Digitalized information management system and method for breeding cow farm

Abstract

The invention relates to the technical field of livestock breeding, in particular to a digital information management system and method for a breeding cow farm. The method comprises the following steps: acquiring basic data of a cow; the basic data comprises estrus behavior data, pregnancy data and historical breeding data; determining estrus characteristics of each cow according to the estrus behavior data and the historical breeding data; determining a group mating batch according to the estrus characteristics; and according to the pregnancy data, adjusting the batch priority of the group mating batches. By accurately analyzing the oestrus cycle waveform characteristics, pregnancy conditions and historical conception efficiency of cows, division of group mating batches is further optimized, the mating opportunity of each cow is adjusted according to real-time data, the breeding efficiency of the cows is more effectively improved, and sustainable development of the whole breeding industry is promoted.

Description

Technical Field

[0001] This application relates to the technical field of livestock breeding, and in particular to a digital information management system and method for a breeding cow farm. Background Art

[0002] In modern cow breeding, breeding efficiency plays a crucial role in increasing production, reducing costs, and ensuring the sustainability of the farm. However, due to the fact that the estrus behavior and physiological changes of cows are affected by various factors, traditional manual monitoring and intervention methods often have certain limitations.

[0003] In large-scale breeding, manual breeding management not only requires a large amount of time and energy, is not only cumbersome but also prone to omissions, and it is easy to miss the best breeding time, resulting in breeding failure or delay, thereby affecting the overall breeding efficiency. Therefore, the breeding work faces huge management difficulties and challenges. Summary of the Invention

[0004] This application provides a digital information management system and method for a breeding cow farm to solve the above problems.

[0005] In a first aspect, this application provides a digital information management method for a breeding cow farm, and the method includes:

[0006] Obtaining basic data of cows; the basic data includes estrus behavior data, pregnancy data, and historical breeding data;

[0007] Determining the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data; determining the group breeding batches according to the estrus characteristics;

[0008] Adjusting the batch priority of the group breeding batches according to the pregnancy data.

[0009] Through this solution, by installing sensors and collecting physiological indicators, real-time monitoring of cow behavior and environmental data is achieved, reducing the time and error of manual data collection. By analyzing the estrus behavior data and historical breeding data, the estrus characteristics of each cow can be determined more accurately, providing a scientific basis for breeding decisions, improving the accuracy and success rate of breeding. According to the estrus characteristics, cows are divided into different breeding batches, optimizing the breeding plan, improving the overall breeding efficiency, and reducing the breeding cost. According to the pregnancy data and the conception efficiency weight, the priority of the breeding batches is adjusted to ensure the maximization of breeding efficiency, improving the conception rate and pregnancy success rate. By accurately analyzing the estrus cycle waveform characteristics, pregnancy status, and historical conception efficiency of cows, the division of group breeding batches is further optimized, and the breeding timing of each cow is adjusted according to real-time data, more effectively improving the breeding efficiency of cows and promoting the sustainable development of the entire breeding industry.

[0010] Optionally, determining the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data includes:

[0011] Analyze the estrus behavior data to determine the change in activity level within a preset time period and the duration of mounting within the preset time period;

[0012] Determine the real-time estrus intensity according to the change in activity level and the duration of mounting;

[0013] Analyze the historical breeding data to determine the conception efficiency weight;

[0014] Determine the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity;

[0015] Analyze the estrus cycle waveform to determine the estrus characteristics.

[0016] Through this solution, by analyzing the change in activity level and the duration of mounting, the estrus behavior of cows can be identified more accurately, improving the recognition rate of estrus characteristics. This helps reduce the risk of missing the optimal breeding time, thereby increasing the conception rate and pregnancy success rate. The determination of real-time estrus intensity helps to more precisely predict the optimal breeding time for each cow, thus optimizing the breeding plan and improving breeding efficiency. By analyzing the historical breeding data, the reproductive ability and conception probability of each cow can be analyzed. The determination of the estrus cycle waveform helps to more accurately predict the estrus cycle of each cow, providing a scientific basis for breeding decisions. By analyzing the estrus cycle waveform, unique estrus characteristics of each cow can be identified, such as the length of the estrus cycle and the trend of waveform changes. These characteristics help optimize the breeding strategy and improve reproductive efficiency.

[0017] Optionally, determining the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity includes:

[0018] Obtain the individual data and environmental data of the cow;

[0019] Analyze the individual data to determine the hormone change curve;

[0020] Analyze the hormone change curve to determine the temporal correlation between the hormone change curve and the real-time estrus intensity;

[0021] Determine the starting point of the estrus cycle according to the temporal correlation;

[0022] Determine the estrus cycle waveform according to the starting point, the conception efficiency weight and the environmental data.

[0023] Through this solution, it is ensured that the individual characteristics of cows and environmental factors are comprehensively identified. By analyzing individual data, the hormone change curve of each cow can be constructed, which helps to identify the estrus cycle of cows and predict the optimal breeding time. By analyzing the temporal correlation between the hormone change curve and the real-time estrus intensity, the estrus cycle and intensity of cows can be predicted more accurately, thus improving the accuracy of breeding decisions. Determining the starting point of the estrus cycle helps to predict the ovulation time of cows, thereby optimizing the breeding time window and increasing the conception rate. By comprehensively considering the starting point, the conception efficiency weight, and environmental data, a more accurate estrus cycle waveform can be constructed, providing a more precise reference for breeding decisions, further optimizing the breeding strategy, and improving the breeding efficiency.

[0024] Optionally, determining the group breeding batches according to the estrus characteristics includes:

[0025] Analyze the estrus characteristics to determine the estrus similarity between any two cows;

[0026] Determine the group breeding batches according to the estrus similarity.

[0027] Through this solution, by analyzing the estrus behavior data, the estrus characteristics of each cow, such as estrus intensity, estrus cycle length, estrus behavior pattern, etc., can be identified more accurately. This helps to improve the analysis of cows' estrus behavior. By calculating the estrus similarity between any two cows, cows can be more effectively divided into different breeding batches. This helps to optimize the breeding plan, improve the breeding efficiency, and reduce the risk of missing the optimal breeding time. According to the estrus similarity, cows with similar estrus characteristics are divided into different breeding batches, which can ensure that cows in the same batch are in estrus within a similar time period, thus facilitating centralized management and breeding. By determining the group breeding batches, the breeding strategy can be optimized, such as selecting the appropriate bull, determining the breeding time, etc., thereby increasing the conception rate and pregnancy success rate and reducing the breeding cost.

[0028] Optionally, adjusting the batch priority of the group breeding batches according to the pregnancy data includes:

[0029] Determine the cow age and the physical condition of the cows according to the pregnancy data;

[0030] Analyze the cow age and the physical condition of the cows to determine the difficulty of parturition;

[0031] Determine the historical conception efficiency according to the historical breeding data;

[0032] Adjust the batch priority of the group breeding batches according to the historical conception efficiency and the difficulty of parturition.

[0033] Through this solution, it is ensured that a comprehensive analysis of the individual characteristics of cows and environmental factors is carried out, which helps to formulate personalized breeding management plans. By analyzing the cow age and the body condition of cows, the difficulty of parturition of each cow can be evaluated more accurately, the risk of dystocia can be reduced, and the survival rates of cows and calves can be increased. By analyzing historical breeding data, the breeding ability and conception probability of each cow can be analyzed, which helps to select cows with better breeding performance for breeding. By comprehensively considering the historical conception efficiency and the difficulty of parturition, the batch priority of breeding batches can be adjusted more effectively, the breeding strategy can be optimized, the conception rate and pregnancy success rate can be increased, the breeding cost can be reduced, and the sustainable development and economic benefits of the farm can be ensured.

[0034] Optionally, determining the historical conception efficiency according to the historical breeding data includes:

[0035] Determining the average conception cycle and pregnancy trend within a historical preset period according to the historical breeding data;

[0036] Determining the total number of cows suitable for breeding within the historical preset period according to the pregnancy trend;

[0037] Determining the historical conception efficiency according to the total number of cows suitable for breeding and the average conception cycle.

[0038] Through this solution, comprehensively collecting historical breeding data helps to identify the breeding history and trends of cows. By calculating the average conception cycle, the breeding efficiency of the cow population within a preset period can be analyzed, providing a reference for formulating reasonable breeding plans and breeding strategies. Analyzing the pregnancy trend helps to identify problems in the breeding process, such as seasonal changes in breeding efficiency, breeding problems of cows or groups, etc., so as to take targeted measures to improve breeding efficiency. Determining the total number of cows suitable for breeding helps to evaluate the implementation of the breeding plan, ensure that there are enough cows participating in breeding, and avoid affecting breeding efficiency due to insufficient number of cows. By calculating the historical conception efficiency, the overall effect of breeding management can be evaluated, providing data support for optimizing breeding time, selecting suitable bulls, and improving breeding techniques.

[0039] Optionally, the method further includes:

[0040] Determining the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity according to the hormone change curve, the real-time estrus intensity, and the time sequence correlation;

[0041] Comparing the time difference with a preset time difference threshold. If the time difference is less than the preset time difference threshold, the time stamp corresponding to the real-time estrus intensity is used as the optimal breeding time.

[0042] Through this solution, a comprehensive analysis of the physiological state and behavioral characteristics of cows is ensured. By analyzing the temporal correlation between the hormone change curve and the real-time estrus intensity data, the estrus cycle and intensity of cows can be predicted more accurately, thereby improving the accuracy of breeding decisions. By calculating the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity, the optimal breeding time can be determined more precisely, improving the success rate of breeding. The setting of the preset time difference threshold helps to standardize the judgment criteria for breeding time, ensuring the consistency and repeatability of breeding time. By comparing the time difference with the preset time difference threshold, the optimal breeding time can be determined more precisely, thereby optimizing the breeding strategy, increasing the conception rate and pregnancy success rate, and further improving the breeding efficiency of the cow farm.

[0043] Optionally, the basic data includes cow development data, and the analysis of the cow age and the body condition of the cow to determine the difficulty of parturition includes:

[0044] According to the cow development data and the cow age, determine the pelvic development of each current cow;

[0045] Analyze the cow development data to determine the body type state of each current cow;

[0046] According to the pregnancy data, determine the number of parturitions of each current cow;

[0047] According to the body type state, the number of parturitions and the pelvic development, determine the difficulty of parturition.

[0048] Through this solution, by analyzing the development data of cows, the pelvic development can be identified, which helps to predict the difficulty of parturition and formulate corresponding management measures. Poor pelvic development can lead to dystocia, so early identification helps to take preventive measures. Evaluating the body type state of cows helps to analyze their overall health status and reproductive potential. Being too thin or too fat can both cause reproductive problems, so adjusting the body type of cows helps to improve reproductive efficiency. Analyzing the number of parturitions of each cow helps to evaluate its reproductive history and experience. Cows with multiple parturitions have a higher parturition success rate than first-calving cows, but also face a higher risk of dystocia. By comprehensively considering the body type state, the number of parturitions and the pelvic development, the difficulty of parturition of each cow can be predicted more accurately. This helps to formulate personalized parturition management plans, reduce the risk of dystocia, and improve the survival rates of cows and calves.

[0049] Optionally, the analysis of the estrus characteristics to determine the estrus similarity between any two cows includes:

[0050] According to the estrus characteristics, analyze the estrus cycle waveform to determine the waveform parameter vector;

[0051] Extract hormone characteristic parameters according to the hormone change curve;

[0052] Calculate the multi-dimensional feature similarity between any two cows according to the waveform parameter vector, real-time estrus intensity and hormone characteristic parameters.

[0053] Through this solution, by analyzing the estrus cycle waveform and extracting the waveform parameter vector, the estrus cycle characteristics of each cow can be quantified. By extracting the characteristic parameters of the hormone change curve, the physiological state of the cow and different stages of the estrus cycle can be deeply analyzed, which is helpful for breeding management. By calculating the multi-dimensional feature similarity between any two cows, the similarity of cows in estrus behavior and physiological state can be comprehensively evaluated, providing a scientific basis for the division of breeding batches.

[0054] In a second aspect, the present application provides a digital information management system for a breeding cow farm, and the system includes:

[0055] A data acquisition module for acquiring the basic data of cows; the basic data includes estrus behavior data, pregnancy data and historical breeding data;

[0056] A breeding determination module for determining the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data; and determining the group breeding batches according to the estrus characteristics;

[0057] A priority adjustment module for adjusting the batch priority of the group breeding batches according to the pregnancy data.

[0058] Optionally, when the breeding determination module determines the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data, it is used for:

[0059] Analyze the estrus behavior data to determine the change in activity level within a preset time period and the duration of mounting within a preset time period;

[0060] Determine the real-time estrus intensity according to the change in activity level and the duration of mounting;

[0061] Analyze the historical breeding data to determine the conception efficiency weight;

[0062] Determine the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity;

[0063] Analyze the estrus cycle waveform to determine the estrus characteristics.

[0064] Optionally, when the breeding determination module determines the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity, it is used for:

[0065] Obtain the individual data and environmental data of cows;

[0066] Analyze the individual data to determine the hormone change curve;

[0067] Analyze the hormone change curve to determine the temporal correlation between the hormone change curve and the real-time estrus intensity;

[0068] Determine the starting point of the estrous cycle according to the temporal correlation;

[0069] Determine the estrous cycle waveform according to the starting point, the conception efficiency weight and the environmental data.

[0070] Optionally, when the breeding determination module determines the group breeding batches according to the estrus characteristics, it is used for:

[0071] Analyze the estrus characteristics to determine the estrus similarity between any two cows;

[0072] Determine the group breeding batches according to the estrus similarity.

[0073] Optionally, when the priority adjustment module adjusts the batch priority of the group breeding batches according to the pregnancy data, it is used for:

[0074] Determine the age of the cow and the body condition of the cow according to the pregnancy data;

[0075] Analyze the age of the cow and the body condition of the cow to determine the difficulty of parturition;

[0076] Determine the historical conception efficiency according to the historical breeding data;

[0077] Adjust the batch priority of the group breeding batches according to the historical conception efficiency and the difficulty of parturition.

[0078] Optionally, when the priority adjustment module determines the historical conception efficiency according to the historical breeding data, it is used for:

[0079] Determine the average conception cycle and the pregnancy trend within a historical preset period according to the historical breeding data;

[0080] Determine the total number of suitable breeders within a historical preset period according to the pregnancy trend;

[0081] Determine the historical conception efficiency according to the total number of suitable breeders and the average conception cycle.

[0082] Optionally, the digital information management system for productive cow farms further includes a timing comparison module, which is used for:

[0083] Determine the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity according to the hormone change curve, the real-time estrus intensity and the temporal correlation;

[0084] Compare the time difference with a preset time difference threshold. If the time difference is less than the preset time difference threshold, use the time stamp corresponding to the real-time estrus intensity as the optimal breeding time.

[0085] Optionally, the basic data includes the development data of the female cows. When the priority adjustment module analyzes the cow age and the physical condition of the female cows to determine the difficulty of delivery, it is used for:

[0086] Determine the pelvic development of each current female cow according to the development data of the female cows and the cow age;

[0087] Analyze the development data of the female cows to determine the body type state of each current female cow;

[0088] Determine the number of deliveries of each current female cow according to the pregnancy data;

[0089] Determine the difficulty of delivery according to the body type state, the number of deliveries and the pelvic development;

[0090] Optionally, when the breeding determination module analyzes the estrus characteristics to determine the estrus similarity between any two female cows, it is used for:

[0091] Analyze the estrus cycle waveform according to the estrus characteristics to determine the waveform parameter vector;

[0092] Extract hormone characteristic parameters according to the hormone change curve;

[0093] Calculate the multi-dimensional characteristic similarity between any two female cows according to the waveform parameter vector, the real-time estrus intensity and the hormone characteristic parameters. Description of the Drawings

[0094] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0095] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0096] Figure 2 It is a flowchart of a method for digital information management of a breeding female cow farm provided by an embodiment of the present application;

[0097] Figure 3 It is a schematic diagram of the structure of a digital information management system for a breeding female cow farm provided by an embodiment of the present application. Detailed Embodiments

[0098] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0099] In addition, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0100] The following further describes the embodiments of this application in detail with reference to the accompanying drawings of the specification.

[0101] In large-scale breeding, artificial breeding management not only requires a large amount of time and energy, but is also cumbersome and prone to omissions, easily missing the optimal breeding time, resulting in breeding failure or delay, and thus affecting the overall breeding efficiency. Therefore, the breeding work faces huge management difficulties and challenges.

[0102] Based on this, this application provides a digital information management system and method for a breeding cow farm, which acquires the basic data of cows; the basic data includes estrus behavior data, pregnancy data, and historical breeding data; determines the estrus characteristics of each cow according to the estrus behavior data and historical breeding data; determines the group breeding batches according to the estrus characteristics; and adjusts the batch priority of the group breeding batches according to the pregnancy data. By collecting physiological indicators, real-time monitoring of the behavior and environmental data of cows is realized, reducing the time and error of manual data collection. By analyzing the estrus behavior data and historical breeding data, the estrus characteristics of each cow can be determined more accurately, providing a scientific basis for breeding decisions, improving the accuracy and success rate of breeding. According to the estrus characteristics, the cows are divided into different breeding batches, optimizing the breeding plan, improving the overall breeding efficiency, and reducing the breeding cost. According to the pregnancy data and the conception efficiency weight, the priority of the breeding batches is adjusted to ensure the maximization of breeding efficiency, improving the conception rate and pregnancy success rate. By precisely analyzing the estrus cycle waveform characteristics, pregnancy status, and historical conception efficiency of cows, the division of group breeding batches is further optimized, and the breeding timing of each cow is adjusted according to real-time data, more effectively improving the breeding efficiency of cows and promoting the sustainable development of the entire aquaculture industry.

[0103] Figure 1A schematic diagram of an application scenario provided for this application. When breeding in livestock farming, the method provided for this application is applied.

[0104] Specifically, the method provided for this application is applied to any server. The server interacts with a number of sensors deployed in the livestock farm, obtains the basic data of the cows through the number of sensors, realizes the real-time monitoring of the behavior and environmental data of the cows, and reduces the time and error of manual data collection. By analyzing the estrus behavior data and historical breeding data, the estrus characteristics of each cow can be determined more accurately, providing a scientific basis for breeding decisions, improving the accuracy and success rate of breeding. According to the estrus characteristics, the cows are divided into different breeding batches, the breeding plan is optimized, the overall breeding efficiency is improved, and the breeding cost is reduced. According to the pregnancy data and the weight of the conception efficiency, the priority of the breeding batches is adjusted to ensure the maximization of the breeding efficiency, and the conception rate and pregnancy success rate are improved. By accurately analyzing the estrus cycle waveform characteristics, pregnancy status, and historical conception efficiency of the cows, the division of the group breeding batches is further optimized, and the breeding timing of each cow is adjusted according to the real-time data, more effectively improving the breeding efficiency of the cows and promoting the sustainable development of the entire breeding industry.

[0105] The specific implementation method can refer to the following embodiments.

[0106] Figure 2 A flowchart of a digital information management method for a breeding cow farm provided for an embodiment of this application. The method of this embodiment can be applied to the server in the above scenario. As Figure 2 shown, the method includes:

[0107] S201. Obtain the basic data of the cows;

[0108] The basic data can be a collection of various data and information for recording the digital information management method of the cow farm. The basic data includes estrus behavior data, pregnancy data, and historical breeding data.

[0109] The estrus behavior data can be data recording various behavioral characteristics such as the change in activity level, mounting behavior, and standing acceptance time during estrus of the cows.

[0110] The pregnancy data can be various physiological indicators and data such as hormone levels, ultrasound examination results, pregnancy duration, parity, etc. during the pregnancy of the cows.

[0111] The historical breeding data can be records such as the conception rate, calving interval, breeding ability decay law, breeding index optimization value, etc. of the past breeding activities of the cows.

[0112] Specifically, several sensors such as motion sensors, temperature sensors, and humidity sensors are installed in the cowshed to monitor the estrus behavior of cows and the environmental data of the cowshed in real time. Physiological indicators such as the body temperature, heart rate, and hormone levels of cows are monitored through biosensors. Through automated behavior analysis software, the obtained physiological indicators and estrus behaviors are analyzed to record the estrus behaviors of cows. An ultrasonic device is used to regularly examine the uterus of cows to determine whether they are pregnant and the development of embryos. Through blood or urine samples, the hormone levels in the cows are detected to judge whether they are pregnant and the progress of pregnancy. A database containing the breeding history of each cow is established to record historical breeding data such as the conception rate, number of deliveries, calving interval, and decline in reproductive ability of each cow.

[0113] S202. Determine the estrus characteristics of each cow based on the estrus behavior data and historical breeding data; determine the group breeding batches according to the estrus characteristics;

[0114] The estrus characteristics can be unique physiological and behavioral characteristics such as the estrus cycle waveform, estrus intensity, estrus duration, and estrus frequency shown by cows during estrus.

[0115] The group breeding batches can be dividing cows into different breeding groups according to the estrus characteristics. Each group has different batches and there are differences in the breeding time.

[0116] Specifically, using the collected estrus behavior data such as changes in activity level, mounting behavior, and standing time accepting mounting, analyze the estrus behavior patterns of each cow. Refer to the historical breeding data such as the conception rate, calving interval, and decline law of reproductive ability of each cow to predict the current estrus cycle and conception probability. By analyzing the estrus behavior data and historical breeding data, determine the estrus characteristics such as the estrus intensity, estrus cycle length, and conception probability of each cow. According to the estrus characteristics of each cow, calculate the estrus similarity between any two cows. Determine the group breeding batches of cows based on the calculated estrus similarity.

[0117] S203. Adjust the batch priority of the group breeding batches according to the pregnancy data.

[0118] The batch priority can be the priority of which batch to breed first according to the pregnancy data and historical breeding data.

[0119] Specifically, using the collected pregnancy data such as cow age, body condition, pregnancy duration, number of deliveries, and conception rate, evaluate the pregnancy status and reproductive ability of each cow. According to the pregnancy data and the physiological characteristics of the cows, evaluate the difficulty of delivery of each cow. Determine the conception efficiency weight of each cow according to the historical breeding data. Adjust the batch priority of the group breeding batches according to the pregnancy data and the conception efficiency weight.

[0120] Through this solution, by collecting physiological indicators, real-time monitoring of the behavior and environmental data of cows is achieved, reducing the time and error of manual data collection. By analyzing estrus behavior data and historical breeding data, the estrus characteristics of each cow can be determined more accurately, providing a scientific basis for breeding decisions, improving the accuracy and success rate of breeding. According to the estrus characteristics, cows are divided into different breeding batches, optimizing the breeding plan, improving the overall breeding efficiency, and reducing breeding costs. According to the pregnancy data and the weight of conception efficiency, the priority of the breeding batches is adjusted to ensure the maximization of breeding efficiency, improving the conception rate and pregnancy success rate. By precisely analyzing the estrus cycle waveform characteristics, pregnancy status, and historical conception efficiency of cows, the division of the group breeding batches is further optimized, and the breeding timing of each cow is adjusted according to real-time data, more effectively improving the breeding efficiency of cows and promoting the sustainable development of the entire aquaculture industry.

[0121] In some embodiments, analyze the estrus behavior data to determine the change in activity level within a preset time period and the duration of mounting within the preset time period; according to the change in activity level and the duration of mounting, determine the real-time estrus intensity; analyze the historical breeding data to determine the weight of conception efficiency; according to the weight of conception efficiency and the real-time estrus intensity, determine the estrus cycle waveform; analyze the estrus cycle waveform to determine the estrus characteristics.

[0122] The preset time period can be a certain time range set for analyzing the estrus behavior of cows, pre-stored in the server, and called when in use.

[0123] The change in activity level can be the increase or decrease in the activity level of cows within the preset time period.

[0124] The duration of mounting can be the length of time that a cow's behavior of mounting other cows lasts.

[0125] The real-time estrus intensity can be the intensity of a cow's estrus evaluated in real time based on behavioral characteristics such as the change in the activity level of the cow and the duration of mounting.

[0126] The weight of conception efficiency can be the weight of conception efficiency assigned to each cow according to the historical breeding data of the cow.

[0127] The estrus cycle waveform can be a waveform diagram of the change in hormone levels during a cow's estrus period.

[0128] Specifically, use the already installed motion sensors and cameras to collect the activity level and behavior data of cows in real time. Use mathematical analysis means to analyze the activity level data and mounting behavior data to determine the change in activity level and the duration of mounting of each cow within the preset time period. Combine the change in activity level and the duration of mounting to construct a real-time estrus intensity index and calculate the real-time estrus intensity of each cow.

[0129] Analyze historical breeding data to determine the number of historical successful conceptions, the total number of inseminations, and the average conception cycle, and then calculate the conception efficiency weight for each cow using the following formula (1):

[0130]

[0131] Where, W e represents the conception efficiency weight for each cow; N s represents the number of historical successful conceptions; N t represents the total number of inseminations; D a represents the average conception cycle.

[0132] Based on the historical conception efficiency weight and the real-time estrus intensity, determine the starting point of the estrus cycle (the overlapping period of the hormone drop point and the sudden increase point of estrus behavior) through time series alignment technology. Use the sliding window algorithm to smooth the estrus intensity to generate an estrus cycle waveform, and the peak of the waveform can be considered as an optimal insemination timing. Analyze the changes in the estrus cycle waveform to determine the estrus characteristics of each cow, such as estrus intensity and estrus cycle pattern.

[0133] Through this solution, by analyzing the changes in activity level and the duration of mounting, the estrus behavior of cows can be identified more accurately, the recognition rate of estrus characteristics can be improved, which helps to reduce the risk of missing the optimal insemination timing, thereby increasing the conception rate and pregnancy success rate. The determination of the real-time estrus intensity helps to more accurately predict the optimal insemination timing for each cow, thus optimizing the insemination plan and improving the insemination efficiency. By analyzing historical breeding data, the reproductive ability and conception probability of each cow can be determined. The determination of the estrus cycle waveform helps to more accurately predict the estrus cycle of each cow, thereby providing a scientific basis for insemination decisions. By analyzing the estrus cycle waveform, unique estrus characteristics of each cow, such as the length of the estrus cycle and the trend of waveform changes, can be identified, which helps to optimize the insemination strategy and improve the reproductive efficiency.

[0134] In some embodiments, obtain the individual data and environmental data of the cows; analyze the individual data to determine the hormone change curve; analyze the hormone change curve to determine the temporal correlation between the hormone change curve and the real-time estrus intensity; based on the temporal correlation, determine the starting point of the estrus cycle; based on the starting point, conception efficiency weight, and environmental data, determine the estrus cycle waveform.

[0135] The individual data can be detailed information about the age, weight, health status, reproductive history, etc. of each cow.

[0136] The environmental data can be environmental factor data such as temperature, humidity, light, and feed quality that affect the reproduction of cows.

[0137] The hormone change curve can be a curve showing the change of hormone levels in cows over time during the estrus cycle.

[0138] The temporal correlation can be the relationship between the hormone change curve and the estrus intensity of the cow.

[0139] The estrous cycle can be the entire physiological process of a cow from the start of one estrus to the start of the next estrus.

[0140] The starting point can be the starting point of the estrous cycle in the hormone change curve, that is, the point where the hormone level begins to rise.

[0141] Specifically, collect individual data such as the age, weight, health status, reproductive history, genetic information, and body type characteristics of each cow. Collect environmental data such as temperature, humidity, light, and feed quality. Use enzyme-linked immunosorbent assay (ELISA) to detect the progesterone concentration in the health status. According to the detection results, construct a hormone time series to obtain a hormone change curve. Integrate the hormone change curve with the real-time estrus intensity data, and use statistical analysis software to analyze the temporal correlation between the hormone change curve and the real-time estrus intensity data to determine the strength and direction of the relationship between the two. According to the results of the temporal correlation analysis, identify the correlation points such as the peak hormone level and the peak estrus behavior between the hormone change curve and the real-time estrus intensity. By identifying the correlation points, confirm the starting point of the estrous cycle. According to the determined starting point of the estrous cycle, the conception efficiency weight, and the environmental data, use curve fitting technology to construct the estrous cycle waveform of each cow.

[0142] Through this solution, ensure the comprehensive identification of the individual characteristics of the cow and environmental factors. By analyzing the individual data and constructing the hormone change curve of each cow, it helps to identify the estrous cycle of the cow and predict the optimal breeding time. By analyzing the temporal correlation between the hormone change curve and the real-time estrus intensity, more accurately predict the estrous cycle and intensity of the cow, thereby improving the accuracy of breeding decisions. Determining the starting point of the estrous cycle helps to predict the ovulation time of the cow, thereby optimizing the breeding time window and increasing the conception rate. By comprehensively considering the starting point, the conception efficiency weight, and the environmental data, construct a more accurate estrous cycle waveform, provide a more precise reference for breeding decisions, further optimize the breeding strategy, and improve the breeding efficiency.

[0143] In some embodiments, analyze the estrus characteristics to determine the estrus similarity between any two cows; according to the estrus similarity, determine the group breeding batches.

[0144] The estrus similarity can be the degree of similarity in estrus behavior characteristics between two or more cows.

[0145] Specifically, waveform features such as cycle length, rising slope, peak value, etc. are extracted from the estrous cycle waveform; hormone features such as progesterone change rate, estrogen change rate, etc. are extracted. Using mathematical analysis methods, the estrous similarity between any two cows is calculated based on the above factors. According to the calculation result of the similarity, a similarity threshold is set to determine which cows can be divided into the same breeding batch. According to the set similarity threshold, cows with similar estrous characteristics are divided into different breeding batches, thereby determining the group breeding batches.

[0146] Through this solution, by analyzing the estrous behavior data, the estrous characteristics of each cow are accurately identified, improving the analysis of the estrous behavior of cows. By calculating the estrous similarity between any two cows, cows are effectively divided into different breeding batches, optimizing the breeding plan, improving the breeding efficiency, and reducing the risk of missing the best breeding time. According to the estrous similarity, cows with similar estrous characteristics are divided into different breeding batches to ensure that cows in the same batch are in estrus within a similar time period, thus facilitating centralized management and breeding. By determining the group breeding batches, the breeding strategy is optimized, the conception rate and pregnancy success rate are increased, and the breeding cost is reduced.

[0147] In some embodiments, according to the pregnancy data, the cow age and the body condition of the cow are determined; the cow age and the body condition of the cow are analyzed to determine the difficulty of parturition; according to the historical breeding data, the historical conception efficiency is determined; according to the historical conception efficiency and the difficulty of parturition, the batch priority of the group breeding batches is adjusted.

[0148] The cow age can be the age of the cow and is one of the important factors for evaluating the reproductive ability and parturition difficulty of the cow.

[0149] The body condition of the cow can be the physical condition and body type characteristics of the cow such as body weight, body type, fat thickness, muscle mass, etc.

[0150] The difficulty of parturition can be the degree of difficulty encountered by the cow during parturition.

[0151] The historical conception efficiency can be the conception success rate of the cow in past breeding activities, usually evaluated through historical breeding data.

[0152] Specifically, the age of each cow is determined through the birth record or ear tag information of the cow. The body condition of each cow such as body weight, body type, fat thickness, etc. is evaluated through body condition scoring or weight record. According to the pregnancy data, the state of each cow during pregnancy is determined, thereby determining the parturition difficulty of each cow at the current cow age and body condition. In a specific implementation manner, a difficulty assessment model can be established, and data such as cow age and body condition that can evaluate the difficulty of parturition in the historical breeding data are used as training samples, so that the model can determine the parturition difficulty of the current cow according to the cow age and body condition.

[0153] Determine the historical conception efficiency of each cow based on historical breeding data. Comprehensively consider the historical conception efficiency and calving difficulty of each cow, and adjust its priority in the group breeding batches.

[0154] Through this solution, it is ensured that a comprehensive analysis of the individual characteristics of cows and environmental factors is conducive to formulating personalized breeding management plans. By analyzing the cow age and the body condition of cows, the calving difficulty of each cow can be evaluated more accurately, reducing the risk of dystocia and increasing the survival rates of cows and calves. By analyzing historical breeding data, the breeding ability and conception probability of each cow can be analyzed, which helps to select cows with better breeding performance for breeding. By comprehensively considering the historical conception efficiency and calving difficulty, the batch priority of breeding batches can be adjusted more effectively, optimizing the breeding strategy, increasing the conception rate and pregnancy success rate, reducing the breeding cost, and ensuring the sustainable development and economic benefits of the farm.

[0155] In some embodiments, based on historical breeding data, determine the average conception cycle and pregnancy trend within a historical preset period; according to the pregnancy trend, determine the total number of cows suitable for breeding within the historical preset period; according to the total number of cows suitable for breeding and the average conception cycle, determine the historical conception efficiency.

[0156] The historical preset period can be a certain time range set for analyzing breeding efficiency in the past cow breeding management.

[0157] The average conception cycle can be the average time length from breeding to conception confirmation for all inseminated cows.

[0158] The pregnancy trend can be the change of the cow pregnancy process over time.

[0159] The total number of cows suitable for breeding can be the total number of cows suitable for breeding within the historical preset period.

[0160] Specifically, for each cow, use historical breeding data and adopt mathematical analysis means to calculate the time interval from breeding to conception confirmation, so as to calculate the average value of the conception cycles of all cows to obtain the average conception cycle within the historical preset period. Analyze historical breeding data to determine pregnancy trends such as the difference in pregnancy rates in different seasons over time. Analyze the pregnancy trend to determine the total number of cows suitable for breeding within the historical preset period. According to the average conception cycle, pregnancy trend and total number of cows suitable for breeding, calculate the percentage of the number of cows with successful conception in the total number of inseminated cows, that is, the historical conception efficiency.

[0161] Through this solution, comprehensively collecting historical breeding data helps to identify the breeding history and trends of cows. By calculating the average conception cycle, the breeding efficiency of the cow population within a preset period can be analyzed, providing a reference for formulating a reasonable breeding plan and breeding strategy. Analyzing the pregnancy trend helps to identify problems in the breeding process, such as seasonal changes in breeding efficiency, breeding problems of individual cows or groups, etc., so as to take targeted measures to improve breeding efficiency. Determining the total number of cows suitable for breeding helps to evaluate the implementation of the breeding plan, ensure that there are enough cows participating in breeding, and avoid affecting breeding efficiency due to insufficient number of cows. By calculating the historical conception efficiency, the overall effect of breeding management can be evaluated, providing data support for optimizing breeding time, selecting suitable bulls, and improving breeding techniques.

[0162] In some embodiments, according to the hormone change curve, real-time estrus intensity, and time sequence correlation, determine the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity; compare the time difference with a preset time difference threshold. If the time difference is less than the preset time difference threshold, then use the time stamp corresponding to the real-time estrus intensity as the optimal breeding time.

[0163] The time difference can be the time interval between the real-time estrus intensity and the hormone change corresponding to the intensity.

[0164] The preset time difference threshold can be a time difference threshold set according to experience and research results for judging whether the time difference between the real-time estrus intensity and the hormone change is within a reasonable range. It is stored in the server in advance and called when in use.

[0165] The optimal breeding time can be the time point in the cow's estrus cycle that is most conducive to successful conception.

[0166] Specifically, integrate the hormone change curve, real-time estrus intensity data time sequence correlation together, use statistical analysis software to determine the relationship strength and direction between the two. Analyze the time sequence correlation to determine the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity. According to the research and experience of reproductive physiology, set a preset time difference threshold for judging whether the time difference between the real-time estrus intensity and the hormone change is within a reasonable range. Compare the calculated time difference with the preset time difference threshold. If the time difference is less than the preset time difference threshold, then use the time stamp corresponding to the real-time estrus intensity as the optimal breeding time.

[0167] Through this solution, a comprehensive analysis of the physiological state and behavioral characteristics of cows is ensured. By analyzing the temporal correlation between the hormone change curve and the real-time estrus intensity data, the estrus cycle and intensity of cows can be predicted more accurately, thereby improving the accuracy of breeding decisions. By calculating the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity, the optimal breeding time can be determined more precisely, improving the success rate of breeding. The setting of the preset time difference threshold helps to standardize the judgment criteria for breeding time, ensuring the consistency and repeatability of breeding time. By comparing the time difference with the preset time difference threshold, the optimal breeding time can be determined more precisely, thereby optimizing the breeding strategy, improving the conception rate and pregnancy success rate, and further improving the breeding efficiency of the cowshed.

[0168] In some embodiments, according to the development data and age of the cows, the pelvic development of each current cow is determined; the development data of the cows is analyzed to determine the body shape state of each current cow; according to the pregnancy data, the number of deliveries of each current cow is determined; and according to the body shape state, the number of deliveries and the pelvic development, the difficulty of delivery is determined.

[0169] The development data of the cows can be growth and development records such as weight gain, body measurement, skeletal development, nutrient intake, and health status during the period from birth to maturity of the cows.

[0170] The pelvic development can be the shape, size, and structural development status of the cow pelvis.

[0171] The body shape state can be the body condition and body shape characteristics such as the weight, body shape, fat thickness, and muscle mass of the cows.

[0172] The number of deliveries can be the number of deliveries of the cows up to the current time.

[0173] Specifically, the pelvic development of each cow is evaluated through veterinary clinical examinations and ultrasonic examinations. The body shape state such as the weight, body shape, and fat thickness of each cow is evaluated through the body condition score or weight record in the development data of the cows. According to the pregnancy data such as the breeding date, pregnancy examination results, and delivery date of each cow, the number of deliveries of each cow is counted. By comprehensively analyzing the age, body shape state, number of deliveries, and pelvic development, a mathematical analysis method is used to determine the delivery difficulty of each cow.

[0174] Through this solution, by analyzing the development data of cows, the development of the pelvis is identified, which helps predict the difficulty of parturition and formulate corresponding management measures. Poor pelvic development can lead to dystocia, so early identification helps take preventive measures. Evaluating the body condition of cows helps analyze their overall health status and reproductive potential. Being too thin or too fat can both cause reproductive problems, so adjusting the body condition of cows helps improve reproductive efficiency. Analyzing the number of parturitions of each cow helps evaluate its reproductive history and experience. Cows with multiple parturitions have a higher parturition success rate than first-calving cows, but also face a higher risk of dystocia. By comprehensively considering the body condition, the number of parturitions, and the pelvic development, the difficulty of parturition of each cow can be predicted more accurately, a personalized parturition management plan can be formulated, the risk of dystocia can be reduced, and the survival rates of cows and calves can be improved.

[0175] In some embodiments, according to the estrus characteristics, the estrus cycle waveform is analyzed to determine the waveform parameter vector; according to the hormone change curve, the hormone characteristic parameters are extracted; according to the waveform parameter vector, the real-time estrus intensity, and the hormone characteristic parameters, the multi-dimensional feature similarity between any two cows is calculated.

[0176] The waveform parameter vector can be a set of parameters that can quantify the estrus cycle characteristics extracted from the estrus cycle waveform of cows.

[0177] The hormone characteristic parameters can be a set of characteristic parameters that reflect the physiological state of cows and different stages of the estrus cycle extracted from the hormone level data of cows.

[0178] The multi-dimensional feature similarity can be the multi-dimensional feature similarity calculated by comparing the estrus cycle waveform parameter vectors, the real-time estrus intensity, and the hormone characteristic parameters of two or more cows.

[0179] Specifically, according to the estrus characteristics, waveform parameter vectors such as the waveform amplitude, cycle length, and peak time of the estrus cycle are extracted. Hormone characteristic parameters such as the hormone peak level and hormone change rate are extracted from the hormone level data. The estrus cycle waveform parameter vector, the real-time estrus intensity, and the hormone characteristic parameters are integrated into a multi-dimensional feature set. Similarity calculation algorithms such as Euclidean distance and cosine similarity are used to calculate the multi-dimensional feature similarity between any two cows.

[0180] Through this solution, by analyzing the estrus cycle waveform and extracting the waveform parameter vector, the estrus cycle characteristics of each cow can be quantified. By extracting the characteristic parameters of the hormone change curve, the physiological state of cows and different stages of the estrus cycle can be analyzed in depth, which helps reproductive management. By calculating the multi-dimensional feature similarity between any two cows, the similarity of cows in estrus behavior and physiological state can be comprehensively evaluated, providing a scientific basis for the division of breeding batches.

[0181] Figure 3The structural schematic diagram of a digital information management system for breeding cow farms provided by an embodiment of the present application is as follows Figure 3 As shown, the digital information management system 300 for breeding cow farms in this embodiment includes: a data acquisition module 301, a breeding determination module 302, and a priority adjustment module 303.

[0182] The data acquisition module 301 is used to acquire the basic data of cows; the basic data includes estrus behavior data, pregnancy data, and historical breeding data;

[0183] The breeding determination module 302 is used to determine the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data; according to the estrus characteristics, determine the group breeding batches;

[0184] The priority adjustment module 303 is used to adjust the batch priority of the group breeding batches according to the pregnancy data.

[0185] Optionally, when the breeding determination module 302 determines the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data, it is used to:

[0186] Analyze the estrus behavior data to determine the activity change within a preset time period and the mounting duration within a preset time period;

[0187] Determine the real-time estrus intensity according to the activity change and the mounting duration;

[0188] Analyze the historical breeding data to determine the conception efficiency weight;

[0189] Determine the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity;

[0190] Analyze the estrus cycle waveform to determine the estrus characteristics.

[0191] Optionally, when the breeding determination module 302 determines the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity, it is used to:

[0192] Obtain the individual data and environmental data of cows;

[0193] Analyze the individual data to determine the hormone change curve;

[0194] Analyze the hormone change curve to determine the timing correlation between the hormone change curve and the real-time estrus intensity;

[0195] Determine the starting point of the estrus cycle according to the timing correlation;

[0196] Determine the estrous cycle waveform based on the starting point, the conception efficiency weight, and the environmental data.

[0197] Optionally, when determining the group breeding batches according to the estrus characteristics, the breeding determination module 302 is used for:

[0198] Analyze the estrus characteristics to determine the estrus similarity between any two cows;

[0199] Determine the group breeding batches according to the estrus similarity.

[0200] Optionally, when adjusting the batch priority of the group breeding batches according to the pregnancy data, the priority adjustment module 303 is used for:

[0201] Determine the age of the cow and the body condition of the cow according to the pregnancy data;

[0202] Analyze the age of the cow and the body condition of the cow to determine the difficulty of delivery;

[0203] Determine the historical conception efficiency according to the historical breeding data;

[0204] Adjust the batch priority of the group breeding batches according to the historical conception efficiency and the difficulty of delivery.

[0205] Optionally, when determining the historical conception efficiency according to the historical breeding data, the priority adjustment module 303 is used for:

[0206] Determine the average conception cycle and pregnancy trend within a historical preset period according to the historical breeding data;

[0207] Determine the total number of suitable breeding cows within a historical preset period according to the pregnancy trend;

[0208] Determine the historical conception efficiency according to the total number of suitable breeding cows and the average conception cycle.

[0209] Optionally, the digital information management system for productive cow farms further includes an opportunity comparison module 304, which is used for:

[0210] Determine the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity according to the hormone change curve, the real-time estrus intensity, and the timing correlation;

[0211] Compare the time difference with a preset time difference threshold. If the time difference is less than the preset time difference threshold, use the time stamp corresponding to the real-time estrus intensity as the optimal breeding opportunity.

[0212] Optionally, the basic data includes cow development data. When the priority adjustment module 303 analyzes the cow age and the physical condition of the cow to determine the difficulty of delivery, it is used for:

[0213] Determine the pelvic development of each current cow according to the cow development data and the cow age;

[0214] Analyze the cow development data to determine the body type status of each current cow;

[0215] Determine the number of deliveries of each current cow according to the pregnancy data;

[0216] Determine the difficulty of delivery according to the body type status, the number of deliveries and the pelvic development;

[0217] Optionally, when the breeding determination module 302 analyzes the estrus characteristics to determine the estrus similarity between any two cows, it is used for:

[0218] Analyze the estrus cycle waveform according to the estrus characteristics to determine the waveform parameter vector;

[0219] Extract hormone characteristic parameters according to the hormone change curve;

[0220] Calculate the multi-dimensional characteristic similarity between any two cows according to the waveform parameter vector, the real-time estrus intensity and the hormone characteristic parameters.

[0221] The system of this embodiment can be used to execute the method of any of the above embodiments. The implementation principle and technical effects are similar and will not be elaborated here.

Claims

1. A digital information management method for a breeding cow farm, characterized in that, Including: Obtain the basic data of the cows; the basic data includes estrus behavior data, pregnancy data, and historical breeding data; According to the estrus behavior data and the historical breeding data, determine the estrus characteristics of each cow; according to the estrus characteristics, determine the group breeding batches; According to the pregnancy data, adjust the batch priority of the group breeding batches.

2. The method according to claim 1, characterized in that The determining the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data includes: Analyze the estrus behavior data to determine the change in activity level within a preset time period and the duration of mounting within a preset time period; According to the change in activity level and the duration of mounting, determine the real-time estrus intensity; Analyze the historical breeding data to determine the conception efficiency weight; According to the conception efficiency weight and the real-time estrus intensity, determine the estrus cycle waveform; Analyze the estrus cycle waveform to determine the estrus characteristics.

3. The method according to claim 2, characterized in that, The determining the estrus cycle waveform according to the conception efficiency weight and the real-time estrus intensity includes: Obtain the individual data and environmental data of the cows; Analyze the individual data to determine the hormone change curve; Analyze the hormone change curve to determine the temporal correlation between the hormone change curve and the real-time estrus intensity; According to the temporal correlation, determine the starting point of the estrus cycle; According to the starting point, the conception efficiency weight, and the environmental data, determine the estrus cycle waveform.

4. The method according to claim 3, wherein The determining the group breeding batches according to the estrus characteristics includes: Analyze the estrus characteristics to determine the estrus similarity between any two cows; According to the estrus similarity, determine the group breeding batches.

5. The method according to claim 1, wherein The adjusting the batch priority of the group breeding batches according to the pregnancy data includes: According to the pregnancy data, determine the cow age and the body condition of the cows; Analyze the cow age and the body condition of the cows to determine the difficulty of delivery; According to the historical breeding data, determine the historical conception efficiency; According to the historical conception efficiency and the difficulty of delivery, adjust the batch priority of the group breeding batches.

6. The method according to claim 5, characterized in that, The determining the historical conception efficiency according to the historical breeding data includes: According to the historical breeding data, determine the average conception cycle and pregnancy trend within a historical preset time period; According to the pregnancy trend, determine the total number of suitable breeding cows within a historical preset time period; According to the total number of suitable breeding cows and the average conception cycle, determine the historical conception efficiency.

7. The method according to claim 3, characterized in that, The method further includes: According to the hormone change curve, the real-time estrus intensity, and the temporal correlation, determine the time difference between the real-time estrus intensity and the hormone change corresponding to the intensity; Compare the time difference with a preset time difference threshold. If the time difference is less than the preset time difference threshold, then use the time stamp corresponding to the real-time estrus intensity as the optimal breeding time.

8. The method according to claim 5, wherein The basic data includes cow development data. The analyzing the cow age and the body condition of the cows to determine the difficulty of delivery includes: According to the cow development data and the cow age, determine the pelvic development of each current cow; Analyze the cow development data to determine the body shape state of each current cow; According to the pregnancy data, determine the number of deliveries of each current cow; Determine the delivery difficulty according to the body shape state, the number of deliveries and the pelvic development condition.

9. The method according to claim 4, characterized in that, Analyze the estrus characteristics and determine the estrus similarity between any two cows, including: Analyze the estrus cycle waveform according to the estrus characteristics and determine the waveform parameter vector; Extract hormone characteristic parameters according to the hormone change curve; Calculate the multi-dimensional characteristic similarity between any two cows according to the waveform parameter vector, the real-time estrus intensity and the hormone characteristic parameters.

10. A digital information management system for a breeding cow farm, characterized in that, Applied to the method according to any one of claims 1-9, including: A data acquisition module for acquiring the basic data of cows; the basic data includes estrus behavior data, pregnancy data and historical breeding data; A breeding determination module for determining the estrus characteristics of each cow according to the estrus behavior data and the historical breeding data; and determining the group breeding batches according to the estrus characteristics; A priority adjustment module for adjusting the batch priority of the group breeding batches according to the pregnancy data.

Images