Broiler health state detection method and system based on Markov chain
By constructing the Markov chain model and using the behavioral data of broilers, the problem of insufficient comprehensive and accurate health status detection in the existing technology is solved, and more accurate health status monitoring and prediction are achieved, and the efficiency and health level of breeding management are improved. .
Patent Information
- Application Number
- CN202411051828.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-01
AI Technical Summary
The prior art fails to fully consider the evolution of the health status in broiler health status detection, resulting in insufficient comprehensiveness and accuracy of the monitoring system.
Using the Markov chain-based detection method, the Markov chain model is constructed and the model is trained by obtaining the behavioral data of broilers (activity frequency, food consumption, water consumption and call frequency). Real-time health status detection is achieved by optimizing the initial probability and state transition probability matrix of healthy state.
It improves the accuracy and prediction ability of broiler health status detection, provides intelligent decision-making support, and improves the efficiency and health level of broiler breeding management.
Smart Images

Figure CN118940152A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart breeding technology, and in particular to a broiler health status detection method and system based on Markov chain. Background Art
[0002] The health status of broilers directly affects their growth rate and final meat quality. Timely and accurate detection of the health status of broilers is of great significance to the broiler farming industry.
[0003] The invention patent with application number 201310547402.9 discloses a real-time monitoring method for the physical health of poultry based on data extraction, which includes the following steps: A1: constructing a regional monitoring wireless sensor network, collecting the characterization data of healthy and diseased poultry within 720 hours respectively, using data extraction technology to process the data, extracting characteristic information, and constructing a health model library and a disease model library for the physical condition of poultry; A2: real-time monitoring of the physical health of poultry, collecting relevant characterization data of poultry in real time, extracting features through data extraction, matching with the health model library and the disease model library respectively, updating the corresponding model library according to the matching results, and sending a report to the administrator to take corresponding measures. This technology adopts a combination of data extraction and wireless sensor networks to monitor the physical condition of poultry in real time. It is suitable for large and medium-sized breeding sites. The health status of poultry can be preliminarily judged by the detected poultry data, so as to achieve timely detection and rapid prevention of diseases, so as to reduce or even avoid the economic losses caused by the spread of poultry diseases.
[0004] Although the data extraction-based poultry physical health monitoring method has certain advantages in real-time monitoring and feature extraction, it does not take into account the evolution of broiler health status, resulting in relatively insufficient modeling and prediction capabilities for poultry health status, limiting the comprehensiveness and accuracy of the monitoring system. Summary of the invention
[0005] In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a broiler health status detection method and system based on Markov chain.
[0006] To achieve the above object, the present invention provides the following solutions:
[0007] A broiler health status detection method based on Markov chain, comprising:
[0008] Obtaining behavioral data of target broilers; the behavioral data includes: activity frequency, food intake, water intake, and call frequency;
[0009] Cleaning, standardizing, feature extracting and feature synthesizing the behavior data to obtain time series detection data for detection;
[0010] The health status of broilers is divided according to a preset broiler historical data set to obtain multiple health statuses;
[0011] constructing a Markov chain model according to the health status;
[0012] The Markov chain model is trained using a preset broiler health status historical data set to optimize the initial probability and state transition probability matrix of each health state, thereby obtaining a trained broiler health status detection model;
[0013] The time series detection data is input into a broiler health status detection model to obtain a detection result.
[0014] Preferably, the health status includes: health, sub-health, mild disease and severe disease.
[0015] Preferably, obtaining the behavioral data of the target broiler chickens includes:
[0016] Setting an infrared sensor in the activity area of the target broiler chicken, and using the infrared sensor to obtain the activity frequency of the target broiler chicken;
[0017] A weight sensor and a flow sensor are respectively arranged on the feeder and the drinker of the target broiler, and the food intake and the water intake are respectively obtained according to the weight sensor and the flow sensor;
[0018] A sound sensor is arranged in the activity area of the target broiler, and the calling frequency is collected according to the sound sensor.
[0019] Preferably, the behavior data is cleaned, standardized and feature extracted to obtain a health feature data set for detection, including:
[0020] Performing outlier processing, missing value filling and data standardization on each type of behavioral data in turn to obtain standardized data;
[0021] Extracting features from the standardized data to obtain activity frequency features, food intake features, water intake features, and call frequency features;
[0022] Integrating the activity frequency feature, the food intake feature, the water intake feature and the call frequency feature to form a plurality of health feature data sets for detection;
[0023] The health feature data set is sampled according to a preset time window to form the time series detection data.
[0024] Preferably, the activity frequency characteristics include the number of activities per unit time, activity intensity, activity time and static time; the food intake characteristics include the number of meals per unit time, the amount of food consumed each time and the total amount of food consumed per day; the water drinking characteristics include the number of water drinks per unit time, the amount of water consumed each time and the total amount of water consumed per day; the call frequency characteristics include: the call frequency per unit time, the duration of each call and the call volume.
[0025] Preferably, constructing a Markov chain model according to the health status includes:
[0026] The health status of broiler chickens is defined as a discrete finite state set S = {s1, s2, ..., s n}, where s i represents the i-th health state;
[0027] Assume that the probability distribution of the broiler chicken state at the initial time t = 0 is π = (π1, π2, ..., π n );where π i =P(S0=s i ); S0 is the system state at the initial time t = 0, P(S0 = s i ) indicates that the system is in state s at the initial moment i The probability of
[0028] Construct state transition probability matrix P; Among them, P ij =P(S t+1 =s j ∣S t =s i ), t is the time step;
[0029] The Markov chain model is constructed according to the finite state set, the probability distribution and the state transition probability matrix.
[0030] Preferably, the broiler health status historical data set includes: preset activity frequency characteristic data, food intake characteristic data, water intake characteristic data and call frequency characteristic data.
[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0032] The present invention provides a broiler health status detection method based on Markov chain, comprising: obtaining the behavior data of target broilers; the behavior data includes: activity frequency, food intake, water intake and call frequency; cleaning, standardizing, feature extraction and feature synthesis of the behavior data to obtain time series detection data for detection; dividing the health status of broilers according to a preset broiler historical data set to obtain multiple health states; building a Markov chain model according to the health state; training the Markov chain model using a preset broiler health status historical data set to optimize the initial probability and state transition probability matrix of each health state to obtain a trained broiler health status detection model; inputting the time series detection data into the broiler health status detection model to obtain a detection result. The broiler health status detection method based on Markov chain of the present invention can combine multidimensional data, realize real-time monitoring and intelligent decision support, and improve the efficiency and level of broiler breeding management. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0034] Figure 1 A flow chart of a method provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0035] 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0037] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides a broiler health status detection method based on Markov chain, comprising:
[0038] Step 100: Obtaining behavioral data of target broilers; the behavioral data includes: activity frequency, food intake, water intake and call frequency;
[0039] Step 200: cleaning, standardizing, feature extracting and feature synthesizing the behavior data to obtain time series detection data for detection;
[0040] Step 300: dividing the health status of broilers according to a preset broiler historical data set to obtain multiple health statuses;
[0041] Step 400: constructing a Markov chain model according to the health status;
[0042] Step 500: training the Markov chain model using a preset broiler health status historical data set to optimize the initial probability and state transition probability matrix of each health status, and obtain a trained broiler health status detection model;
[0043] Step 600: Input the time series detection data into a broiler health status detection model to obtain a detection result.
[0044] Preferably, the health status includes: health, sub-health, mild disease and severe disease.
[0045] Preferably, obtaining the behavioral data of the target broiler chickens includes:
[0046] Setting an infrared sensor in the activity area of the target broiler chicken, and using the infrared sensor to obtain the activity frequency of the target broiler chicken;
[0047] A weight sensor and a flow sensor are respectively arranged on the feeder and the drinker of the target broiler, and the food intake and the water intake are respectively obtained according to the weight sensor and the flow sensor;
[0048] A sound sensor is arranged in the activity area of the target broiler, and the calling frequency is collected according to the sound sensor.
[0049] Specifically, this embodiment first installs the equipment and collects data, as follows:
[0050] Step 101: Equipment selection and installation, use activity monitoring sensors (such as infrared sensors) installed around the cages. Install weight sensors under the trough of the feeder to record the amount of food reduction in real time. Install flow sensors at the outlet and inlet of the drinker to monitor water intake. Install sound sensors or microphones to capture the frequency and intensity of broiler calls. Reasonably install the above sensor equipment in the cages, feeders, drinkers and activity areas of the farm to ensure that the data of each target broiler can be accurately collected.
[0051] Step 102, data collection and transmission, records the number and amplitude of broiler movements within a certain period of time, and detects movement behavior; measures the weight change of feed in the feeder in real time, and records the amount of food eaten each time; measures the water volume change in the waterer in real time, and records the amount of water drunk each time; collects broiler call data through sound sensors, including frequency, duration, and intensity.
[0052] Step 103, data transmission, uses a wireless sensor network (such as WiFi, ZigBee) to transmit the collected behavior data to the central data processing system in real time, establishes a data receiving point (such as a data gateway) to centrally collect sensor data, and transmits it to the server for further processing.
[0053] Preferably, the behavior data is cleaned, standardized and feature extracted to obtain a health feature data set for detection, including:
[0054] Performing outlier processing, missing value filling and data standardization on each type of behavioral data in turn to obtain standardized data;
[0055] Extracting features from the standardized data to obtain activity frequency features, food intake features, water intake features, and call frequency features;
[0056] Integrating the activity frequency feature, the food intake feature, the water intake feature and the call frequency feature to form a plurality of health feature data sets for detection;
[0057] The health feature data set is sampled according to a preset time window to form the time series detection data.
[0058] Furthermore, the data preprocessing step of this embodiment includes:
[0059] Step 201, data cleaning, includes: outlier processing, identifying and removing outliers in the data (such as food intake or water intake data that is obviously beyond the normal range); missing value filling, using appropriate methods (such as mean filling, interpolation) to fill in missing values in the collected data.
[0060] Step 202, data normalization, normalizes the behavior data recorded by different sensors to make the data scale consistent and suitable for subsequent feature extraction and model calculation.
[0061] Furthermore, the feature extraction step of this embodiment includes:
[0062] Step 203, calculate the number of activities, activity intensity, activity time, rest time, etc. within a unit time.
[0063] Step 204, calculating the number of times food is eaten per unit time, the amount of food eaten each time, the total amount of food eaten per day, etc.
[0064] Step 205, calculating the number of times of drinking water per unit time, the amount of water drunk each time, the total amount of water drunk per day, etc.
[0065] Step 206, calculating the frequency of calls per unit time, the duration of each call, the volume of the call, etc.
[0066] Preferably, the activity frequency characteristics include the number of activities per unit time, activity intensity, activity time and static time; the food intake characteristics include the number of meals per unit time, the amount of food consumed each time and the total amount of food consumed per day; the water drinking characteristics include the number of water drinks per unit time, the amount of water consumed each time and the total amount of water consumed per day; the call frequency characteristics include: the call frequency per unit time, the duration of each call and the call volume.
[0067] Furthermore, this embodiment also includes the step of generating a health feature data set, specifically:
[0068] Step 207, integrating the characteristic data collected and processed by each sensor to form a plurality of health characteristic data sets for detection, one corresponding to each broiler chicken.
[0069] Step 208, sampling the feature data according to a certain time window (such as hours, days) to form time series data.
[0070] Preferably, constructing a Markov chain model according to the health status includes:
[0071] The health status of broiler chickens is defined as a discrete finite state set S = {s1, s2, ..., s n}, where s i represents the i-th health state;
[0072] Assume that the probability distribution of the broiler chicken state at the initial time t = 0 is π = (π1, π2, ..., π n );where π i =P(S0=s i ); S0 is the system state at the initial time t = 0, P(S0 = s i ) indicates that the system is in state s at the initial moment i The probability of
[0073] Construct state transition probability matrix P; Among them, P ij =P(S t+1 =s j ∣S t =s i ), t is the time step;
[0074] The Markov chain model is constructed according to the finite state set, the probability distribution and the state transition probability matrix.
[0075] Specifically, suppose that the health status of broilers is divided into four discrete states S = {healthy, sub-healthy, mild disease, severe disease}, and s1, s2, s3, s4 are used to represent these four states. Then P(S0 = s1) represents the probability that a broiler is in a healthy state at the beginning of monitoring. The sum of the probability distributions of all initial states should be 1, that is, Wherein, n is the total number of states. In the example of this embodiment: P(S0=s1)+P(S0=s2)+P(S0=s3)+P(S0=s4)=1.
[0076] Furthermore, the state probability P(S0=s i ) can usually be statistically analyzed based on historical data. If there is a large amount of historical data, we can estimate these probabilities by counting the frequency of each state at the beginning of monitoring. For example:
[0077] In the past 1000 monitoring cycles, there were 600 times when the broilers started out healthy, so P(S0=s1)≈0.6.
[0078] There are 200 times when the broilers are in sub-healthy state at the beginning, then P(S0=s2)≈0.2.
[0079] There are 150 times when the broilers start out in a mild disease state, then P(S0=s3)≈0.15.
[0080] There were 50 times when the broilers started out in a severe disease state, then P(S0=s4)≈0.05.
[0081] Preferably, the broiler health status historical data set includes: preset activity frequency characteristic data, food intake characteristic data, water intake characteristic data and call frequency characteristic data.
[0082] Specifically, the Markov chain model of this embodiment also includes an observation matrix O, which describes the probability of observing a specific observation value (sensor data) in each state.
[0083] The beneficial effects of the present invention are as follows:
[0084] (1) The present invention utilizes the behavioral data of broilers, including multi-dimensional information such as activity frequency, food intake, water intake, and call frequency. By integrating these data, a more comprehensive understanding of the health status of broilers can be obtained.
[0085] (2) The present invention obtains time series data for detection by cleaning, standardizing, feature extracting and feature synthesizing the behavior data, which enables dynamic monitoring and analysis of the health status of broilers, thereby timely detecting status changes.
[0086] (3) The present invention divides the health status of broilers based on a preset historical data set of broilers and constructs a Markov chain model. Through modeling and training of historical data, the health status of broilers can be inferred and predicted more accurately.
[0087] (4) The Markov chain model of the present invention can effectively compress and represent the complexity of state transition, so that the relationship and transition rules between the health states of broilers can be described in a concise way.
[0088] (5) The present invention uses a trained broiler health status detection model to detect and diagnose the health status of broilers in real time after acquiring new time series detection data, helping breeders to take corresponding measures in a timely manner.
[0089] (6) The present invention can provide intelligent decision support and help breeders formulate more reasonable breeding management strategies through model analysis and test results, thereby improving the health level and production efficiency of broiler chickens.
[0090] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0091] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A broiler health status detection method based on Markov chain, characterized in that: include: Obtain behavioral data of target broilers; The behavioral data include: activity frequency, food intake, water intake and call frequency; Cleaning, standardizing, feature extracting and feature synthesizing the behavior data to obtain time series detection data for detection; The health status of broilers is divided according to a preset broiler historical data set to obtain multiple health statuses; constructing a Markov chain model according to the health status; The Markov chain model is trained using a preset broiler health status historical data set to optimize the initial probability and state transition probability matrix of each health state, thereby obtaining a trained broiler health status detection model; The time series detection data is input into a broiler health status detection model to obtain a detection result.
2. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: The health status includes: healthy, sub-healthy, mild disease and severe disease.
3. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: Obtain behavioral data of target broilers, including: Setting an infrared sensor in the activity area of the target broiler chicken, and using the infrared sensor to obtain the activity frequency of the target broiler chicken; A weight sensor and a flow sensor are respectively arranged on the feeder and the drinker of the target broiler, and the food intake and the water intake are respectively obtained according to the weight sensor and the flow sensor; A sound sensor is arranged in the activity area of the target broiler, and the calling frequency is collected according to the sound sensor.
4. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: The behavior data is cleaned, standardized and feature extracted to obtain a health feature data set for detection, including: Performing outlier processing, missing value filling and data standardization on each type of behavioral data in turn to obtain standardized data; Extracting features from the standardized data to obtain activity frequency features, food intake features, water intake features, and call frequency features; Integrating the activity frequency feature, the food intake feature, the water intake feature and the call frequency feature to form a plurality of health feature data sets for detection; The health feature data set is sampled according to a preset time window to form the time series detection data.
5. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: The activity frequency characteristics include the number of activities per unit time, activity intensity, activity time and static time; the food intake characteristics include the number of meals per unit time, the amount of food eaten each time and the total amount of food eaten per day; The water drinking characteristics include the number of times of drinking per unit time, the amount of water drunk each time and the total amount of water drunk per day; The call frequency characteristics include: the call frequency per unit time, the duration of each call and the call volume.
6. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: A Markov chain model is constructed according to the health state, including: The health status of broiler chickens is defined as a discrete finite state set S = {s1, s2, ..., s n }, where s i represents the i-th health state; Assume that the probability distribution of the broiler state at the initial time t = 0 is π = (π1, π2, ..., π n );where π i =P(S0=s i ); S0 is the system state at the initial time t = 0, P(S0 = s i ) indicates that the system is in state s at the initial moment i probability; Construct state transition probability matrix P; Among them, P ij =P(S t+1 =s j ∣S t =s i ), t is the time step; The Markov chain model is constructed according to the finite state set, the probability distribution and the state transition probability matrix.
7. The broiler health status detection method based on Markov chain according to claim 1, characterized in that: The broiler health status historical data set includes: preset activity frequency characteristic data, food intake characteristic data, water intake characteristic data and call frequency characteristic data.
Citation Information
Patent Citations
Henhouse environment monitoring system and method
CN107907158A
Method for monitoring health of domestic animals and system
CN108990831A
Flow anomaly detection method based on multi-order Markov chain
CN110460458A
Fish, shrimp and sea cucumber breeding precise feeding system and device based on target detection and tracking
CN110583550A
Health state detection method and device, storage medium and electronic equipment
CN114842415A
Cited By
Timing and quantitative control method and device for automatic water supply equipment for experimental animals
CN119512239A
A timed and quantitative control method and device for automatic water supply equipment for experimental animals
CN119512239B
