Intelligent incubation prediction method and device and computer readable medium

Abstract

The invention provides an intelligent incubation prediction method and device and a computer readable medium, and the method comprises the steps: obtaining a feature sample of a target animal in response to an intelligent incubation prediction request; inputting the feature sample of the target animal into a preset feature information analysis model to obtain feature data of the target animal; and inputting the feature data of the target animal into a preset intelligent incubation prediction model, and obtaining an intelligent incubation prediction result of the target animal.

Description

Technical Field

[0001] The present application relates to the field of poultry breeding technology, and in particular to an intelligent hatching prediction method, device and computer-readable medium. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the application that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

[0003] With the development of breeding technology, there are more and more animal species. In order to better plan the growth of animals, it is necessary to predict the hatching success rate of animals and then adjust the breeding strategy. At present, most animal hatching rates are predicted by manual experience.

[0004] In recent years, modern scientific breeding technology has been continuously introduced and applied to the breeding industry, which has played a great role in promoting the healthy development of the poultry breeding industry and meeting people's consumption needs for poultry. At the same time, the poultry breeding structure has gradually shifted from family management to large-scale, intensive and professional management. Relying on traditional manual prediction methods can no longer meet the current poultry breeding needs.

[0005] Therefore, there is an urgent need to propose an intelligent hatching prediction method with high integration, high accuracy and strong real-time performance. Summary of the invention

[0006] Multiple aspects of the present application provide an intelligent hatching prediction method, device and computer-readable storage medium for predicting the hatching results of animals.

[0007] In one aspect of the present application, an intelligent hatching prediction method is provided, comprising:

[0008] Responding to the intelligent hatch prediction request, obtaining characteristic samples of the target animal;

[0009] Inputting the characteristic sample of the target animal into a preset characteristic information analysis model to obtain the characteristic data of the target animal;

[0010] The characteristic data of the target animal is input into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0011] Furthermore, in response to the intelligent hatching prediction request, a characteristic sample of the target animal is obtained, including: in response to the intelligent hatching prediction request, sample data of the target animal and its mother are obtained; the sample data of the target animal and the sample data of the mother of the target animal are associated to generate an associated information table; based on the identity code of the target animal or the identity code of the mother of the target animal, the associated information table is named to obtain the characteristic sample of the target animal.

[0012] Further, in response to the intelligent hatching prediction request, obtaining a characteristic sample of the target animal also includes:

[0013] In response to the intelligent hatching prediction request, acquiring and cleaning sample data of the target animal to obtain the cleaned sample data;

[0014] Standardizing and normalizing the cleaned sample data to obtain processed sample data;

[0015] Converting the non-numerical sample data of the target animal into binary sample data based on a hot encoding rule;

[0016] Based on the binary sample data and the processed sample data, a characteristic sample of the target animal is obtained.

[0017] Further, in response to the intelligent hatching prediction request, the sample data of the target animal is acquired and cleaned to obtain the cleaned sample data, including:

[0018] Check the integrity of the sample data of the target animal. If there is missing sample data, fill in the sample data based on the following formula:

[0019]

[0020] Where: x i represents the i-th time in the time series, y i Indicates the corresponding x i data;

[0021] The abnormality of the sample data of the target animal is detected, and if there is abnormal sample data, the abnormal sample data is processed based on an abnormal data processing rule.

[0022] Furthermore, the cleaned sample data is standardized and normalized, including: based on the following formula, the cleaned sample data is standardized:

[0023]

[0024] Wherein: x represents the sample data before standardization, mean(x) represents the mean value of the sample data x; std(x) represents the standard deviation of the sample data x; the cleaned sample data is normalized based on the following formula:

[0025]

[0026] Where: x represents the sample data before normalization, min(x) represents the minimum value of the sample data x, and max(x) represents the maximum value of the sample data x.

[0027] Furthermore, the method also includes: generating a preset feature information analysis model; the generating of the preset feature information analysis model includes: responding to an intelligent hatching prediction request, the intelligent hatching prediction request including an intelligent hatching prediction target; based on the intelligent hatching prediction target, according to a correlation analysis model, determining the correlation between the sample data and the intelligent hatching prediction target, and obtaining a first analysis result; based on the intelligent hatching prediction target, according to a random forest model, determining the correlation between the sample data and the intelligent hatching prediction target, and obtaining a second analysis result; based on the first analysis result and the second analysis result, obtaining the feature data of the target animal.

[0028] Furthermore, the method further includes: generating a preset intelligent hatching prediction model; generating a preset intelligent hatching prediction model, including: obtaining multiple sets of training sample sets; dividing each set of training sample sets into two sets of training sample subsets based on a preset value; and determining the information entropy of any training sample subset in each set of training sample sets based on the following formula:

[0029]

[0030] Among them, i represents any training subset, p i Represents the proportion of sample data in any training subset; based on the following formula, the information gain of each training sample set is determined:

[0031]

[0032] Among them, |D| represents the total number of sample data, |D i | represents the number of samples in any training sample subset in any set of training sample sets; based on the information entropy of each set of training sample sets, a preset intelligent hatching prediction model is generated.

[0033] Another aspect of the present application provides an intelligent hatching prediction device, the device comprising:

[0034] A response unit, for responding to intelligent hatching prediction requests and obtaining characteristic samples of target animals;

[0035] A first acquisition unit is used to input the characteristic sample of the target animal into a preset characteristic information analysis model to acquire characteristic data of the target animal;

[0036] The second acquisition unit is used to input the characteristic data of the target animal into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0037] In another aspect of the present application, an electronic device is provided, the device comprising:

[0038] at least one processor; and

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the intelligent hatching prediction method as described above.

[0041] In another aspect of the present application, a computer-readable storage medium is provided, on which computer program instructions are stored, and the computer program instructions can be executed by a processor to implement the intelligent hatching prediction method.

[0042] In the solution provided in the embodiment of the present application, by responding to the intelligent hatching prediction request, the characteristic sample of the target animal is obtained; the characteristic sample of the target animal is input into a preset characteristic information analysis model to obtain the characteristic data of the target animal; the characteristic data of the target animal is input into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal. Based on the above-mentioned intelligent hatching prediction method, through the big data model, it can help breeders better control the hatching process of animals and improve the survival rate of animals. Early detection of possible health problems such as diseases and developmental abnormalities in animals allows breeders to take corresponding measures in time to reduce unknown risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0045] Figure 1 A schematic diagram of a process flow of an intelligent hatching prediction method provided in one embodiment of the present application;

[0046] Figure 2 A schematic diagram of the structure of an intelligent hatching prediction device provided in another embodiment of the present application;

[0047] Figure 3 A schematic diagram of the structure of an electronic device suitable for implementing the solution in the embodiment of the present application

[0048] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] In a typical configuration of the present application, the terminal and the equipment of the service network each include one or more processors (CPU), input / output interface, network interface and memory.

[0051] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0052] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer program instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0053] The present application embodiment provides an intelligent hatching prediction method, including:

[0054] Responding to the intelligent hatch prediction request, obtaining characteristic samples of the target animal;

[0055] Inputting the characteristic sample of the target animal into a preset characteristic information analysis model to obtain the characteristic data of the target animal;

[0056] The characteristic data of the target animal is input into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0057] In actual scenarios, the execution subject of the method can be a user device, or a device formed by integrating a user device and a network device through a network, or an application running on the above device. The user device includes but is not limited to various terminal devices such as computers, mobile phones, tablet computers, smart watches, and bracelets. The network device includes but is not limited to network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets. Here, the cloud is composed of a large number of hosts or network servers based on cloud computing, where cloud computing is a type of distributed computing, a virtual computer composed of a group of loosely coupled computer sets.

[0058] Embodiment 1

[0059] The embodiment of the present application provides a model generation method to generate a feature information analysis model for obtaining feature data of a target animal, the method comprising:

[0060] In response to an intelligent hatching prediction request, the intelligent hatching prediction request includes an intelligent hatching prediction target; wherein the intelligent hatching prediction type includes but is not limited to the hatching rate, survival rate, growth rate and health status of the animal;

[0061] Based on the intelligent hatching prediction target, according to the correlation analysis model, determining the correlation between the sample data and the intelligent hatching prediction target to obtain a first analysis result;

[0062] Based on the intelligent hatching prediction target, determining the correlation between the sample data and the intelligent hatching prediction target according to the random forest model to obtain a second analysis result;

[0063] Based on the first analysis result and the second analysis result, characteristic data of the target animal is acquired.

[0064] In one embodiment, the characteristic data of an animal related to hatchability is determined as an example. The original characteristic data of the animal includes: hen data: weight: 2000 g; body size: medium; age: 24 months; feed intake: 100 g; genotype: AA; SNP (Single Nucleotide Polymorphism): rs1234567A / G. Egg data: egg size: 5.5 cm; egg weight: 50 g; egg shape: oval; egg color: white; protein content: 12 g / 100 g egg; fat content: 10 g / 100 g egg; carbohydrate content: 5 g / 100 g egg.

[0065] Through the correlation model, the first analysis result between the above sample data and hatching rate is obtained:

[0066] The correlation coefficient between weight and hatching rate is 0.8;

[0067] Correlation coefficient between age and hatching rate: 0.7;

[0068] Correlation coefficient between egg size and hatching rate: 0.6;

[0069] Correlation coefficient between egg weight and hatching rate: 0.75;

[0070] Correlation coefficient between protein content and hatching rate: 0.65;

[0071] Correlation coefficient between fat content and hatching rate: 0.55;

[0072] The correlation coefficient between carbohydrate content and hatching rate is 0.45.

[0073] Using the random forest model, the second analysis result between the above sample data and hatching rate was obtained:

[0074] Importance score of weight: 0.35;

[0075] The importance score of age: 0.28;

[0076] Importance score of Egg Size: 0.25;

[0077] Importance score of Egg Weight: 0.22;

[0078] Importance score of protein content: 0.18;

[0079] Importance score of fat content: 0.15;

[0080] Importance score of carbohydrate content: 0.1.

[0081] Specifically, Weight has a high correlation with hatchability (0.8) and also has a high importance score (0.35) in the random forest model.

[0082] Age also has a high correlation with hatching rate (0.7) and an importance score of (0.28) in the random forest model.

[0083] Egg Size has a high correlation with hatchability (0.6) and an importance score of (0.25) in the random forest model.

[0084] Based on the first analysis result and the second analysis result, it is determined that the characteristic data related to the hatchability include: the weight (Weight) of the hen, the age (Age) of the hen, and the size (Egg Size) of the egg.

[0085] Similarly, based on the above method, the characteristic data related to the growth rate include: the weight of the hen (Weight), the age of the hen (Age), and the feed intake of the hen (Feed Intake); the characteristic data related to the survival rate include: the weight of the egg (Egg Weight), the protein content of the egg (Protein Content), and the genetic data of the hen (Gene Data); the important characteristics related to the health attributes of the target animal are determined: the weight of the hen (Weight), the protein content of the egg (Protein Content), and the genetic data of the hen (Gene Data).

[0086] Embodiment 2

[0087] The embodiment of the present application provides a model generation method to generate an intelligent hatching prediction model for obtaining intelligent hatching prediction results of target animals, wherein the intelligent hatching prediction results include but are not limited to the hatching rate, survival rate, growth rate and health status of the animal, and the method includes:

[0088] Obtain characteristic data of target animals and generate multiple sets of training sample sets;

[0089] Divide each training sample set into two training sample subsets based on a preset value;

[0090] Based on the following formula, the information entropy of any subset of training samples in each set of training samples is determined:

[0091]

[0092] Among them, i represents any training subset, p i Represents the proportion of sample data in any training subset;

[0093] The information gain of each training sample set is determined based on the following formula:

[0094]

[0095] Among them, |D| represents the total number of sample data, |D i | represents the number of samples in any training sample subset in any set of training sample sets;

[0096] Based on the information entropy of each set of training samples, a preset intelligent hatching prediction model is generated.

[0097] In one embodiment, the characteristic data related to hatchability is used for illustration. The training sample set includes three training sample sets of hen weight (Weight), hen age (Age) and egg size (Egg Size). Each training sample set includes a training sample subset with high hatchability and a training sample subset with low hatchability; wherein, high hatchability (High): 80 sample data; low hatchability (Low): 20 sample data. Based on the following formula, the information entropy of any training sample subset in each training sample set is determined:

[0098] Entroopy(D)=-(p high i log2(p high i )+p 1ow i log2(p low i ))

[0099] Among them, i represents any training subset, p high i Indicates the proportion of sample data with sample label high in any training subset, p low iIndicates the proportion of sample data with sample label low in any training subset; based on the following formula, the information gain of each training sample set is determined:

[0100] Gain(Weight)

[0101] =Entropy(D)-(p high log2(p high )+p low log2(p low ))·Entropy(D)

[0102] Among them, p high Indicates the proportion of sample data with sample label high in the training sample set, p low Indicates the proportion of sample data with sample label low in the training sample set.

[0103] Based on the hen's weight, hen's age and egg size data, we can calculate:

[0104]

[0105] Based on the hen's weight, hen's age and egg size data, the information entropy is calculated as:

[0106]

[0107] Calculate the information gain for each feature:

[0108] Training sample set 1: weight of hens (Weight); number of samples (Total Samples): 100.

[0109] The groups were divided into two groups based on body weight:

[0110] Training sample subset 1 (Subset 1): weight greater than or equal to 1800 grams. The corresponding hatchability data are as follows:

[0111] Number of samples with “high” hatchability: 60;

[0112] Number of samples with "low" hatchability: 10.

[0113] Training sample subset 2 (Subset 2): weight less than 1800 grams. The corresponding hatchability data are as follows:

[0114] Number of samples with “high” hatchability: 20;

[0115] Number of samples with "low" hatchability: 10.

[0116] The information gain of training sample 1 is calculated to be approximately 0.2566.

[0117] By analogy, the information gain of the hen's age (Age) is 0.2065; the information gain of the egg size (Egg Size) is 0.

[0118] Calculate the information entropy of training sample subset 1:

[0119]

[0120] Calculate the information entropy of training sample subset 2:

[0121]

[0122] Calculate the information gain of the weight feature:

[0123]

[0124] Similarly, the information gain of the age feature (Age) is calculated to be approximately 0.2065; the information gain of the egg size feature (Egg Size) is approximately 0.0000.

[0125] Compare the information gain of the three sets of training samples:

[0126] The information gain of the weight feature (Weight) is about 0.2566;

[0127] The information gain of the age feature (Age) is about 0.2065;

[0128] The information gain of the egg size feature (Egg Size) is about 0.0000.

[0129] Based on the information gain of the above three sets of training sample sets, a preset intelligent hatching prediction model for predicting the hatching rate of the target animal is generated. In one embodiment, the preset intelligent hatching prediction model is a decision tree, and the nodes of the decision tree are generated based on the information gain of the three sets of training sample sets, and the weight feature is set as the parent node of the age feature, and the age feature is set as the parent node of the egg size feature.

[0130] Embodiment 3

[0131] Figure 1 The processing flow of an intelligent hatching prediction method provided by an embodiment of the present application is shown. The intelligent hatching result of the target animal is predicted based on the feature information analysis model generated in the first embodiment and the intelligent hatching prediction model generated in the second embodiment. The method includes at least the following processing steps:

[0132] Step S101, in response to an intelligent hatching prediction request, obtaining a characteristic sample of a target animal;

[0133] Step S102, inputting the characteristic sample of the target animal into a preset characteristic information analysis model to obtain characteristic data of the target animal;

[0134] Step S103, inputting the characteristic data of the target animal into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0135] The intelligent hatching prediction method described in this embodiment integrates scattered data, associates the data, and selects a suitable prediction model for prediction according to the characteristics of different indicators. The trained intelligent hatching prediction model is used to predict hatching prediction results such as hatching rate, growth rate, survival rate and health status, monitor the status of target animals in real time, and provide early warnings and suggestions for breeders.

[0136] It should be understood that this embodiment takes chickens as the target animal to illustrate the intelligent hatching prediction method described in this application.

[0137] In one embodiment, step S101 obtains the characteristic sample of the target animal, including: obtaining sample data of eggs and sample data of hens (i.e., the mother of the eggs); generating information codes corresponding to the eggs and hens respectively; associating the sample data of the eggs with the sample data of the hens to generate an associated information table; naming the associated information table based on the information code of the eggs, or the identity code of the hen, to generate a characteristic sample of the eggs.

[0138] Specifically, sample data of hens can be collected through wearable devices, including weight, body shape, age, feed intake, etc. In practical applications, the weight of a hen can be numerical data in grams (g); for example, a hen weighs 2000 grams. The body shape of a hen can be categorical data, such as small, medium, and large; for example, a hen is medium in size. The age of a hen can be numerical data in months; for example, a hen is 24 months old. The amount of feed a hen consumes per day can be numerical data in grams (g); for example, a hen consumes 100 grams of feed per day.

[0139] The sample data of hens also includes the genetic data of the hens. The genetic data is obtained by sequencing the genes of the hens, which describes the genetic composition of the hens. Genetic data is usually presented in the form of DNA sequences, which consist of a series of base pairs (A, T, C, G). The base pair sequence in the genetic data determines the genetic characteristics of the hens, such as color, body shape, disease resistance, etc. For example, genotype describes different variants of a gene. For example, there may be two common genotypes for a certain gene, represented by letters (such as AA and Aa). Gene frequency is used to describe the frequency of occurrence of a certain genotype in the entire population. SNP (Single Nucleotide Polymorphism) is used to describe the variation of a single base pair in a gene. rs1234567A / G means that there are two possible base pairs (i.e., A and G) at this site. Gene function is used to describe the function of the protein encoded by the gene, or the association between the gene and a specific characteristic.

[0140] The sample data of eggs includes the collection of egg phenotypic data (such as size, weight, shape, color, etc.) and egg composition data. Egg size includes egg length, which is usually the distance from the longest end to the other end (such as 5.5 cm, 6.0 cm, 6.5 cm, etc.). Egg shapes include oval, round, etc. Egg shell colors include white and brown.

[0141] Specifically, the ingredient data of eggs include protein content, fat content, carbohydrate content, etc. The egg ingredient data described in this application refers to the proportion of its content within 100g unit.

[0142] In one of the embodiments, information codes are generated for eggs and hens respectively, sample data of eggs and sample data of hens are associated to generate an associated information table, including: naming the associated information table based on the information code of the egg or the identity code of the hen to generate a characteristic sample of the egg.

[0143] Specifically, generating information codes corresponding to eggs and hens respectively includes: after the hen lays eggs, marking the eggs with invisible liquid spray, and obtaining the unique ID of the eggs through ultraviolet irradiation, for example: ID-001, ID-002, ID-003, etc.

[0144] Specifically, the sample data of eggs and the sample data of hens are associated to generate an associated information table; including: creating a hen table (Chickens): storing the phenotypic data of hens, including weight, body shape, age, feed intake, etc.; creating a gene table (Genes): storing gene data, including genotype, gene frequency, SNP, etc.; an egg table (Eggs); creating a phenotypic data table of eggs: storing the phenotypic data of eggs, including size, weight, shape, color, etc.; creating an egg ingredient table (Nutrients): storing the ingredient data of eggs, including protein content, fat content, carbohydrate content, etc.; establishing associations: in the database, each table has a unique identifier as a primary key (Primary Key), such as a hen ID, an egg ID, etc. In the Genes and Eggs tables, the hen ID can be used as a foreign key to associate the two tables with the Chickens table; in the Nutrients table, the egg ID can be used as a foreign key to associate the Nutrients table with the Eggs table to generate an associated information table. SQL query statements can be used to connect the associated information tables.

[0145] In one embodiment, the associated information table is named based on the information code of the egg, or the identity code of the hen, and a characteristic sample of the egg is generated; so as to realize a connection query between each associated information table through a unique ID (the information code of the egg, or the identity code of the hen) to obtain complete information including the phenotypic data, genetic data of the hen, the phenotypic data and component data of the egg.

[0146] In one embodiment, in response to the intelligent hatching prediction request in step S101, obtaining the characteristic sample of the target animal also includes: performing data cleaning on the sample data of the eggs to obtain cleaned sample data; standardizing and normalizing the cleaned sample data to obtain processed sample data; converting non-numeric sample data into binary sample data based on hot encoding rules; and obtaining the characteristic data of the target animal based on the binary sample data and the processed sample data.

[0147] In one embodiment, data cleaning of egg sample data includes: detecting and processing missing values; missing values ​​will affect model training and prediction, which can be processed by deleting missing values, interpolating, etc.

[0148] Among them, the processing of missing values ​​by deletion includes: if the number of missing values ​​is small and the missing values ​​do not affect the distribution and pattern of the overall data, the rows or columns where the missing values ​​are located can be directly deleted. Suppose there is a data set that contains the weight of hens, the size of eggs, and the weight of eggs. If the weight of some eggs is missing, you can choose to delete these missing data rows.

[0149] Among them, using interpolation methods to fill missing values ​​includes: using interpolation methods to fill missing values ​​according to the rules of existing data, such as linear interpolation, polynomial interpolation, KNN interpolation, etc. For time series data or ordered data, linear interpolation can be used to fill missing values.

[0150] Specifically, filling the missing values ​​using the interpolation method includes: detecting the integrity of the sample data of the egg, and if there is missing sample data, filling the missing sample data based on the following formula:

[0151]

[0152] Where: x i represents the i-th time in the time series, y i Indicates the corresponding x i data;

[0153] The abnormality of the sample data of the egg is detected, and if the abnormal sample data exists, the abnormal sample data is processed based on an abnormal data processing rule.

[0154] In one embodiment, the sample data of the egg is standardized and normalized, including: based on the following formula, the sample data of the egg is standardized:

[0155]

[0156] Where: x represents the sample data before standardization, mean(x) represents the mean value of the sample data x; std(x) represents the standard deviation of the sample data x;

[0157] Based on the following formula, the sample data of the eggs is normalized:

[0158]

[0159] Where: x represents the sample data before normalization, min(x) represents the minimum value of the sample data x, and max(x) represents the maximum value of the sample data x.

[0160] Through standardization, processed sample data can be obtained. The standardized sample data indicates the degree of deviation of each sample from the average value of each feature. If the standardized value is positive, it means that the value of the sample on the feature is higher than the average value of the feature; if it is negative, it means that the value of the sample on the feature is lower than the average value of the feature.

[0161] Taking an egg weighing 150g (i.e. x=150) as an example, the weight of the egg is normalized to the range of [0,1]. The minimum value min(x) in the original data set is 100g, and the maximum value max(x) is 200g. Then we can calculate

[0162]

[0163] That is, the normalized value of an egg weighing 150g is 0.5.

[0164] Taking the egg composition data as an example (protein content: 20 grams; fat content: 10 grams; carbohydrate content: 5 grams; protein content: 15 grams; fat content: 8 grams), the above data is standardized and calculated:

[0165]

[0166] in,

[0167]

[0168] std(carbohydrate)=0g.

[0169] Taking protein content as an example, the standardized value of 20 grams of protein content is 1, indicating that the protein content of the sample is one standard deviation higher than the average; the standardized value of 15 grams of protein content is -1, indicating that the protein content of the sample is one standard deviation lower than the average. Standardizing and normalizing the sample data of the target animal helps to compare data with different characteristics, and it is easy to observe the relative relationship between data with different characteristics, which is more conducive to the convergence speed and learning performance of algorithms such as machine learning.

[0170] In one implementation, non-numerical sample data of eggs are converted into binary sample data based on one-hot encoding rules. The non-numerical sample data of eggs include egg size, egg color, egg shape, hen body shape, etc. In this embodiment, the color of eggs is used as an example to illustrate the conversion of non-numerical sample data of eggs into binary sample data; assuming that the color feature of eggs has possible values ​​such as "white", "brown", etc. We can use one-hot encoding to convert this feature into multiple binary features.

[0171] Specifically, each different color is first mapped to a unique integer code, such as: white: 0, brown: 1; then one-hot encoding is applied to each integer code to create a new binary feature; that is, the binary feature corresponding to the white color of the egg is [1,0,0], and the binary feature corresponding to the brown color of the egg is [0,1,0].

[0172] In one embodiment, in step S102, the characteristic sample of the target animal is input into a preset characteristic information analysis model to obtain the characteristic data of the target animal: based on the intelligent hatching prediction request, the intelligent hatching prediction target is obtained; based on the type of the intelligent hatching request, the characteristic data of the target animal is obtained.

[0173] Specifically, the intelligent hatching prediction targets include but are not limited to hatching rate, hatchability, growth rate, survival rate and health status. Among them, when the intelligent hatching prediction target is hatching rate, the characteristic data of the target animal include weight of the hen, age of the hen and egg size; when the intelligent hatching prediction target is growth rate, the characteristic data of the target animal include: weight of the hen, age of the hen, feed intake of the hen; when the intelligent hatching prediction target is survival rate, the characteristic data of the target animal include: egg weight, protein content of the egg, gene data of the hen; when the intelligent hatching prediction target is health status, the characteristic data of the target animal include: weight of the hen, protein content of the egg, gene data of the hen.

[0174] In one embodiment, step S103 inputs the characteristic data of the target animal into a preset intelligent hatching prediction model, and obtaining the intelligent hatching prediction result of the target animal includes: obtaining the intelligent hatching prediction result of the target animal based on the characteristic data of the target animal, and the intelligent hatching prediction result corresponds to an intelligent hatching prediction target, including but not limited to hatching rate, survival rate, growth rate and health status.

[0175] In one embodiment, the characteristic data of the target animal is input into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0176] Take the following data as an example to obtain the hatchability prediction result of chicks:

[0177] Among them, the characteristic data of hens and eggs include: hen weight (Weight): 1800 grams; hen age (Age): 20 months; egg size (Egg Size): 5 cm.

[0178] The above feature data is input into the preset feature information analysis model. The first feature is the weight of the hen (Weight). If the weight is less than or equal to 2000 grams, enter the next feature. If the weight is greater than 2000 grams, the hatching rate is directly judged to be "high". Enter the second feature, the age of the hen (Age): if the age is less than or equal to 24 months, enter the next feature. If the age is greater than 24 months, the hatching rate is directly judged to be "low". Enter the third feature, egg size (EggSize): if the egg size is less than or equal to 5.5 cm, the hatching rate is judged to be "high". If the egg size is greater than 5.5 cm, the hatching rate is judged to be "low". Specifically, the above hatching rate prediction process includes: the weight of the hen (Weight) is 1800 grams, less than 2000 grams, enter the next feature; the age of the hen (Age) is 20 months, less than 24 months, enter the next feature; the egg size (Egg Size) is 5 cm, less than or equal to 5.5 cm, so the final prediction of the hatching rate of the chicks in this set of data is "high".

[0179] In one embodiment, a set of sample data of hens and eggs is used to predict the survival rate of chicks. Specifically, egg weight (Egg Weight): 45 grams; protein content of eggs (Protein Content): 11 grams / 100 grams of eggs; gene data of hens (Gene Data): AA. Based on the preset feature information analysis model, the characteristic data of the target animal are obtained, including: egg weight (Egg Weight), protein content of eggs (Protein Content), and gene data of hens (Gene Data) as important features related to survival rate. After obtaining the characteristic data of the target animal, the survival rate prediction result of the target animal is obtained based on the preset intelligent hatching prediction model. The specific steps include: the first feature is egg weight (Egg Weight). If the egg weight is less than or equal to 50 grams, enter the next feature. If the egg weight is greater than 50 grams, the survival rate is directly judged to be "high". Enter the second feature of egg protein content (Protein Content): if the protein content is less than or equal to 10 grams / 100 grams of eggs, the survival rate is judged to be "low". If the protein content is greater than 10 grams per 100 grams of eggs, proceed to the next feature. Enter the third feature, the genetic data of the hen: if the genetic data is AA, the survival rate is judged to be "high". If the genetic data is other, the survival rate is judged to be "low".

[0180] In one embodiment, a set of sample data of hens is used to predict the growth rate of chicks. The data are as follows: hen weight (Weight): 2000 grams; hen age (Age): 28 months; hen feed intake (Feed Intake): 120 grams. Based on the preset feature information analysis model, the feature data of the target animal are obtained, including the hen weight (Weight); the hen age (Age); the hen feed intake (Feed Intake). According to the preset intelligent hatching prediction model, the growth rate prediction result of the target animal is obtained. The specific prediction process includes: the first feature is the hen weight (Weight). If the weight is less than or equal to 2000 grams, enter the next feature. If the weight is greater than 2000 grams, the growth rate is directly judged to be "fast". Enter the second feature hen age (Age): if the age is less than or equal to 24 months, enter the next feature. If the age is greater than 24 months, the growth rate is directly judged to be "slow". Enter the third feature, Feed Intake of the hen: If the feed intake is less than or equal to 100 grams, the growth rate is judged to be "fast". If the feed intake is greater than 100 grams, the growth rate is judged to be "slow".

[0181] In one embodiment, a set of sample data of hens and eggs is used to predict the health status of chicks. The data are as follows: weight of the hen (Weight): 1800 grams; protein content of eggs (Protein Content): 11 grams / 100 grams of eggs; gene data of the hen (Gene Data): AG. According to the preset intelligent hatching prediction model, the health status prediction result of the target animal is obtained. The specific prediction process includes: the first feature is the weight of the hen (Weight). If the weight is less than or equal to 2000 grams, enter the next feature. If the weight is greater than 2000 grams, the health status is directly judged as "good". If the protein content is less than or equal to 10 grams / 100 grams of eggs, the health status is judged as "general". If the protein content is greater than 10 grams / 100 grams of eggs, enter the next feature. If the gene data is AA, the health status is judged to be "good". If the gene data is other situations, the health status is judged to be "general".

[0182] Embodiment 4

[0183] The present application also provides an intelligent hatching prediction device, the structure of which is as follows: Figure 2 As shown, the device includes:

[0184] A response unit, for responding to an intelligent hatching prediction request and acquiring a characteristic sample of a target animal, wherein the intelligent hatching prediction request includes an intelligent hatching prediction target;

[0185] A first acquisition unit is used to input the characteristic sample of the target animal into a preset characteristic information analysis model to acquire characteristic data of the target animal;

[0186] The second acquisition unit is used to input the characteristic data of the target animal into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

[0187] Embodiment 5

[0188] Based on the same inventive concept, an electronic device is also provided in an embodiment of the present application, and the method corresponding to the electronic device may be the intelligent hatching prediction method in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The electronic device provided in an embodiment of the present application includes: 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 methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0189] The electronic device may be a user device, or a device formed by integrating a user device and a network device through a network, or may be an application running on the above device. The user device includes but is not limited to various terminal devices such as computers, mobile phones, tablet computers, smart watches, and bracelets. The network device includes but is not limited to network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets. Here, the cloud is composed of a large number of hosts or network servers based on cloud computing, where cloud computing is a type of distributed computing, a virtual computer composed of a group of loosely coupled computer sets.

[0190] Figure 3 The structure of a device suitable for implementing the method and / or technical solution in the embodiment of the present application is shown, and the device 300 includes a central processing unit (CPU, Central Processing Unit) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM, Read Only Memory) 302 or the program loaded from the storage part 308 to the random access memory (RAM, Random Access Memory) 303. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. An input / output (I / O, Input / Output) interface 305 is also connected to the bus 304.

[0191] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, a touch screen, a microphone, an infrared sensor, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), an LED display, an OLED display, etc., and a speaker, etc.; a storage section 308 including one or more computer-readable media such as a hard disk, an optical disk, a magnetic disk, a semiconductor memory, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet.

[0192] In particular, the methods and / or embodiments in the embodiments of the present application may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. When the computer program is executed by the central processing unit (CPU) 301, the above functions defined in the method of the present application are executed.

[0193] Embodiment 6

[0194] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application described above.

[0195] Specifically, the present embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0196] Computer readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0197] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0198] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0199] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0200] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0201] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0202] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0203] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0204] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0206] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. An intelligent hatching prediction method, wherein: The method comprises: Responding to the intelligent hatch prediction request, obtaining characteristic samples of the target animal; Inputting the characteristic sample of the target animal into a preset characteristic information analysis model to obtain the characteristic data of the target animal; The characteristic data of the target animal is input into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

2. The intelligent hatching prediction method according to claim 1, wherein: In response to the intelligent hatching prediction request, characteristic samples of the target animal are obtained, including: In response to the intelligent hatching prediction request, obtaining sample data of the target animal and its mother; Associating the sample data of the target animal with the sample data of the mother of the target animal to generate an associated information table; Based on the identity code of the target animal, or the identity code of the mother of the target animal, the association information table is named to obtain a characteristic sample of the target animal.

3. The intelligent hatching prediction method according to claim 2, wherein: In response to the intelligent hatching prediction request, a characteristic sample of the target animal is obtained, which also includes: In response to the intelligent hatching prediction request, acquiring and cleaning sample data of the target animal to obtain the cleaned sample data; Standardizing and normalizing the cleaned sample data to obtain processed sample data; Converting the non-numerical sample data of the target animal into binary sample data based on a hot encoding rule; Based on the binary sample data and the processed sample data, a characteristic sample of the target animal is obtained.

4. The intelligent hatching prediction method according to claim 3, wherein: In response to the intelligent hatching prediction request, sample data of the target animal is acquired and cleaned, and the cleaned sample data is obtained, including: Check the integrity of the sample data of the target animal. If there is missing sample data, fill in the sample data based on the following formula: Where: x i represents the i-th time in the time series, y i Indicates the corresponding x i data; The abnormality of the sample data of the target animal is detected, and if there is abnormal sample data, the abnormal sample data is processed based on an abnormal data processing rule.

5. The intelligent hatching prediction method according to claim 3, wherein: The cleaned sample data is standardized and normalized, including: The cleaned sample data is standardized based on the following formula: Where: x represents the sample data before standardization, mean(x) represents the mean value of the sample data x; std(x) represents the standard deviation of the sample data x; Based on the following formula, the cleaned sample data is normalized: Where: x represents the sample data before normalization, min(x) represents the minimum value of the sample data x, and max(x) represents the maximum value of the sample data x.

6. The intelligent hatching prediction method according to any one of claims 1 to 5, further comprising: Generate a preset feature information analysis model; The generating of a preset feature information analysis model comprises: In response to a smart hatching prediction request, the smart hatching prediction request includes a smart hatching prediction target; Based on the intelligent hatching prediction target, according to the correlation analysis model, determining the correlation between the sample data and the intelligent hatching prediction target to obtain a first analysis result; Based on the intelligent hatching prediction target, determining the correlation between the sample data and the intelligent hatching prediction target according to the random forest model to obtain a second analysis result; Based on the first analysis result and the second analysis result, characteristic data of the target animal is acquired.

7. The intelligent hatching prediction method according to claim 6, wherein: The method further comprises: generating a preset intelligent hatching prediction model; Generates a preset intelligent hatching prediction model, including: Obtain multiple sets of training sample sets; Divide each training sample set into two training sample subsets based on a preset value; Based on the following formula, the information entropy of any subset of training samples in each set of training samples is determined: Among them, i represents any training subset, p i Represents the proportion of sample data in any training subset; The information gain of each training sample set is determined based on the following formula: Among them, |D| represents the total number of sample data, |D i | represents the number of samples in any training sample subset in any set of training sample sets; Based on the information entropy of each set of training samples, a preset intelligent hatching prediction model is generated.

8. An intelligent hatching prediction device, wherein: The device comprises: A response unit, for responding to intelligent hatching prediction requests and obtaining characteristic samples of target animals; A first acquisition unit is used to input the characteristic sample of the target animal into a preset characteristic information analysis model to acquire characteristic data of the target animal; The second acquisition unit is used to input the characteristic data of the target animal into a preset intelligent hatching prediction model to obtain the intelligent hatching prediction result of the target animal.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 1 to 7.

Images