Laying hen breeding productivity model and prediction method and system

Abstract

The invention provides a laying hen breeding productivity model and a prediction method, and belongs to the technical field of breeding, and the method comprises the steps: training a productivity evaluation model through employing a laying hen breeding income training set, and determining an egg pre-purchase price interval through employing the trained productivity evaluation model. The method has the technical effects that the farmers can sell multiple eggs in the future can be accurately evaluated, so that the farmers can have more intuitive understanding of their expected income in the process of capacity transaction with financial individuals, and the fund pressure of the farmers can be further reduced. The invention also provides a laying hen breeding productivity model and a prediction system.

Description

Technical Field

[0001] The present application relates to the field of breeding technology, and in particular to a laying hen breeding capacity model and prediction method and system. Background Art

[0002] Regarding capacity trading, that is, trading of product output (or inventory) within a certain period of time in the future, that is, forward contract trading, taking the egg industry as an example, farmers can sell the egg output of the next 180 days in advance through forward contracts when they first purchase chicks. This move can not only obtain payment in advance for purchasing production materials such as feed, effectively alleviating the pressure of capital turnover, but also further improve the efficiency and level of breeding. This is the core significance of the capacity trading model.

[0003] In the egg production capacity transaction, the sellers are farmers, while the buyers include listed companies, supply guarantee units, and corporate purchasing personnel. In order to ensure that farmers can fulfill forward contracts, a method to evaluate and confirm farmers' future production capacity through scientific production capacity models and algorithms is urgently needed. Summary of the invention

[0004] The embodiments of the present application provide a laying hen farming capacity model and prediction method and system to improve the above-mentioned problems.

[0005] In order to achieve the above purpose, this application adopts the following technical solutions: In a first aspect, the present application embodiment proposes a laying hen breeding capacity model and prediction method, characterized in that the method comprises: Obtaining a training set of laying hen breeding benefits, and training a capacity assessment model based on the training set of laying hen breeding benefits, the capacity assessment model is used to assess the predicted egg production benefits of laying hens after a preset time, wherein the training set of laying hen breeding benefits includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, benefit time, and egg production benefits; Obtain existing laying hen breeding data and target time, where the target time is the time when the output needs to be predicted. The existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites; Import the existing laying hen breeding data and target time into the capacity assessment model, and determine the target egg production benefit according to the predicted egg production benefit output by the capacity assessment model. The target egg production benefit is the egg production benefit at the target time. Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit; Determine the pre-purchase price range for eggs based on the maximum and minimum egg production benefits.

[0006] In combination with the first aspect, in some embodiments, a laying hen breeding income training set is obtained, and a production capacity assessment model is trained based on the laying hen breeding income training set, and the production capacity assessment model is used to evaluate the egg production income of laying hens after a preset time, wherein the laying hen breeding income training set includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, income time, and egg production income, including: A validation set is obtained based on the egg-laying chicken farming income training set, and the production capacity assessment model is verified based on the validation set. According to the verification result, it is determined whether the training process is completed.

[0007] In combination with the first aspect, in some implementations, obtaining a validation set based on a laying hen farming income training set, validating the production capacity assessment model based on the validation set, and determining whether the training process is completed based on the validation result, including: Extract some data from the laying hen breeding income training set as the validation set; Import the validation set into the evaluation model and obtain the verified egg production benefits output by the evaluation model; The verified egg production benefits are compared with the egg production benefits in the verification set, and the verification results are determined based on the comparison results.

[0008] In combination with the first aspect, in some embodiments, comparing the verified egg production income with the egg production income in the verification set, and determining the verification result according to the comparison result, includes: Compare the verified egg production income with the egg production income in the verification set. If the verified egg production income is greater than the egg production income in the verification set, obtain the error value. The error value T satisfies: T=( - )

[0009] If the verified egg production benefit is less than the egg production benefit in the verification set, the error value is obtained, and the error value T satisfies: T=( - )

[0010] in, To verify egg production, To verify the egg production gains in the set.

[0011] In combination with the first aspect, in some embodiments, comparing the verified egg production income with the egg production income in the verification set, and determining the verification result according to the comparison result, includes: The error value is compared with the preset value. If the error value is less than the preset value, the verification is determined to be successful and the training process of the capacity assessment model is stopped.

[0012] In combination with the first aspect, in some embodiments, based on the target egg production benefit, determining the maximum egg production benefit and the minimum egg production benefit includes: Obtain the verified egg production benefits outputted multiple times by the production capacity assessment model when the error value is greater than the predicted value during the training process of the production capacity assessment model; The floating parameter d is determined based on multiple verified egg production benefits, and the floating parameter d satisfies: ; Among them, n is the number of iterations in the validation set iteration process, and x is the predicted egg production benefit; The predicted egg production benefit output by the capacity assessment model is obtained, and the maximum egg production benefit and the minimum egg production benefit are determined based on the predicted egg production benefit and the floating parameters, and the following conditions are met: ; ; in, is the minimum egg production benefit, For maximum egg production benefit.

[0013] In combination with the first aspect, in some embodiments, existing laying hen breeding data and a target time are obtained, where the target time is the time when the output needs to be predicted, and the existing laying hen breeding data includes the perceived feed intake, perceived behavior characteristic data, and perceived chicken house environment data obtained from the existing laying hen breeding site, including: Obtain existing laying hen farming data, where the perception behavior characteristic data includes: Acquire a first chicken farm image at a first moment, and identify a plurality of breeding individual images from the first chicken farm image based on image recognition technology; Determine the posture data of each visible farmed individual based on the farmed individual image, assign a separate identification to each farmed individual and keep tracking it; The posture data of each breeding individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result.

[0014] In combination with the first aspect, in some embodiments, the posture data of the farmed individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result, including: Acquire a posture data evaluation model, import the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model, and determine the perception behavior characteristic data according to the result output by the posture data evaluation model, wherein the posture data of the farmed individual includes the head-to-body ratio of the farmed individual, the moving speed of the farmed individual, and the number of up and down movements of the head of the farmed individual per unit time.

[0015] In conjunction with the first aspect, in some implementations, obtaining a posture data evaluation model, and importing the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model include: The posture data evaluation model is trained based on historical data to obtain a trained posture data evaluation model.

[0016] In a second aspect, the present application embodiment proposes a laying hen breeding capacity model and prediction system, which is configured as follows: Obtaining a training set of laying hen breeding benefits, and training a capacity assessment model based on the training set of laying hen breeding benefits, the capacity assessment model is used to assess the predicted egg production benefits of laying hens after a preset time, wherein the training set of laying hen breeding benefits includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, benefit time, and egg production benefits; Obtain existing laying hen breeding data and target time, where the target time is the time when the output needs to be predicted. The existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites; Import the existing laying hen breeding data and target time into the capacity assessment model, and determine the target egg production benefit according to the predicted egg production benefit output by the capacity assessment model. The target egg production benefit is the egg production benefit at the target time. Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit; Determine the pre-purchase price range for eggs based on the maximum and minimum egg production benefits.

[0017] In conjunction with the second aspect, in some embodiments, the system is configured as follows: A training set of laying hen breeding benefits is obtained, and a capacity assessment model is trained based on the training set of laying hen breeding benefits. The capacity assessment model is used to assess the predicted egg production benefits of laying hens after a preset time. The training set of laying hen breeding benefits includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, benefit time, and egg production benefits, including: A validation set is obtained based on the egg-laying chicken farming income training set, and the production capacity assessment model is verified based on the validation set. According to the verification result, it is determined whether the training process is completed.

[0018] In conjunction with the second aspect, in some embodiments, the system is configured as follows: A validation set is obtained based on the egg-laying chicken farming income training set, and the capacity assessment model is verified based on the validation set. According to the verification result, it is determined whether the training process is completed, including: Extract some data from the laying hen breeding income training set as the validation set; Import the validation set into the evaluation model and obtain the verified egg production benefits output by the evaluation model; The verified egg production benefits are compared with the egg production benefits in the verification set, and the verification results are determined based on the comparison results.

[0019] In conjunction with the second aspect, in some embodiments, the system is configured as follows: Compare the verified egg production benefits with the egg production benefits in the verification set, and determine the verification results based on the comparison results, including: Compare the verified egg production income with the egg production income in the verification set. If the verified egg production income is greater than the egg production income in the verification set, obtain the error value. The error value T satisfies: T=( - )

[0020] If the verified egg production benefit is less than the egg production benefit in the verification set, the error value is obtained, and the error value T satisfies: T=( - )

[0021] in, To verify egg production, To verify the egg production gains in the set.

[0022] In conjunction with the second aspect, in some embodiments, the system is configured as follows: Compare the verified egg production benefits with the egg production benefits in the verification set, and determine the verification results based on the comparison results, including: The error value is compared with the preset value. If the error value is less than the preset value, the verification is determined to be successful and the training process of the capacity assessment model is stopped.

[0023] In conjunction with the second aspect, in some embodiments, the system is configured as follows: Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit, including: Obtain the verified egg production benefits outputted multiple times by the production capacity assessment model when the error value is greater than the predicted value during the training process of the production capacity assessment model; The floating parameter d is determined based on multiple verified egg production benefits, and the floating parameter d satisfies: ; Among them, n is the number of iterations in the validation set iteration process, and x is the predicted egg production benefit; The predicted egg production benefit output by the capacity assessment model is obtained, and the maximum egg production benefit and the minimum egg production benefit are determined based on the predicted egg production benefit and the floating parameters, and the following conditions are met: ; ; in, is the minimum egg production benefit, For maximum egg production benefit.

[0024] In conjunction with the second aspect, in some embodiments, the system is configured as follows: Obtain existing laying hen breeding data and target time. The target time is the time when the output needs to be predicted. The existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristics data and perceived chicken house environment data obtained from the existing laying hen breeding sites, including: Obtain existing laying hen farming data, where the perception behavior characteristic data includes: Acquire a first chicken farm image at a first moment, and identify a plurality of breeding individual images from the first chicken farm image based on image recognition technology; Determine the posture data of each visible farmed individual based on the farmed individual image, assign a separate identification to each farmed individual and keep tracking it; The posture data of each breeding individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result.

[0025] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The posture data of the breeding individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result, including: Acquire a posture data evaluation model, import the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model, and determine the perception behavior characteristic data according to the result output by the posture data evaluation model, wherein the posture data of the farmed individual includes the head-to-body ratio of the farmed individual, the moving speed of the farmed individual, and the number of up and down movements of the head of the farmed individual per unit time.

[0026] In conjunction with the second aspect, in some embodiments, the system is configured as follows: Obtaining a posture data evaluation model, importing the posture data at the first moment and the posture data of the breeding individual at the second moment into the posture data evaluation model, including: The posture data evaluation model is trained based on historical data to obtain a trained posture data evaluation model.

[0027] A third aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in the first aspect of the embodiment of the present invention.

[0028] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the embodiment of the present invention.

[0029] In summary, the above method and device have the following technical effects: The present application proposes a laying hen farming capacity model and prediction method. By obtaining a laying hen farming income training set and training a capacity assessment model, the trained capacity assessment model can be used to more accurately assess how many eggs a farmer can sell in the future. This allows farmers to have a more intuitive understanding of their expected returns during capacity transactions with financial individuals, which can further reduce the financial pressure on farmers. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic flow chart of a laying hen farming capacity model and prediction method proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0032] This application embodiment proposes a laying hen breeding capacity model and prediction method. Figure 1 ,,the method comprises the following steps: S101: Obtain a training set for laying hen farming income, and train a capacity assessment model based on the laying hen farming income training set. The capacity assessment model is used to evaluate the egg production income of laying hens after a preset time, wherein the laying hen farming income training set includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, income time, and egg production income.

[0033] The core of capacity trading is that when farmers buy chicks, they can sell eggs produced 180 days in the future in advance, and use the money from eggs to buy feed in advance, solve the shortage of funds, and improve the level of breeding. How to prove that farmers can sell so many eggs in the future depends on collecting data from sensing devices (hardware) and using capacity models including algorithms to determine farmers' future capacity, that is, how many eggs they can sell. Therefore, in this embodiment, In order to accurately evaluate the economic benefits of laying hen farming, it is first necessary to collect and organize a detailed training set of laying hen farming benefits. This training set will contain a series of key data so that an efficient capacity evaluation model can be trained. Specifically, this training set will include data in the following aspects: Feed intake data: This part of the data will record the feed intake of laying hens in different time periods, thus helping to understand their eating habits and feeding patterns. This data is crucial for evaluating the health status and production performance of laying hens.

[0034] Perceived behavioral characteristic data: By collecting daily behavioral characteristic data of laying hens, we can better understand their activity patterns and behavior patterns. These data include but are not limited to the frequency of movement, standing time, rest time, etc. of laying hens. These behavioral characteristics help to assess the health status and production potential of laying hens.

[0035] Perceiving chicken house environmental data: In order to ensure that laying hens grow in a suitable environment, it is necessary to collect environmental data in the chicken house, such as temperature, humidity, light intensity, air quality, etc. These environmental factors directly affect the growth and egg-laying performance of laying hens, so their importance in the training set is self-evident.

[0036] Revenue time data: This part of the data will record the time span from the beginning of laying hens to laying eggs, as well as the egg-laying situation in different time periods. By analyzing this data, the growth rate and egg-laying cycle of laying hens can be evaluated, thereby more accurately predicting future revenue.

[0037] Egg production and profit data: This is the core data of the training set, which records the actual number and quality of eggs laid by laying hens in different time periods, as well as the economic benefits brought about by them. By analyzing these data, the production performance and breeding benefits of laying hens can be evaluated.

[0038] Based on the above detailed training set of laying hen farming income, the capacity assessment model will be trained. This model will use machine learning algorithms to learn the production rules and income patterns of laying hens by analyzing the data in the training set. Ultimately, the model will be able to predict the predicted egg production income of laying hens after a preset time. In this way, farmers can understand the future income in advance, so as to make more informed farming decisions, optimize farming strategies, and improve economic benefits.

[0039] As an implementation method, in order to ensure the accuracy of the results, a verification set can be obtained based on the laying hen farming income training set, and the production capacity assessment model can be verified based on the verification set. According to the verification results, it is determined whether the training process is completed.

[0040] Specifically, first, some data can be extracted from the laying hen farming income training set as a verification set, and then the verification set can be imported into the evaluation model, and the verified egg production income output by the evaluation model can be obtained, and then the verified egg production income is compared with the egg production income in the verification set, and the verification result is determined according to the comparison result.

[0041] In this process, in order to avoid the problem of overfitting, the training process of the neural network can be stopped by determining the error value. In this embodiment, the verified egg production income is compared with the egg production income in the verification set. If the verified egg production income is greater than the egg production income in the verification set, the error value is obtained, and the error value T satisfies: T=( - )

[0042] If the verified egg production benefit is less than the egg production benefit in the verification set, the error value is obtained, and the error value T satisfies: T=( - )

[0043] in, To verify egg production, To verify the egg production gains in the set.

[0044] By comparing the error value with a preset value, if the error value is less than the preset value, it can be determined that the verification is successful and the training process of the capacity assessment model is stopped.

[0045] S102: Obtain existing laying hen breeding data and target time, where the target time is the time when the output needs to be predicted. The existing laying hen breeding data includes perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites.

[0046] In order to make a laying hen production forecast, it is necessary to collect and analyze relevant data on current laying hen farming. This data includes various information obtained from existing laying hen farms. First, it is necessary to understand the target time, that is, the specific time point or time period when you want to predict the production. This target time is a reference point for prediction and helps determine when the production forecast results need to be obtained.

[0047] Next, it is necessary to collect various data from existing laying hen farms in detail. First, it is crucial to perceive the feed intake data, which records the feeding behavior and feed intake of laying hens in different time periods. By analyzing this data, we can understand the eating habits and feeding patterns of laying hens, and thus infer the factors that may affect production.

[0048] Secondly, it is also essential to perceive behavioral characteristic data. These data include behavioral characteristics such as the activity frequency, activity range, and rest time of laying hens. By analyzing these behavioral characteristics, we can better understand the health status and production status of laying hens, and thus predict their future production performance.

[0049] As an implementation method, the perception behavior feature data can be performed through image sensing. Specifically, First, it is necessary to obtain existing laying hen farming data. Specifically, obtaining the perception behavior characteristic data includes the following steps: S201: Acquire a first chicken farm image at a first moment, and identify a plurality of images of breeding individuals from the first chicken farm image based on image recognition technology.

[0050] It is understandable that the image data from the first chicken farm is obtained at the first time, and these images are analyzed and processed using advanced image recognition technology. Through these technologies, we can identify and extract image information of multiple breeding individuals from the images of the first chicken farm.

[0051] S202: Determine the posture data of each visible farmed individual based on the farmed individual image, assign a separate identification to each farmed individual and continue tracking.

[0052] As can be understood, after identifying the images of these farmed individuals, the posture data of each visible farmed individual is further analyzed. In order to better manage and track these individuals, we assign a unique identifier to each farmed individual and continuously monitor and record its behavior.

[0053] S203: Acquire the posture data of each farmed individual at the second moment, and compare it with the posture data at the first moment, and determine the perception behavior data according to the comparison result.

[0054] Understandably, at the second moment, we obtain the posture data of each farmed individual again and compare it in detail with the posture data obtained at the first moment. Through this comparative analysis, we can accurately determine the perceptual behavior data of each farmed individual, so as to better understand their behavior patterns and health status.

[0055] Specifically, as an implementation method, a posture data evaluation model can be obtained, and the posture data at the first moment and the posture data of the farmed individual at the second moment are imported into the posture data evaluation model. According to the result output by the posture data evaluation model, the perceptual behavior characteristic data is determined, wherein the posture data of the farmed individual includes the head-to-body ratio of the farmed individual, the movement speed of the farmed individual, and the number of up and down movements of the head of the farmed individual per unit time. For the acquisition of the initial model, the posture data evaluation model can be trained based on historical data to obtain a trained posture data evaluation model, or data can be input manually, which is not limited here.

[0056] As for the perceived chicken house environmental data, these data cover environmental factors such as temperature, humidity, light intensity, ventilation, etc. in the chicken house. These environmental factors have a direct impact on the growth and egg production of laying hens. By monitoring and analyzing these environmental data, the breeding environment can be adjusted in time to optimize the production performance of laying hens.

[0057] In summary, by acquiring and analyzing the perceived feed intake data, perceived behavioral characteristics data, and perceived chicken house environment data of existing laying hen farms, a solid data foundation can be provided for laying hen production prediction. The comprehensive analysis of these data will help to more accurately predict the production at the target time, thereby providing a scientific basis for the production decision of the farm.

[0058] S103: Import the existing laying hen breeding data and the target time into the capacity assessment model, and determine the target egg production benefit based on the predicted egg production benefit output by the capacity assessment model. The target egg production benefit is the egg production benefit at the target time.

[0059] It is understandable that the existing laying hen breeding data and the set target time are input into the capacity assessment model, and the predicted egg production benefits can be obtained through the calculation and analysis of the model. Based on these predicted data, the target egg production benefits can be further determined, that is, the expected egg production benefits within the set target time.

[0060] S104: Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit.

[0061] As an implementation method, the maximum egg production benefit and the minimum egg production can be achieved in the following ways: Obtain the verified egg production benefits outputted multiple times by the production capacity assessment model when the error value is greater than the predicted value during the training process of the production capacity assessment model; The floating parameter d is determined based on multiple verified egg production benefits, and the floating parameter d satisfies: ; Among them, n is the number of iterations in the validation set iteration process, and x is the predicted egg production benefit; The predicted egg production benefit output by the capacity assessment model is obtained, and the maximum egg production benefit and the minimum egg production benefit are determined based on the predicted egg production benefit and the floating parameters, and the following conditions are met: ; ; in, is the minimum egg production benefit, For maximum egg production benefit.

[0062] S105: Determine the pre-purchase price range of eggs based on the maximum egg production profit and the minimum egg production profit.

[0063] It is understandable that by analyzing and comparing the maximum egg production benefits and the minimum egg production benefits, a reasonable pre-purchase price range for eggs can be determined. This price range will be set based on the maximum and minimum benefits of egg production to ensure that both buyers and sellers can obtain fair trading conditions. Specifically, the maximum egg production benefit refers to the highest benefit that egg producers can obtain under the best production conditions, while the minimum egg production benefit refers to the lowest benefit that producers can obtain under the most unfavorable conditions. By comprehensively considering these two factors, a price range can be set that can not only protect the interests of producers, but also meet the purchasing needs of consumers, thereby achieving market balance and stability.

[0064] The present application proposes a laying hen farming capacity model and prediction method. By obtaining a laying hen farming income training set and training a capacity assessment model, the trained capacity assessment model can be used to more accurately assess how many eggs a farmer can sell in the future. This allows farmers to have a more intuitive understanding of their expected returns during capacity transactions with financial individuals, which can further reduce the financial pressure on farmers.

[0065] Based on the same inventive concept, the embodiment of the present application also proposes a laying hen breeding capacity model and prediction system, which is configured as follows: Obtaining a training set of laying hen breeding benefits, and training a capacity assessment model based on the training set of laying hen breeding benefits, the capacity assessment model is used to assess the predicted egg production benefits of laying hens after a preset time, wherein the training set of laying hen breeding benefits includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, benefit time, and egg production benefits; Obtain existing laying hen breeding data and target time, where the target time is the time when the output needs to be predicted. The existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites; Import the existing laying hen breeding data and target time into the capacity assessment model, and determine the target egg production benefit according to the predicted egg production benefit output by the capacity assessment model. The target egg production benefit is the egg production benefit at the target time. Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit; Determine the pre-purchase price range for eggs based on the maximum and minimum egg production benefits.

[0066] In some embodiments, the system is configured to: A training set of laying hen breeding benefits is obtained, and a capacity assessment model is trained based on the training set of laying hen breeding benefits. The capacity assessment model is used to assess the predicted egg production benefits of laying hens after a preset time. The training set of laying hen breeding benefits includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, benefit time, and egg production benefits, including: A validation set is obtained based on the egg-laying chicken farming income training set, and the production capacity assessment model is verified based on the validation set. According to the verification result, it is determined whether the training process is completed.

[0067] In some embodiments, the system is configured to: A validation set is obtained based on the egg-laying chicken farming income training set, and the capacity assessment model is verified based on the validation set. According to the verification result, it is determined whether the training process is completed, including: Extract some data from the laying hen breeding income training set as the validation set; Import the validation set into the evaluation model and obtain the verified egg production benefits output by the evaluation model; The verified egg production benefits are compared with the egg production benefits in the verification set, and the verification results are determined based on the comparison results.

[0068] In some embodiments, the system is configured to: Compare the verified egg production benefits with the egg production benefits in the verification set, and determine the verification results based on the comparison results, including: Compare the verified egg production income with the egg production income in the verification set. If the verified egg production income is greater than the egg production income in the verification set, obtain the error value. The error value T satisfies: T=( - )

[0069] If the verified egg production benefit is less than the egg production benefit in the verification set, the error value is obtained, and the error value T satisfies: T=( - )

[0070] in, To verify egg production, To verify the egg production gains in the set.

[0071] In some embodiments, the system is configured to: Compare the verified egg production benefits with the egg production benefits in the verification set, and determine the verification results based on the comparison results, including: The error value is compared with the preset value. If the error value is less than the preset value, the verification is determined to be successful and the training process of the capacity assessment model is stopped.

[0072] In some embodiments, the system is configured to: Based on the target egg production benefit, determine the maximum egg production benefit and the minimum egg production benefit, including: Obtain the verified egg production benefits outputted multiple times by the production capacity assessment model when the error value is greater than the predicted value during the training process of the production capacity assessment model; The floating parameter d is determined based on multiple verified egg production benefits, and the floating parameter d satisfies: ; Among them, n is the number of iterations in the validation set iteration process, and x is the predicted egg production benefit; The predicted egg production benefit output by the capacity assessment model is obtained, and the maximum egg production benefit and the minimum egg production benefit are determined based on the predicted egg production benefit and the floating parameters, and the following conditions are met: ; ; in, is the minimum egg production benefit, For maximum egg production benefit.

[0073] In some embodiments, the system is configured to: Obtain existing laying hen breeding data and target time. The target time is the time when the output needs to be predicted. The existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristics data and perceived chicken house environment data obtained from the existing laying hen breeding sites, including: Obtain existing laying hen farming data, where the perception behavior characteristic data includes: Acquire a first chicken farm image at a first moment, and identify a plurality of breeding individual images from the first chicken farm image based on image recognition technology; Determine the posture data of each visible farmed individual based on the farmed individual image, assign a separate identification to each farmed individual and keep tracking it; The posture data of each breeding individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result.

[0074] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The posture data of the breeding individual at the second moment is obtained and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result, including: Acquire a posture data evaluation model, import the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model, and determine the perception behavior characteristic data according to the result output by the posture data evaluation model, wherein the posture data of the farmed individual includes the head-to-body ratio of the farmed individual, the moving speed of the farmed individual, and the number of up and down movements of the head of the farmed individual per unit time.

[0075] In some embodiments, the system is configured to: Obtaining a posture data evaluation model, importing the posture data at the first moment and the posture data of the breeding individual at the second moment into the posture data evaluation model, including: The posture data evaluation model is trained based on historical data to obtain a trained posture data evaluation model.

[0076] The present application proposes a laying hen farming capacity model and prediction system, which obtains a laying hen farming income training set and trains a capacity assessment model. The trained capacity assessment model can more accurately assess how many eggs a farmer can sell in the future, so that farmers can have a more intuitive understanding of their expected returns in the process of capacity transactions with financial individuals, which can further reduce the financial pressure on farmers.

[0077] Based on the same inventive concept, an embodiment of the present application further proposes an electronic device, the electronic device comprising: At least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the laying hen farming capacity model and prediction method of the embodiment of the present application.

[0078] In addition, to achieve the above-mentioned purpose, the embodiment of the present application also proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the egg-laying chicken farming capacity model and prediction method of the embodiment of the present application are implemented.

[0079] The following is a detailed introduction to the various components of electronic equipment: The processor is the control center of the electronic device, which can be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0080] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0081] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0082] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processor through an interface circuit of the electronic device, which is not specifically limited in the embodiments of the present invention.

[0083] A transceiver is used to communicate with a network device or a terminal device.

[0084] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0085] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0086] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, which will not be repeated here.

[0087] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0088] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0089] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0090] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0091] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0092] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes 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.

[0093] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. A laying hen breeding capacity model and prediction method, characterized in that: The method comprises: Acquire a training set of laying hen breeding income, and train a capacity assessment model based on the laying hen breeding income training set, wherein the capacity assessment model is used to assess the predicted egg production income of the laying hen after a preset time, wherein the laying hen breeding income training set includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, income time, and egg production income; Obtaining existing laying hen breeding data and a target time, wherein the target time is the time when the output needs to be predicted, and the existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites; Importing the existing laying hen breeding data and the target time into the production capacity assessment model, and determining the target egg production benefit according to the predicted egg production benefit output by the production capacity assessment model, wherein the target egg production benefit is the egg production benefit at the target time; Based on the target egg production benefit, determining a maximum egg production benefit and a minimum egg production benefit; The pre-purchase price range of eggs is determined based on the maximum egg production profit and the minimum egg production profit.

2. The laying hen breeding capacity model and prediction method according to claim 1, characterized in that: A layer-laying chicken breeding income training set is obtained, and a capacity assessment model is trained based on the layer-laying chicken breeding income training set, wherein the capacity assessment model is used to assess the predicted egg production income of the layer after a preset time, wherein the layer-laying chicken breeding income training set includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, income time, and egg production income, including: A verification set is obtained based on the laying hen farming income training set, the production capacity assessment model is verified based on the verification set, and whether the training process is completed is determined based on the verification result.

3. The laying hen breeding capacity model and prediction method according to claim 2, characterized in that: Obtaining a verification set based on the laying hen breeding income training set, verifying the production capacity assessment model based on the verification set, and determining whether the training process is completed according to the verification result, including: Extracting part of the data from the laying hen breeding income training set as the verification set; Importing the verification set into the energy evaluation model, and obtaining the verified egg production benefit output by the evaluation model; The verified egg production benefit is compared with the egg production benefit in the verification set, and the verification result is determined according to the comparison result.

4. The laying hen breeding capacity model and prediction method according to claim 3, characterized in that: Comparing the verified egg production income with the egg production income in the verification set, and determining the verification result according to the comparison result, including: The verified egg production income is compared with the egg production income in the verification set. If the verified egg production income is greater than the egg production income in the verification set, an error value is obtained, and the error value T satisfies: T=( - ) 5. If the verified egg production yield is less than the egg production yield in the verification set, an error value is obtained, and the error value T satisfies: T=( - ) 6. Among them, To verify egg production, is the egg production gain in the validation set.

7. A laying hen breeding capacity model and prediction method according to any one of claim 4, characterized in that: Comparing the verified egg production income with the egg production income in the verification set, and determining the verification result according to the comparison result, including: The error value is compared with a preset value. If the error value is smaller than the preset value, it is determined that the verification is successful and the training process of the production capacity assessment model is stopped.

8. A laying hen breeding capacity model and prediction method according to claim 5; It is characterized in that Based on the target egg production benefit, the maximum egg production benefit and the minimum egg production benefit are determined, including: Acquire the verified egg production benefits outputted multiple times by the production capacity assessment model when the error value is greater than the predicted value during the training process of the production capacity assessment model; A floating parameter is determined based on a plurality of the verified egg production benefits, and the floating parameter d satisfies: ; Wherein, n is the number of iterations in the verification set iteration process, and x is the predicted egg production benefit; The predicted egg production benefit output by the production capacity assessment model is obtained, and the maximum egg production benefit and the minimum egg production benefit are determined based on the predicted egg production benefit and the floating parameter, and the following conditions are satisfied: ; ; in, is the minimum egg production benefit, is the maximum egg production gain.

9. The laying hen breeding capacity model and prediction method according to claim 1, characterized in that: Obtain existing laying hen breeding data and target time, where the target time is the time when the output needs to be predicted, and the existing laying hen breeding data includes the perceived feed intake, perceived behavior characteristic data, and perceived chicken house environment data obtained from the existing laying hen breeding site, including: Acquire the existing laying hen breeding data, wherein acquiring the perceptual behavior characteristic data comprises: Acquire a first chicken farm image at a first moment, and identify a plurality of breeding individual images from the first chicken farm image based on image recognition technology; Determine the posture data of each visible farmed individual based on the farmed individual image, assign a separate identification to each farmed individual and continuously track it; The posture data of each of the farmed individuals at the second moment is obtained, and compared with the posture data at the first moment, and the perception behavior data is determined according to the comparison result.

10. A laying hen breeding capacity model and prediction method according to claim 7, characterized in that: Acquiring the posture data of the farmed individual at the second moment, and comparing it with the posture data at the first moment, and determining the perception behavior data according to the comparison result, including: Acquire a posture data evaluation model, import the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model, and determine the perceptual behavior characteristic data according to a result output by the posture data evaluation model, wherein the posture data of the farmed individual includes the head-to-body ratio of the farmed individual, the moving speed of the farmed individual, and the number of up and down movements of the head of the farmed individual per unit time.

11. A laying hen breeding capacity model and prediction method according to claim 8, characterized in that: Acquiring a posture data evaluation model, and importing the posture data at the first moment and the posture data of the farmed individual at the second moment into the posture data evaluation model, comprising: The posture data evaluation model is trained based on historical data to obtain a trained posture data evaluation model.

12. A laying hen breeding capacity model and prediction method, characterized in that: The system is configured to: Acquire a training set of laying hen breeding income, and train a capacity assessment model based on the laying hen breeding income training set, wherein the capacity assessment model is used to assess the predicted egg production income of the laying hen after a preset time, wherein the laying hen breeding income training set includes: perceived feed intake, perceived behavioral characteristic data, perceived chicken house environment data, income time, and egg production income; Obtaining existing laying hen breeding data and a target time, wherein the target time is the time when the output needs to be predicted, and the existing laying hen breeding data includes the perceived feed intake, perceived behavioral characteristic data, and perceived chicken house environment data obtained from existing laying hen breeding sites; Importing the existing laying hen breeding data and the target time into the production capacity assessment model, and determining the target egg production benefit according to the predicted egg production benefit output by the production capacity assessment model, wherein the target egg production benefit is the egg production benefit at the target time; Based on the target egg production benefit, determining a maximum egg production benefit and a minimum egg production benefit; The pre-purchase price range of eggs is determined based on the maximum egg production profit and the minimum egg production profit.

Images