based on the collection direction, the cumulative number of target objects corresponding to the target points in the dynamic collection path is counted in sequence, until the cumulative number is greater than or equal to the standard carrying capacity, and the corresponding target point is used as a recovery point.

[0113] It can be understood that the number of target objects at the target points in the dynamic collection path can be accumulated in sequence according to the collection direction to obtain the cumulative number. When the cumulative number is greater than or equal to the standard carrying number, it means that the first target carrying object is full. Therefore, the corresponding target carrying object filled with target objects needs to be placed at this position so that it can be recovered and taken away when returning later.

[0114] Among them, the cumulative number is the number obtained by accumulating the number of target objects corresponding to the target points in the dynamic collection path along the collection direction, and the recovery point is the target point corresponding to the cumulative number greater than or equal to the standard carrying capacity.

[0115] For example, Figure 2 As shown, when the number of target points in the dynamic collection path is determined to be 10, 5, 6, 3, 4, 8, and 12 along the collection direction (the direction pointed by the arrow), and the standard carrying capacity of each target carrier is 20, then when 10, 5, and 6 are accumulated in sequence, it is determined that the cumulative number when reaching the third target point is 21, which is greater than the standard carrying capacity of 20, and the third target point can be used as a recovery point.

[0116] S45: Determine the end point in the dynamic collection path as a return point based on the collection direction.

[0117] It can be understood that the return point is the position point where the target object is collected and returned, that is, the end point in the dynamic collection path determined along the collection direction.

[0118] S46, counting the recycling points in the path planning map to obtain a set of recycling points corresponding to the path planning map.

[0119] It is understandable that the recycling points in the path planning map are counted to obtain a recycling point set, and then a dynamic recycling path can be generated based on the recycling point set to improve the return efficiency of the breeders and save time.

[0120] The collection point set is a set of geographical coordinates corresponding to the collection points.

[0121] S47, generating a dynamic recovery path according to the return point and the recovery point set.

[0122] It can be understood that the return points and recycling points are arranged and connected to generate a corresponding dynamic recovery path so that the breeders who collect the target objects can quickly walk to the recovery point and recycle the target carrier filled with the target objects. Through the guidance of the dynamic recovery path, the planning time for personnel to determine the recovery path is reduced.

[0123] In some embodiments, a specific implementation of step S47 (generating a dynamic recovery path according to the return point and the recovery point set) includes: S471, determining the recycling point in the recycling point set that is closest to the return point as a connection point, connecting the return point in the path planning graph with the connection point, and obtaining a sub-recycling path.

[0124] It is understandable that in order to generate a more suitable recovery path and reduce the walking time of personnel, the recovery point closest to the return point where the breeder is located can be selected from the recovery point set as the location point for the next person to go to, so as to avoid people walking in other directions and increase the length of the walking path.

[0125] Among them, the connection point is the recycling point in the recycling point set that is closest to the return point, and the sub-recycling path is a line segment path formed by connecting the return point and the connection point.

[0126] S472: The direction from the return point to the connection point along the sub-recovery path is used as the recovery direction.

[0127] It can be understood that the recovery direction is the direction of the return path of the recovery target object, that is, the direction from the return point to the connection point along the sub-recovery path.

[0128] S473, deleting the connection point in the recovery point set, and using the connection point as the current return point.

[0129] It is understandable that the connection point in the recovery point set is deleted to avoid the subsequent reselection of the point, and the connection point is used as the current return point so that it can be connected with the new connection point determined in the current recovery point set to generate the corresponding sub-recovery path.

[0130] S474, repeat the above steps until the collection point set is an empty set, and then generate a dynamic collection path.

[0131] It can be understood that by repeating the above-mentioned implementation steps of determining the sub-recovery path, the recovery direction and generating the current return point until the recovery point set is an empty set, it can be said that all the recovery points in the recovery point set have been connected, and a dynamic recovery path has been obtained, so that it can be sent to the breeding end later to facilitate the breeding personnel to refer to the path.

[0132] It is not difficult to understand that when personnel return with reference to the dynamic recovery path, after reaching the last recovery point, personnel can decide the walking path by themselves, or they can take the first point in the dynamic collection path as the final recovery point, thereby connecting the last point in the dynamic recovery path with the final recovery point, so that subsequent personnel can return to the place where they first started to collect the target objects.

[0133] S48, sending the dynamic collection path and the dynamic recovery path in the path planning diagram to the breeding end.

[0134] It can be understood that the dynamic collection path and dynamic recovery path in the path planning map are sent to the breeding end for the convenience of the breeding personnel to view, so as to guide the personnel to refer to the path to collect and recover the target objects, reduce the walking path of the breeding personnel, and improve the collection efficiency.

[0135] It should be noted that when personnel judge whether the target object is fertilized, the traditional method is to manually illuminate the target object with a flashlight one by one, and check whether there are bloodshot and other substances before the fertilization status of the target object such as eggs can be determined. This will greatly increase the selection time. Therefore, in order to reduce the time for checking fertilized eggs, a preliminary judgment can be made from the initial positioning information of the poultry. For example, the fertilization status can be judged by the position overlap and overlap time of the positioning information of different positioning devices of roosters and hens, so as to reduce the subsequent time for egg selection. Therefore, in some embodiments, it also includes: B1, retrieve the attribute information corresponding to the breeding positioning device, and divide the breeding positioning device into a first positioning device and a second positioning device based on the attribute information.

[0136] It can be understood that the attribute information is the male and female attributes corresponding to the poultry, so the breeding positioning device can be divided into a first positioning device and a second positioning device according to the male and female information in the attribute information, so that the corresponding positioning information can be obtained according to the distinguished first positioning device and second positioning device to judge the fertilization situation.

[0137] Among them, the first positioning device is a breeding positioning device installed correspondingly on female poultry, and the second positioning device is a breeding positioning device installed correspondingly on male poultry.

[0138] B2. Acquire first location information of the first positioning device and second location information of the second positioning device.

[0139] It can be understood that the first position information is the position coordinate information obtained by the first positioning device, and the second position information is the position coordinate information obtained by the second positioning device.

[0140] Through the above implementation, the present invention can obtain the first position information and the second position information, so that the fertilization status of the poultry can be determined according to the overlap of the first position information and the second position information.

[0141] B3: When it is determined that the first location information and the second location information are at the same location point, the corresponding location point is used as an interaction point.

[0142] It can be understood that when the first position information and the second position information are the same, it can be explained that fertilization may occur between the two male and female poultry at the position point, and therefore, the corresponding position point can be used as an interaction point.

[0143] The interactive point is a point where the first position information and the second position information are the same.

[0144] B4, counting the linkage time when the first positioning device and the second positioning device stay at the interaction point at the same time, and when it is determined that the linkage time is greater than or equal to the preset interaction time, the first positioning device at the corresponding interaction point is used as the third positioning device, and the current time is used as the classification time.

[0145] It can be understood that the linkage duration is the duration during which the first positioning device and the second positioning device simultaneously stay at the interaction point, and the preset interaction duration is a preset reference duration, which can be manually preset.

[0146] It is not difficult to understand that when the linkage time is less than the preset interaction time, the corresponding female poultry may only have a short-term position overlap in the activity path. When the linkage time is greater than or equal to the preset interaction time, it can be said that male and female poultry may be fertilized. Therefore, the first positioning device at the corresponding interaction point can be used as the third positioning device, and the current moment can be used as the classification moment, so that the position of the fertilized target object can be determined later according to the classification moment.

[0147] Among them, the third positioning device is the first positioning device at the interaction point when the linkage time is greater than or equal to the preset interaction time, that is, the breeding positioning device installed on the female poultry, and the classification time is the time to distinguish whether the target object is fertilized or not, that is, to determine the current time corresponding to when the linkage time is greater than or equal to the preset interaction time.

[0148] B5, taking the classification time as the starting time, and sequentially counting the target points passed by the third positioning device based on the preset classification time as the target object selection points.

[0149] It is understandable that in order to determine the location where the hen lays the fertilized eggs, the classification time can be used as the starting time. Within a certain period of time, the first egg laid may be a fertilized egg. Therefore, the target points passed by the hen within the preset classification time can be counted, which means that the eggs at the corresponding target points are more likely to be fertilized eggs, thereby increasing the probability of selecting fertilized eggs and reducing manual selection time.

[0150] Among them, the preset classification time is a pre-set time for distinguishing fertilized targets, such as 24 hours, that is, eggs laid by hens within 24 hours may be fertilized eggs, and the target object selection point is the location point where the target object is located, that is, the target point passed by the third positioning device within the preset classification time, for example, the location where the fertilized eggs may be.

[0151] See also Figure 3 , is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, the electronic device 30 includes: a processor 31, a memory 32 and a computer program; wherein The memory 32 is used to store the computer program, which may also be a flash memory. The computer program is, for example, an application program, a functional module, etc. for implementing the above method.

[0152] The processor 31 is used to execute the computer program stored in the memory to implement each step performed by the device in the above method. For details, please refer to the relevant description in the above method embodiment.

[0153] Optionally, the memory 32 may be independent or integrated with the processor 31 .

[0154] When the memory 32 is a device independent of the processor 31, the device may further include: The bus 33 is used to connect the memory 32 and the processor 31 .

[0155] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0156] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist in a communication device as discrete components. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0157] The present invention also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0158] In the embodiments of the above-mentioned devices, 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), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent processing of aquaculture data, characterized in that: include: Acquire the shielded area and the open area in the breeding area, control the mobile collection device to inspect the open area, and obtain the area inspection data corresponding to the open area; Identify the target object in the area inspection data, obtain the identification point of the target object, and use the identification point as the target point of the open area; Acquire the location information of the breeding positioning device, and when it is determined that the location information is in the shielded area, use the corresponding location information as the stay position, and determine the target point of the shielded area according to the stay time of the stay position; A dynamic collection path and a dynamic recovery path are generated according to the positioning information of the breeding end and the target point, and the dynamic collection path and the dynamic recovery path are sent to the breeding end.

2. The method according to claim 1, characterized in that The identifying the target object in the area inspection data, obtaining the identification point of the target object, and using the identification point as the target point of the open area includes: Identify the target object in the area inspection data, obtain the position information of the target object as an identification point, and use the identification point as the target point of the open area.

3. The method according to claim 2, characterized in that The method of obtaining the position information of the breeding positioning device and determining that the position information is in the shielded area uses the corresponding position information as the stay position, and determines the target point of the shielded area according to the stay time of the stay position, including: Acquire the position information of the breeding positioning device, and when it is determined that the position information is in the shielded area, use the corresponding position information as the stay position; Retrieving multiple stay time periods corresponding to each of the stay locations, and obtaining the duration of each of the stay time periods as the stay duration; When it is determined that the stay duration is greater than or equal to the preset stay duration, the corresponding stay duration is used as the stay duration, and the stay location with the stay duration is used as the point to be verified; Receive verification information of the point to be verified from the breeding end, and determine the corresponding point to be verified as the target point of the shielded area based on the verification information, as well as the verified number of targets at the target point of the shielded area.

4. The method according to claim 3, characterized in that Also includes: Retrieving an open target image corresponding to the target point in the open area in the area inspection data, identifying a closed contour of the target object in the open target image based on OpenCV, and determining the number of identified target points in the open area according to the closed contour; According to the verified number of target points in the shielded area and the length of stay, a prediction ratio is obtained, and a collection interval period corresponding to the target points in the shielded area is obtained, and based on the prediction ratio and the collection interval period, a predicted number of target points in the shielded area is obtained; The target point of the open area and the target point of the shielded area are updated to the breeding area, and the identified number is updated to the target point of the corresponding open area, and the predicted number is updated to the target point of the corresponding shielded area, to generate a point update map; Counting the predicted quantity and the identified quantity in the point update map to obtain the total collection quantity corresponding to the breeding area; The standard carrying quantity of the target carrier is obtained, and the carrying quantity of the target carrier is obtained according to the ratio of the total collection quantity to the standard carrying quantity, and the carrying quantity is sent to the breeding end.

5. The method according to claim 4, characterized in that The method of identifying the closed contour of the target object in the open target image based on OpenCV, and determining the number of target points in the open area according to the closed contour, includes: Based on OpenCV, a closed contour of a target object in the open target image is identified, and a target pixel value of the target object is retrieved, and a binarization process is performed on the open target image based on the target pixel value to obtain a quantity recognition image; The number of contours with black pixels in the closed contours in the number recognition image is counted to obtain the number of target points in the open area.

6. The method according to claim 4, characterized in that The method of obtaining a prediction ratio according to the verified number of target points in the shielded area and the length of stay, and obtaining a collection interval corresponding to the target points in the shielded area, and obtaining a predicted number of target points in the shielded area based on the prediction ratio and the collection interval, includes: Counting the duration of stay of the target point in the shielded area to obtain the historical cumulative duration corresponding to the target point in the shielded area; According to the ratio of the verification quantity to the historical cumulative duration, a prediction ratio is obtained, and a current collection interval corresponding to the target point in the shielded area is obtained; Obtain the current accumulated duration corresponding to the target point of the shielded area within the current collection interval; Based on the product of the current cumulative time and the predicted ratio, the predicted number of target points in the shielded area is obtained.

7. The method according to claim 4, characterized in that The generating a dynamic collection path and a dynamic recovery path according to the positioning information of the breeding end and the target point, and sending the dynamic collection path and the dynamic recovery path to the breeding end, comprises: Acquire the positioning information of the breeding end as the starting point, update the starting point to the point update map, and obtain a path planning map; Counting the target points in the path planning map to obtain a set of target points corresponding to the path planning map; Generate a dynamic collection path and a collection direction in the dynamic collection path according to the starting point and the target point set; The cumulative number of target objects corresponding to the target points in the dynamic collection path is counted sequentially based on the collection direction until the cumulative number is greater than or equal to the standard carrying capacity, and the corresponding target points are used as recycling points; Determine the end point in the dynamic collection path as the return point based on the collection direction; Counting the recycling points in the path planning graph to obtain a set of recycling points corresponding to the path planning graph; Generate a dynamic recovery path according to the return point and the recovery point set; The dynamic collection path and the dynamic recovery path in the path planning diagram are sent to the breeding end.

8. The method according to claim 7, characterized in that The step of generating a dynamic acquisition path and an acquisition direction in the dynamic acquisition path according to the starting point and the target point set includes: Determine a target point in the target point set that is closest to the starting point as a connecting point, connect the starting point in the path planning graph with the connecting point, and obtain a sub-collection path; The direction from the starting point to the connection point along the sub-collection path is used as the collection direction; Deleting the connection point in the target point set and using the connection point as the current starting point; Repeat the above steps until the target point set is an empty set, and then generate a dynamic acquisition path.

9. The method according to claim 7, characterized in that: The generating a dynamic recovery path according to the return point and the recovery point set includes: Determine a recycling point in the recycling point set that is closest to the return point as a connection point, connect the return point in the path planning graph with the connection point, and obtain a sub-recycling path; The direction from the return point to the connection point along the sub-recovery path is used as the recovery direction; Deleting the connection point in the collection point set, and using the connection point as the current return point; Repeat the above steps until the collection point set is an empty set, and then generate a dynamic collection path.

10. The method according to claim 3, characterized in that Also includes: Retrieving attribute information corresponding to the breeding positioning device, and dividing the breeding positioning device into a first positioning device and a second positioning device based on the attribute information; Acquire first location information of the first positioning device and second location information of the second positioning device; When it is determined that the first location information and the second location information are at the same location point, the corresponding location point is used as an interaction point; Counting the linkage time duration when the first positioning device and the second positioning device stay at the interaction point at the same time, and when it is determined that the linkage time duration is greater than or equal to the preset interaction time duration, using the first positioning device at the corresponding interaction point as the third positioning device, and using the current time as the classification time; Taking the classification time as the starting time, the target points passed by the third positioning device are sequentially counted based on the preset classification time as the target object selection points.

Images