Prediction method, system and equipment of pasture cattle herd structure and storage medium

By combining herd status and feed data for prediction, and establishing correlation adjustment control indicators, the problem that feed factors in the existing technology are not fully considered is solved, the accuracy of herd structure prediction and the scientific nature of management decisions are improved, and the Production efficiency and health level of the ranch.

CN119067471AInactive Publication Date: 2024-12-03YIMU TECH (BEIJING CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411114073.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art does not fully consider feed data in herd structure prediction, which affects the accuracy and practicality of the prediction results and cannot provide more refined management suggestions for ranch managers.

Method used

By obtaining current and historical herd status data, feed consumption data and control indicators, establish the correlation between herd status and feed data, adjust the control indicators to predict future herd status, and provide scientific management decision support.

Benefits of technology

It improves the accuracy and reliability of herd structure prediction, helps ranch managers formulate reasonable feeding and management strategies, improve production efficiency, promptly detect potential problems such as malnutrition and disease risks, and improves herd health and production performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067471A_ABST
    Figure CN119067471A_ABST
Patent Text Reader

Abstract

The invention discloses a pasture cattle herd structure prediction method, system and device and a storage medium, and relates to the field of animal husbandry management. In the method, first data of a cattle herd state at a current moment is acquired, and the first data comprises adult cow data and backup cow data; acquiring first feed data at the current moment and second feed data in the historical data; acquiring a control index in the historical data, wherein the control index comprises a plurality of sub-indexes; establishing a first association between the to-be-predicted cattle herd state and the corresponding sub-index in the control index, establishing a second association between the second feed data and the corresponding sub-index in the control index, adjusting the control index according to the second association and the first feed data, and predicting the to-be-predicted cattle herd state according to the adjusted control index, the first association and the first data. And integrating the states of the cattle herds to be predicted to obtain a prediction result. By implementing the technical scheme provided by the invention, the state of the cattle herd in the future can be predicted more accurately in combination with the feed consumption data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of animal husbandry management, and in particular to a method, system, device and storage medium for predicting pasture herd structure. Background Art

[0002] Animal husbandry is a key pillar of agriculture, and the refined breeding and management of cattle herds are increasingly valued. In order to improve the production efficiency and health of cattle herds, ranch managers not only need to understand the current herd structure, but also need to predict the future herd structure in order to make reasonable management decisions. In this context, although existing technologies can predict herd structure based on adult cow data and reserve cow data, these technologies do not fully consider the important factor of feed during prediction, which affects the accuracy and practicality of the prediction results.

[0003] In actual ranch operations, factors such as feed quality, type, and consumption have a direct impact on the state of the herd. For example, changes in feed composition may lead to unbalanced nutritional intake of cattle, which in turn affects their growth, reproduction, and health. However, when predicting herd structure, most existing technologies ignore the deep connection between feed data and herd status, and thus fail to provide ranch managers with more refined management suggestions.

[0004] Therefore, considering the importance of feed factors in predicting herd structure, there is an urgent need for a method that can comprehensively consider feed data and herd data for scientific prediction. Summary of the invention

[0005] The present application provides a method, system, device and storage medium for predicting the structure of a ranch herd, which combines the current and historical data of the herd structure and feed consumption data, and can more accurately predict the future state of the herd, guide ranch managers to formulate reasonable feeding and management strategies, and improve production efficiency.

[0006] In a first aspect of the present application, a method for predicting pasture herd structure is provided, which is applied to a pasture management platform. The method comprises: Acquire first data of the cattle herd status at the current moment, wherein the first data includes data of adult cows and data of replacement cows, wherein the data of adult cows includes data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows, and the number of non-pregnant dry cows, and the data of replacement cows includes data of calves, data of growing cows, data of pregnant young cows, and the number of non-pregnant young cows; Acquire first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; Acquire a control indicator in historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a birth sub-indicator; A first association is established between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, a second association is established between the second feed data and the corresponding sub-indicator in the control index, the control index is adjusted according to the second association and the first feed data, the state of the cattle herd to be predicted is predicted according to the adjusted control index, the first association and the first data, and the state of the cattle herd to be predicted is integrated to obtain a prediction result.

[0007] By adopting the above technical solution, by collecting and analyzing the current herd structure data (first data), feed consumption data (first and second feed data) and historical control index data, the herd status can be accurately predicted based on actual data. This data-driven approach is more scientific and effective than traditional experience management. By establishing a first association between each herd status to be predicted and the corresponding sub-indicator in the control index, and a second association between the second feed data and the corresponding sub-indicator in the control index, the present application can comprehensively consider the mutual influence between multiple factors, thereby improving the accuracy of the prediction. This multi-factor association analysis helps to reveal the complex relationship hidden behind the data. By adjusting the control index through feed consumption data, the present application can be combined with feed data for prediction, which improves accuracy. Through the adjustment of prediction and control indicators, the present application helps to timely discover and solve potential problems, such as malnutrition, disease risks, etc., thereby improving the health level of the herd. At the same time, by optimizing the herd structure and feed management, the production performance of the herd can also be improved, such as increasing milk production and increasing reproduction rate. The present application provides scientific data support and prediction results for ranch managers, which helps them make more reasonable and effective management decisions. For example, when deciding to expand the scale of farming, adjust the herd structure or introduce new breeds, the forecast results can be used to assess the risks and benefits.

[0008] Optionally, the establishing of the first association between each cattle herd state to be predicted and the corresponding sub-indicator in the control indicator includes: determining the current first cattle herd state associated with the target cattle herd state to be predicted according to a preset relationship, and judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group; When the current first cattle herd state and the target cattle herd state to be predicted belong to the same category, selecting a first factor corresponding to the dead-elimination sub-index according to the category of the current first cattle herd state, and establishing an association between the target cattle herd state to be predicted and the first factor; When the current first cattle herd state and the target cattle herd state to be predicted do not belong to the same category, the second factor corresponding to the death sub-indicator is selected according to the category of the target cattle herd state to be predicted, and the third factor corresponding to the pregnancy sub-indicator and the fourth factor corresponding to the production sub-indicator are selected to establish an association between the target cattle herd state to be predicted and the second factor, the third factor and the fourth factor.

[0009] By adopting the above technical solution, the current first herd state associated with the target herd state to be predicted is determined according to the preset relationship, and it is judged whether they belong to the same category, so that the factors directly related to the target state can be matched more accurately. When they belong to the same category, the first factor in the dead culling sub-indicator is focused on, and when they do not belong to the same category, the relevant factors in multiple sub-indicators such as dead culling, pregnancy and production are comprehensively considered. This targeted selection helps to reduce interference factors and improve the accuracy and reliability of prediction. By establishing the association between the target herd state to be predicted and multiple sub-indicators in the control index, the present application provides more comprehensive and scientific data support for ranch managers. According to these associations, managers can more accurately evaluate the impact of different management strategies on the herd state, so as to make more reasonable and effective management decisions. This helps to optimize resource allocation, improve production efficiency and reduce operating costs. Since the present application can flexibly select the associated factors according to the category relationship between the current first herd state and the target herd state to be predicted, it has strong adaptability and flexibility. No matter what changes or challenges the ranch faces, managers can quickly adjust management strategies according to this method to adapt to new situations and needs. This adaptability and flexibility helps ensure the continued stability and competitiveness of the ranch.

[0010] Optionally, before judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group, the method further includes: The non-pregnant lactating cow data are arranged into a plurality of different first groups, wherein the first groups include lactation days and corresponding cow numbers; The data of the pregnant lactating cows are arranged into a plurality of different second groups, wherein the second groups include the number of gestation days and the corresponding number of cows; The data of the pregnant dry cows are arranged into a plurality of different third groups, wherein the third groups include the number of gestation days and the corresponding number of cows; The calf data is arranged into a plurality of different fourth groups, the fourth group including the growth days and the corresponding number of cattle; the growing cattle data is arranged into a plurality of different fifth groups, the fifth group including the growth days and the corresponding number of cattle; the pregnant young cattle data is arranged into a plurality of different sixth groups, the sixth group including the pregnancy days and the corresponding number of cattle.

[0011] By adopting the above technical solution, different types of cattle (such as non-pregnant lactating cows, pregnant lactating cows, pregnant dry cows, calves, growing cows, and pregnant young cows) are grouped according to their specific physiological states (such as lactation days, pregnancy days, and growth days) and quantities, and the herd data is processed in a refined manner. This processing helps to more accurately capture the characteristics and changing trends of each type of herd. By segmenting the herd, the behavior patterns and needs of each type of herd in different states can be more accurately identified. When it is necessary to predict the state of the herd at a certain point in the future, a more accurate prediction model can be built based on these segmented group data. Compared with considering the entire herd in general, this prediction method based on segmented groups can significantly improve the accuracy and reliability of the prediction. After the herd data is grouped according to specific standards, data analysis and monitoring can be carried out more conveniently. For example, the number of cattle, health status, production performance and other indicators of each group can be regularly counted to evaluate the feeding and management effect and find problems in time. At the same time, this grouping method also helps to establish a database of herd health and production performance to provide support for future research and decision-making. Optionally, determining the current first cattle herd state associated with the target cattle herd state to be predicted according to a preset relationship, and judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group includes: When the target cattle herd state to be predicted is 0-30 days after calf birth, determining the current first cattle herd state associated with the target cattle herd state to be predicted includes pregnant lactating cows for 206-235 days, pregnant dry cows for 206-235 days, pregnant dry cows for 236-265 days, pregnant dry cows for more than 265 days, pregnant heifers for 206-235 days, pregnant heifers for 236-265 days, and pregnant heifers for more than 265 days; It is determined that the calves born 0-30 days ago belong to the fourth group, the pregnant lactating cows 206-235 days pregnant belong to the second group, the pregnant dry cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the third group, the pregnant young cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the sixth group, and it is determined that the current first herd status and the target herd status to be predicted do not belong to the same category.

[0012] By adopting the above technical solution, the current first herd state (such as pregnant lactating cows, pregnant dry cows and pregnant young cows at different stages of pregnancy) that may be associated with the target herd state to be predicted (0-30 days after calf birth) is listed in detail, and the application establishes a clear logical chain. This logical chain helps to more accurately identify the herd state that will directly affect the target herd state to be predicted, thereby improving the accuracy of the prediction. By judging whether the current first herd state and the target herd state to be predicted belong to the same category, a forward-looking perspective is provided for ranch managers. Managers can foresee the herd state that will change in advance and make corresponding management adjustments accordingly. This foresight helps to reduce management lags and improve management efficiency. After understanding the correlation between different herd states, ranch managers can allocate resources more reasonably. For example, when it is known that the pregnant herd state will produce new calves, the feeding environment and feed resources required for the calves can be prepared in advance to ensure that the calves can be properly cared for after they are born. By accurately predicting changes in herd states and making preparations in advance, this application helps to improve the operational efficiency of the ranch. Managers can organize production and management activities more efficiently, reduce unnecessary waste and losses, and improve the overall economic benefits of the ranch.

[0013] Optionally, the selecting the second factor corresponding to the death sub-indicator according to the category of the target cattle herd state to be predicted, and selecting the third factor corresponding to the pregnancy sub-indicator and / or the fourth factor corresponding to the production sub-indicator includes: Select the 60-day-old mortality rate and the replacement cattle mortality rate from the mortality indicators according to the calf category, and the mortality indicators include the mortality rate of adult cows, the mortality rate of 60 days after calving, the mortality rate of replacement cattle and the 60-day-old mortality rate; The production sub-indicators including the abortion rate of adult cows, the abortion rate of reserve cows and the premature birth rate are selected according to the categories of pregnant lactating cows, pregnant dry cows and pregnant heifers. The pregnancy sub-indicators include the 21-day pregnancy rate of adult cows and the 21-day pregnancy rate of reserve cows. The production sub-indicators include the abortion rate of adult cows, the abortion rate of reserve cows, the survival rate of first-born cows, the survival rate of multiparous cows and the premature birth rate.

[0014] By adopting the above technical scheme, the specific factors in the death sub-indicator, pregnancy sub-indicator and production sub-indicator are accurately selected according to the category of the target herd status to be predicted (such as calves, pregnant lactating cows, pregnant dry cows and pregnant young cows), and the present application ensures the pertinence and relevance of the indicator selection. This targeted selection helps to reduce unnecessary data collection and analysis work and improve management efficiency. Selecting control indicator factors closely related to the state of the target herd to be predicted can more accurately reflect the actual situation and potential risks of the state of the herd. For example, for the calf category, selecting the 60-day-old death rate and the reserve cow death rate as the death sub-indicator can more directly evaluate the survival and health status of the calf; for the pregnant lactating cows, pregnant dry cows and pregnant young cows, selecting the abortion rate of adult cows, the abortion rate of reserve cows and the premature birth rate as the production sub-indicators can more accurately predict the problems that these herds may encounter during the production process. Based on accurate prediction and evaluation results, ranch managers can make more scientific and reasonable management decisions. For example, in response to the high mortality rate of calves, managers can strengthen calf feeding management and disease prevention and control; in response to the high abortion and premature birth rates in pregnant cattle, managers can optimize breeding management strategies and improve breeding efficiency.

[0015] Optionally, the establishing of the second association between the second feed data and the corresponding sub-indicator in the control indicator includes: establishing an association between the second data of the herd structure and the proportion of feed at each level, the second data includes data of adult cows and data of replacement cows, and the proportion of feed at each level includes a first proportion of primary feed, a second proportion of secondary feed, and a third proportion of tertiary feed; A first influencing factor for a corresponding sub-indicator in the control indicator is determined according to the first proportion, and a second influencing factor for a corresponding sub-indicator in the control indicator is determined according to the second proportion.

[0016] By adopting the above technical solution, the second data of the herd structure is associated with the proportion of feed at each level, and the refinement of feed management is achieved. Managers can clearly understand the demand for feed at each level for different herds (such as adult cows and reserve cows), so as to more accurately adjust the ratio and supply of feed. This refined management helps to reduce feed waste and improve feed utilization. The proportion of feed at each level directly affects the health status and production performance of the herd, and then affects the performance of control indicators (such as mortality rate, pregnancy rate, production performance, etc.). By establishing the association between feed data and corresponding sub-indicators in the control index, and determining the influencing factors of the proportion of feed at each level on the control index, this application can more accurately predict the changing trend of the control index and provide strong decision-making support for managers. Through refined feed management and accurate prediction of control indicators, this application helps to improve the operational efficiency of the ranch. Managers can organize production and management activities more efficiently, reduce unnecessary waste and losses, and improve economic benefits. At the same time, this application also helps to improve the health status and production performance of the herd, thereby further enhancing the competitiveness of the ranch.

[0017] Optionally, the adjusting the control index according to the second association and the first feed data includes: obtaining a fourth proportion of the primary feed in the first feed data, calculating a first difference between the fourth proportion and the first proportion, and calculating a first product of the first difference and the first influencing factor; Obtaining a fifth proportion of the secondary feed in the first feed data, calculating a second difference between the fifth proportion and the second proportion, and calculating a second product of the second difference and the second influencing factor; The corresponding sub-indicator in the control indicator is adjusted according to the first product and the second product.

[0018] By adopting the above technical solution, the difference between the actual feed usage data (first feed data) and the preset or ideal feed ratio (the proportion of feed at each level in the second association) is obtained, and the product of these differences and the corresponding influencing factors is calculated, the degree of influence of feed usage deviation on the control index can be accurately quantified. This precise adjustment helps to ensure that the control index can accurately reflect the actual production situation, thereby improving the pertinence and effectiveness of management decisions. The present application avoids the drawbacks of adjusting the control index based on experience or fuzzy judgment in traditional management. Through mathematical calculations and data analysis, the adjustment direction and adjustment range can be determined more quickly and accurately. This efficient adjustment helps to reduce the trial and error costs and time waste in the adjustment process and improve the efficiency of ranch operations. By adjusting the corresponding sub-indicators in the control indicators, the ranch managers can be indirectly guided to make a more reasonable configuration of feed resources. For example, if it is found that the actual use of the first-level feed accounts for too high a proportion, resulting in an increase in certain control indicators (such as the mortality rate), the manager can reduce the supply of the first-level feed according to the adjustment results, while increasing the supply of other types of feed to optimize the feed structure and improve resource utilization efficiency. The present application guides the adjustment of control indicators based on data analysis and mathematical calculations, which enhances the scientificity and objectivity of management decisions. Managers can more confidently formulate and implement management strategies based on the adjustment results, reducing the risks of subjective assumptions and blind decision-making.

[0019] In a second aspect of the present application, a prediction system for a cattle herd structure in a pasture is provided, characterized in that it includes a quantity module, a feed module, an indicator module and a prediction module, wherein: a quantity module configured to obtain first data on the state of the cattle herd at a current moment, wherein the first data includes data of adult cows and data of replacement cows, wherein the data of adult cows includes data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows, and the number of non-pregnant dry cows, and the data of replacement cows includes data of calves, data of growing cows, data of pregnant young cows, and the number of non-pregnant young cows; A feed module, configured to obtain first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; An indicator module configured to obtain a control indicator in historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a production sub-indicator; A prediction module is configured to establish a first association between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, establish a second association between the second feed data and the corresponding sub-indicator in the control index, adjust the control index according to the second association and the first feed data, predict the state of the cattle herd to be predicted according to the adjusted control index, the first association and the first data, and integrate the state of the cattle herd to be predicted to obtain a prediction result.

[0020] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0021] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By comprehensively considering the current herd structure data (including detailed classification data of adult cows and replacement cows), current and historical feed consumption data, and historical control indicators (such as pregnancy rate, mortality rate, production performance, etc.), this application can more comprehensively reflect the actual situation of ranch operations. This multi-dimensional and multi-level data input significantly improves the accuracy and reliability of herd structure prediction; 2. Based on the prediction results, ranch managers can plan feed procurement, distribution and use more accurately to avoid resource waste or shortage. At the same time, managers can adjust breeding strategies in advance for possible changes in herd structure in the forecast, such as adjusting breeding plans and feeding management measures, so as to achieve optimal allocation and efficient use of resources. 3. By predicting the changing trend of the herd structure, ranch managers can timely discover potential business risks, such as aging of the herd and decreased production capacity, and take corresponding preventive measures, which will help reduce economic losses caused by unreasonable herd structure and improve the overall business stability and profitability of the ranch; 4. This application provides ranch managers with a scientific and objective basis for decision-making. Based on the prediction results, managers can more confidently formulate long-term development plans, adjust business strategies, optimize cattle herd structure, etc., to achieve sustainable development of the ranch; 5. Through the automated and intelligent prediction process, this application reduces the workload of ranch managers and improves management efficiency. At the same time, the intuitive display of prediction results and data analysis functions enable managers to grasp the ranch operation status more quickly and respond and adjust in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flow chart of a method for predicting pasture herd structure disclosed in an embodiment of the present application; Figure 2 It is a schematic diagram of the preliminary prediction results disclosed in the examples of this application; Figure 3 is a schematic diagram of the error rate of the preliminary prediction disclosed in the embodiment of the present application; Figure 4 It is a module schematic diagram of a prediction system for pasture cattle structure disclosed in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0024] Explanation of the reference numerals: 401, quantity module; 402, feed module; 403, indicator module; 404, prediction module; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. DETAILED DESCRIPTION

[0025] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0027] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0028] This embodiment discloses a method for predicting the structure of a pasture herd, which is applied to a pasture management platform. Figure 1 is a flow chart of a method for predicting pasture herd structure disclosed in an embodiment of the present application, such as Figure 1As shown, the method includes the following steps: S110, obtaining first data of the state of the cattle herd at the current moment, the first data including data of adult cows and data of reserve cows, the data of adult cows including data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows and the number of non-pregnant dry cows, the data of reserve cows including data of calves, data of growing cattle, data of pregnant young cows and the number of non-pregnant young cows; Adult cows refer to cows that have reached sexual maturity and started to participate in reproduction and calve and start to produce milk. Their data is crucial for evaluating the production capacity and economic benefits of the ranch. Data on non-pregnant lactating cows: This type of data refers to the number of cows that are not currently pregnant but are lactating. Data on pregnant lactating cows: This refers to the number of cows that are pregnant but still lactating. Data on pregnant dry cows: Cows that are pregnant but no longer lactating are usually in the late pregnancy and are preparing to enter the next lactation cycle. Knowing the number of such cows will help plan the next round of calving due date and lactation plan. Number of non-pregnant dry cows: This refers to the number of cows that are not pregnant and no longer lactating. These cows may be in a sub-healthy state, have mastitis or reproductive disorders, and lag behind the normal reproductive cycle of adult cows.

[0029] Reserve cows refer to cows that have not yet reached the standard of adult cows, that is, they have not experienced calving and milk production, but have the potential to become the main force of future production. Their data is crucial to assessing the sustainability of the ranch and its future production potential. Calf data: refers to newly born calves, which is the starting point for herd renewal. Understanding the number and health of calves is crucial for formulating feeding management strategies and preventing disease transmission plans. Growing cow data: refers to cows that are in the growth and development stage but have not yet reached sexual maturity. These cows are preparing for future reproduction and milk production. Understanding their growth status helps optimize feeding management and improve production performance. Pregnant young cow data: refers to young cows that are pregnant but have not yet reached the standard of adult cows, that is, young cows that have not yet calved. These cows are about to become new production forces. Understanding their pregnancy status helps predict future production plans and resource requirements. The number of non-pregnant young cows: refers to the number of young cows that are not yet pregnant. These cows are potential breeding objects. Understanding their number helps formulate breeding plans and optimize herd structure.

[0030] S120, acquiring first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; The first feed data refers to the feed consumption data collected at the current moment (or within a specific time period). The first feed data records in detail the actual consumption of different grades of feed for different herds of cattle on the ranch. Feed grades may be divided according to factors such as nutritional ingredients, raw material types, and uses, such as roughage, concentrate feed, and concentrated feed. Each grade of feed will have a corresponding consumption record for different herds of cattle. By collecting feed consumption data at the current moment, ranch managers can timely understand the actual use of feed, evaluate the feeding effect of feed, and discover possible waste or shortage problems. This is crucial for timely adjustment of feed formula and optimization of feeding management strategies. The second feed data refers to feed consumption data obtained from historical records. These data may span a longer period of time, such as the last quarter, the last year, or longer. Similar to the first feed data, the second feed data also contains the consumption of different grades of feed. But the difference is that these data provide a historical record of feed use over a period of time in the past, which is helpful for trend analysis and comparative research. By analyzing historical feed data, ranch managers can understand the changing trend of feed consumption and identify the impact of seasonality, cyclicality or other factors on feed consumption. At the same time, these data can also be used as a reference for adjusting subsequent control indicators.

[0031] S130, obtaining a control indicator in historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a production sub-indicator; Control indicators are key parameters used to monitor and evaluate the operation of a ranch. They help managers understand the production efficiency, health and reproductive performance of the ranch. These control indicators are broken down into multiple sub-indicators to more accurately reflect the performance of each aspect. The death and elimination sub-indicator focuses on the death and elimination of ranch animals and is an important indicator for evaluating the health level of ranch animals and management efficiency. Specific sub-indicators include: Mortality and culling rate of adult cows: reflects the proportion of death and culling of adult cows due to disease, accidents, old age and weakness.

[0032] Mortality and culling rate within 60 days after calving: Pay special attention to the death and culling of cows within 60 days after calving, which may be related to factors such as delivery complications and improper postpartum care.

[0033] Mortality and culling rate of reserve cattle: Assessing the mortality and culling ratio of reserve cattle helps to understand the health status and management effectiveness of the reserve cattle herd.

[0034] Mortality and culling rate at 60 days of age: This is crucial for evaluating the effectiveness of calf care and feeding management, especially the death and culling of calves within 60 days of birth.

[0035] The pregnancy sub-indicator focuses on the reproductive performance of female animals and is an important parameter for evaluating the reproductive efficiency of ranches. Specific sub-indicators include: 21-day pregnancy rate of mature cows: measures the proportion of mature cows that successfully become pregnant within 21 days after an active suspension period, reflecting the reproductive management level of the ranch and the health status of the cows.

[0036] 21-day pregnancy rate of replacement cows: Similarly, evaluating the pregnancy rate of replacement cows every 21 days after they reach the standard age for mating helps to understand the reproductive potential and reproductive management effectiveness of the replacement cow herd.

[0037] The production sub-indicators are directly related to the economic benefits and production results of the ranch. Specific sub-indicators include: Abortion rate of adult cows: reflects the proportion of abortions in adult cows during pregnancy and is an important indicator for assessing the health status of cows and the quality of reproductive management.

[0038] Heifer abortion rates: Also keeping an eye on heifer abortion rates can help identify potential reproductive problems.

[0039] Survival rate of first-calf calves: Assessing the survival rate of calves born from first-calf cows is important for maintaining and expanding the cow herd.

[0040] Survival rate of calves given birth to multiparous cows: This focuses on the survival rate of calves given birth to cows that have given birth before, reflecting the comprehensive ability of the ranch in reproduction and feeding management.

[0041] Premature birth rate: Assess the proportion of cows that give birth prematurely before their due date. Premature birth may lead to a decrease in calf survival rate and is an issue that the ranch needs to pay close attention to.

[0042] S140, establishing a first association between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, establishing a second association between the second feed data and the corresponding sub-indicator in the control index, adjusting the control index according to the second association and the first feed data, predicting the state of the cattle herd to be predicted according to the adjusted control index, the first association and the first data, and integrating the state of the cattle herd to be predicted to obtain a prediction result.

[0043] Identify the sub-indicators that have a direct and quantifiable relationship between the state of the herd to be predicted and the control indicators. Non-pregnant lactating cows: their number may be affected by control indicators such as the mortality rate of adult cows, the mortality rate of 60 days after delivery, and the pregnancy rate of adult cows on the 21st day (affecting the speed of transfer to pregnant lactating cows). Pregnant lactating cows: the change in number is closely related to the pregnancy rate of adult cows on the 21st day, the abortion rate of adult cows, and the premature birth rate. Pregnant dry cows: mainly affected by the mortality rate of 60 days after delivery, the mortality rate of adult cows, and the management of the reproductive cycle. Non-pregnant dry cows: the change in number is related to the control indicators such as the pregnancy rate of replacement cows on the 21st day and the mortality rate of replacement cows. Calf data: the mortality rate at 60 days of age, the survival rate of first-born cows, and the survival rate of multiparous cows directly affect the number and survival rate of calves. Heifers: the change in number is related to the mortality rate of replacement cows and the pregnancy rate of replacement cows on the 21st day (affecting the speed of transfer to pregnant young cows). Pregnant young cows: mainly affected by the 21-day pregnancy rate of replacement cows and the abortion rate of replacement cows. Non-pregnant young cows: changes in quantity are related to the mortality rate of replacement cows and the reproductive performance of replacement cows (such as estrus cycle and breeding success rate). Determine the impact of feed data on the sub-indicators in the above control indicators. Analyze how feed data such as feed formula, nutritional ingredients, and feeding amount affect the reproductive performance (such as pregnancy rate, abortion rate), health status (such as mortality rate), and production performance (such as milk production and calf survival rate) of adult cows and replacement cows. For example, high-quality feed may reduce mortality rate and improve reproductive performance. According to the actual situation of current feed data, adjust the control indicators such as mortality rate, pregnancy rate, and abortion rate in historical data to reflect the potential impact of feed changes on the status of the herd. Predict the number of each herd to be predicted in the future based on the adjusted control indicators. Integrate the prediction results (including quantity and status) of all herds to be predicted to evaluate the future trends of the herd structure, production capacity, health status, etc. of the entire ranch. Based on the prediction results, formulate corresponding management strategies and optimization measures to improve the overall operational efficiency and economic benefits of the ranch.

[0044] Optionally, the establishing of the first association between each cattle herd state to be predicted and the corresponding sub-indicator in the control indicator includes: determining the current first cattle herd state associated with the target cattle herd state to be predicted according to a preset relationship, and judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group; When the current first cattle herd state and the target cattle herd state to be predicted belong to the same category, selecting a first factor corresponding to the dead-elimination sub-index according to the category of the current first cattle herd state, and establishing an association between the target cattle herd state to be predicted and the first factor; When the current first cattle herd state and the target cattle herd state to be predicted do not belong to the same category, the second factor corresponding to the death sub-indicator is selected according to the category of the target cattle herd state to be predicted, and the third factor corresponding to the pregnancy sub-indicator and the fourth factor corresponding to the production sub-indicator are selected to establish an association between the target cattle herd state to be predicted and the second factor, the third factor and the fourth factor.

[0045] According to a preset relationship or rule, determine the current first herd state associated with the target herd state to be predicted. This preset relationship may be based on the actual operation of the ranch, the biological characteristics of the cattle, or the management experience. For example, for the target herd state to be predicted, "pregnant lactating cows", the current first herd state may be "non-pregnant lactating cows" (if the transition from non-pregnant to pregnant is considered) or "pregnant dry cows" (if the transition from dry period to lactation is considered). Next, determine whether the current first herd state and the target herd state to be predicted belong to the same category. The "category" here can be divided based on factors such as reproductive status, production stage, or health status. For example, the categories in this application include non-pregnant lactating cows, pregnant lactating cows, pregnant dry cows, non-pregnant dry cows, calf data, growing cows, pregnant young cows, and non-pregnant young cows. If they belong to the same type group, this means that they belong to the same category. If they belong to the same category, it means that the transition between the two states may not need to cross significant biological or management boundaries, so certain factors in the dead cow index can be focused on. When they belong to the same category: According to the category of the current first herd state, select the corresponding first factor in the death sub-indicator (such as a specific death rate or cause of death). The corresponding category can be determined based on the identifier in the group. Since the state transition is relatively smooth, it can be considered that the first factor is the main factor affecting the state of the target herd to be predicted. Therefore, the association between the target herd state to be predicted and this first factor is established. When they do not belong to the same category: This indicates that there are significant biological or management differences between the current first herd state and the target herd state to be predicted. In this case, it is necessary to consider the factors affecting the state transition more comprehensively. Second factor in the death sub-indicator: According to the category of the target herd state to be predicted, select the more specific second factor in the death sub-indicator. Third factor in the pregnancy sub-indicator: If the state transition involves a change in reproductive state (such as from never pregnant to pregnant), the third factor in the pregnancy sub-indicator (such as pregnancy rate, abortion rate, etc.) needs to be considered. Fourth factor in the production sub-indicator: If the state transition is directly related to production performance (such as from pregnant to non-pregnant), the fourth factor in the production sub-indicator needs to be considered.

[0046] The current first herd state associated with the target herd state to be predicted is determined by the preset relationship. This step ensures that the starting point of the association is accurate and consistent with the actual operation logic of the ranch. It helps the system or model to accurately find the starting point and end point in the complex and changeable herd state transition, laying the foundation for subsequent analysis and prediction. Determining whether the current first herd state and the target herd state to be predicted belong to the same category reflects a deep understanding of the state transition characteristics of different categories of herds. For state transitions of the same category, such as pregnant lactating cows 0-30 days to pregnant lactating cows 31-60 days, the main focus is on specific factors in the death and culling sub-indicator, because such transitions may be relatively stable and are mainly affected by a single factor such as mortality. For state transitions of different categories, such as from growing cattle to pregnant young cattle, it is necessary to comprehensively consider multiple sub-indicators such as death and culling, pregnancy and production, because such transitions involve more biological and management changes. When the state transition does not belong to the same category, the second factor in the death sub-indicator, the third factor in the pregnancy sub-indicator, and the fourth factor in the production sub-indicator are selected for association, which reflects the comprehensive consideration of the complex conversion process. The introduction of multiple factors enables the prediction model to more carefully reflect the various influencing factors in the state transition of the herd, thereby improving the accuracy and reliability of the prediction. The association established through the above process can provide more accurate data support for subsequent herd state predictions. The prediction model can dynamically predict the state of the herd based on these associations, combined with historical data and real-time data. At the same time, these prediction results can also provide strong decision-making support for ranch managers, helping them to better formulate breeding plans, feeding management strategies, etc., to improve the overall operational efficiency and economic benefits of the ranch.

[0047] Optionally, before judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group, the method further includes: The non-pregnant lactating cow data are arranged into a plurality of different first groups, wherein the first groups include lactation days and corresponding cow numbers; The data of the pregnant lactating cows are arranged into a plurality of different second groups, wherein the second groups include the number of gestation days and the corresponding number of cows; The data of the pregnant dry cows are arranged into a plurality of different third groups, wherein the third groups include the number of gestation days and the corresponding number of cows; The calf data is arranged into a plurality of different fourth groups, the fourth group including the growth days and the corresponding number of cattle; the growing cattle data is arranged into a plurality of different fifth groups, the fifth group including the growth days and the corresponding number of cattle; the pregnant young cattle data is arranged into a plurality of different sixth groups, the sixth group including the pregnancy days and the corresponding number of cattle.

[0048] By dividing non-pregnant lactating cows into different first groups according to the number of days of lactation, the number of cows in different lactation stages can be clearly seen. This helps to evaluate current milk production, predict future production trends, and develop corresponding feeding and management strategies to optimize milk production performance. Grouping pregnant but still lactating cows by gestation days helps to understand the impact of pregnancy on lactation performance and predict future changes in calving and lactation cycles. This is important for formulating calving plans, adjusting feeding plans, and preventing pregnancy diseases. Since the type of group cannot be accurately identified by the number of days of pregnancy alone, different identifiers can be added to different groups, so that different types of groups can be better distinguished. Similar to pregnant lactating cows, but pregnant dry cows are no longer lactating, their grouping is mainly used to track pregnancy progress, predict calving time, and prepare for the upcoming lactation cycle. By understanding the number of these cows at different stages of pregnancy, ranch managers can better plan resource allocation and feeding management. Grouping calves by growth days helps to monitor their growth and development, evaluate feeding results, and promptly discover and solve potential health problems. In addition, this will help predict the number of growing cattle available for selection in the future and plan for the long-term development of the ranch. Growing cattle are the main force of future production on the ranch. By grouping by growth days, we can clearly understand the number and health status of growing cattle of different ages, and provide a basis for formulating breeding plans, optimizing feeding management, and improving production performance. Grouping pregnant young cattle by pregnancy days will help track their pregnancy progress, predict calving time, and prepare for subsequent feeding management and production arrangements. This will also help evaluate the reproductive performance and health status of young cattle and formulate strategies for the long-term development of the ranch. Table 1 and Table 2 are the data of adult cows and reserve cows on the ranch on January 1, 2020, respectively. For example, the data of non-pregnant lactating cows can be set into multiple different first groups, including a lactation group of 0-30 days, a lactation group of 31-60 days, and a lactation group of more than 60 days, and the others are similar.

[0049] Table 1 Statistics of the number of adult cows at different lactation and pregnancy stages Table 2 Statistics of the number of replacement cattle at different stages Optionally, determining the current first cattle herd state associated with the target cattle herd state to be predicted according to a preset relationship, and judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group includes: When the target cattle herd state to be predicted is 0-30 days after calf birth, determining the current first cattle herd state associated with the target cattle herd state to be predicted includes pregnant lactating cows for 206-235 days, pregnant dry cows for 206-235 days, pregnant dry cows for 236-265 days, pregnant dry cows for more than 265 days, pregnant heifers for 206-235 days, pregnant heifers for 236-265 days, and pregnant heifers for more than 265 days; It is determined that the calves born 0-30 days ago belong to the fourth group, the pregnant lactating cows 206-235 days pregnant belong to the second group, the pregnant dry cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the third group, the pregnant young cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the sixth group, and it is determined that the current first herd status and the target herd status to be predicted do not belong to the same category.

[0050] When the target herd state to be predicted is "calf born 0-30 days", since the birth of a calf is directly related to the pregnancy state of its cow, it is necessary to find all cow groups that may be in different stages before delivery as the current first herd state. These possible current first herd states include: pregnant lactating cows at 206-235 days of pregnancy (close to the delivery period), pregnant dry cows at different stages of pregnancy (206-235 days, 236-265 days, and more than 265 days), and pregnant young cows at different stages of pregnancy (also divided into three stages). The selection of these time periods is based on the pregnancy cycle of the cow and the expected delivery period before the calf is born. Then clarify the category of each state. Here, "calf born 0-30 days" belongs to the fourth group and belongs to the "calf" category. The current first herd status associated with it, although they are all pregnant cows, is further subdivided into three different categories: "pregnant lactating cows", "pregnant dry cows" and "pregnant young cows" according to their different physiological stages (lactation, dry period, young adult period) and pregnancy time. Finally, make a category judgment. Since "calf born 0-30 days" belongs to the "calf" category, and the current first herd status associated with it all belongs to different types of groups, and thus belongs to different cow categories (pregnant lactating cows, pregnant dry cows, pregnant young cows), it can be clearly judged that the current first herd status and the target herd status to be predicted do not belong to the same category.

[0051] Through the preset relationship, the association between the specific state of calf birth 0-30 days and various states of pregnant herds is clarified. This association not only takes into account the biological characteristics of cattle (such as the relationship between pregnancy cycle and delivery time), but also reflects the actual situation in ranch operations (such as the conversion path between different herd states). This clear association provides a solid foundation for subsequent analysis and prediction. The herd states involved are refined and divided into categories, including calves, pregnant lactating cows, pregnant dry cows and pregnant young cows, and the internal states of each category (such as the number of days of pregnancy) are also subdivided. This refined division helps to more accurately understand the conversion relationship between different herd states and the factors that may affect the conversion process. Through category judgment, it is clear that the current first herd state and the target herd state to be predicted do not belong to the same category. This judgment result is crucial for the subsequent selection of appropriate control indicators and the establishment of associations. Because it points out that there are significant biological and management changes from the pregnant state to the calf birth state, it is necessary to consider multiple factors comprehensively to predict the number of calves born and the health status. Since the impact of various pregnant herd states on calf birth status is taken into account, and refined classification and accurate category judgment are performed, it can more comprehensively reflect the complexity and diversity of herd state transitions. This helps to improve the accuracy of calf birth quantity and health status prediction, and provide more reliable decision support for ranch managers.

[0052] Optionally, the selecting the second factor corresponding to the death sub-indicator according to the category of the target cattle herd state to be predicted, and selecting the third factor corresponding to the pregnancy sub-indicator and / or the fourth factor corresponding to the production sub-indicator includes: Select the 60-day-old mortality rate and the replacement cattle mortality rate from the mortality indicators according to the calf category, and the mortality indicators include the mortality rate of adult cows, the mortality rate of 60 days after calving, the mortality rate of replacement cattle and the 60-day-old mortality rate; The production sub-indicators including the abortion rate of adult cows, the abortion rate of reserve cows and the premature birth rate are selected according to the categories of pregnant lactating cows, pregnant dry cows and pregnant heifers. The pregnancy sub-indicators include the 21-day pregnancy rate of adult cows and the 21-day pregnancy rate of reserve cows. The production sub-indicators include the abortion rate of adult cows, the abortion rate of reserve cows, the survival rate of first-born cows, the survival rate of multiparous cows and the premature birth rate.

[0053] For calf categories (such as calves 0-30 days old), the main focus is on their survival rate and health status. Therefore, in the mortality sub-indicator, the 60-day mortality rate and the replacement cattle mortality rate are selected as key factors. These two indicators can reflect the early death of calves after birth, and are of great significance for evaluating the feeding and management effects, disease prevention and control measures, and genetic quality of calves. For the categories of pregnant lactating cows, pregnant dry cows, and pregnant young cows, the main focus is on their reproductive performance and production performance. Therefore, in the production sub-indicator, the abortion rate of adult cows, the abortion rate of replacement cows, and the premature birth rate are selected as key factors. These indicators can reflect the health status and reproductive ability of cattle during pregnancy, and are important for predicting the reproductive performance of the herd, formulating breeding plans, and optimizing feeding management. At the same time, although these categories also involve pregnancy status, in this context, more attention may be paid to its production performance rather than the pregnancy ability itself. Therefore, in the pregnancy sub-indicator, although the 21-day pregnancy rate of adult cows and the 21-day pregnancy rate of replacement cows are mentioned, they may not be the main analysis factors under these categories. However, this does not mean that these indicators are unimportant and they may still be key indicators in other contexts (such as evaluating the effectiveness of breeding programs).

[0054] Table 3 Actual index values ​​of Ranch A in each month from January to November 2020 Based on the monthly forecast indicators, the monthly number of mature cows and replacement cows in each stage is preliminarily predicted. The main calculation method is that the end of the period = the beginning of the period - full-term transfer-out - abortion - death + full-term transfer. The calculation steps of the example "non-pregnant lactating cows 0-30" are as follows: At the beginning of the period (i.e., the data calculated in Tables 1 and 2): the data for non-pregnant lactating cows 0-30 is 1835; Transfer: data of non-pregnant lactating cows 0-30 * (1-mortality rate 60 days after calving), the specific data is 1835 * (1-0.113); Mortality: data of non-pregnant lactating cows 0-30 * mortality rate 60 days after calving, the specific data is 1835 * 0.113; Transfer: [data of pregnant dry cows 236-265 days*(1-mortality rate of adult cows)+data of pregnant dry cows 206-235 days*(1-mortality rate of adult cows)+data of pregnant young cows 206-235 days*(1-mortality rate of reserve cows)+data of pregnant young cows 236-265 days*(1-mortality rate of reserve cows)]*premature birth rate+data of pregnant dry cows over 265 days*(1-mortality rate of adult cows)+data of pregnant young cows over 265 days*(1-mortality rate of reserve cows), the specific data is [186*(1-0.026)+55*(1-0.026)+64*(1-0.008)+67*(1-0.008)]*0.069+105*(1-0.026)+28*(1-0.008).

[0055] Other calculations are similar.

[0056] Table 4 Budget results of lactating cows at different stages in each month Figure 2 is a schematic diagram of the preliminary prediction results disclosed in the examples of this application, Figure 2 P in it refers to the budget value, R refers to the actual value, and D refers to the difference between the budget value and the actual value. Figure 2 From the result -1, it can be seen that the difference between the budget and actual number of cattle, adult cows, and reserve cattle in February-August 2020 was within 70 heads per month, while the difference was larger from September to December 2020, mostly exceeding 100 heads, among which the budgeted number of reserve cattle was 100-200 heads less. Figure 2 From the result 2, it can be seen that the difference between the budget and actual number of lactating cows, pregnant lactating cows, and non-pregnant lactating cows is mostly within 100 heads, while the budget for pregnant lactating cows from June to December 2020 is 100-300 heads more, and the budget for non-pregnant lactating cows from October to December 2020 is 100-320 heads less. Figure 2 From result 3, it can be seen that the difference between the budget and actual number of young cattle, pregnant young cattle, and non-pregnant young cattle is basically within 100 heads, but the budgeted number of young cattle and pregnant young cattle from February to August 2020 is higher than the actual number. Figure 2 It can be seen from result 4 that the difference between the budget and actual number of growing cattle, lactating calves, and weaned calves is basically within 100 heads. The budget difference of growing cattle from August to November 2020 is larger, exceeding 70 heads, and the budget difference of weaned calves from April to June and December 2020 is larger, exceeding 60 heads. Figure 2 From result -5, it can be seen that the difference between the monthly dry cow budget and the actual number of cows is large and the budget is smaller than the actual number of cows.

[0057] Figure 3is a schematic diagram of the error rate of the preliminary prediction disclosed in the embodiment of the present application; Figure 3 From the median error rate of 1-5, it can be seen that the budget error rate of the whole herd, adult cows, reserve cows, and lactating cows is the lowest, within 5% in most months; the budget error rate of pregnant young cows, young cows, and growing cows is relatively low, within 10% in most months; the budget error rate of pregnant lactating cows, non-pregnant lactating cows, and weaned calves is relatively high in some months, exceeding 10% and below 30%; the budget error rate of non-pregnant young cows, lactating calves, and dry cows is relatively large, with a budget error rate of more than 10% for 6 months or more, and there is an error rate of more than 30% in a single month. According to the actual data, some cows on the ranch were found to be dry in advance, that is, there were more than 360 dry cows with a pregnancy of 0-205 days, so the budgeted number of dry cows was less than the actual data, and the budget formula did not dry out the lactating cows that were pregnant for 0-205 days, so the budgeted number of pregnant lactating cows was more than the actual number of pregnant lactating cows; in addition, in the actual data from February to April, there were about 50 more non-pregnant dry cows, and most of them were forbidden to mate, which was also the reason for the large error rate in February-April. The budget for non-pregnant young cows is small, mainly because most non-pregnant young cows are too old in actual production and are forbidden to mate (that is, there are more non-pregnant young cows in reality), but the budget formula calculates the breeding pregnancy rate of non-pregnant young cows according to the normal pregnancy rate, making it more likely that non-pregnant young cows will become pregnant young cows, which also makes the budget for non-pregnant young cows smaller and the budget for pregnant young cows larger. Therefore, the forbidden mating factor needs to be considered in the budget formula, and the pregnancy rate of non-pregnant young cows at 21 days is relatively low. The budget for lactating calves in April was relatively high. The main reason may be that the premature birth rate was high. The budget for pregnant lactating cows and pregnant young cows was relatively high, resulting in more premature calves. Although there were only 58 calves, the error rate was relatively large because the base number of lactating calves was small.

[0058] Optionally, the establishing of the second association between the second feed data and the corresponding sub-indicator in the control indicator includes: establishing an association between the second data of the herd structure and the proportion of feed at each level, the second data includes data of adult cows and data of replacement cows, and the proportion of feed at each level includes a first proportion of primary feed, a second proportion of secondary feed, and a third proportion of tertiary feed; A first influencing factor for a corresponding sub-indicator in the control indicator is determined according to the first proportion, and a second influencing factor for a corresponding sub-indicator in the control indicator is determined according to the second proportion.

[0059] The "second data" mentioned here refers to the detailed data that constitutes the structure of the herd, which mainly includes two parts: adult cow data and replacement cow data. In dairy farms, different levels of feed are usually provided according to the different needs of cows. These feeds differ in nutritional content, energy density and cost. For example, the first-level feed may be rich in high protein and high energy, suitable for adult cows with high milk production; the second-level feed has a slightly lower nutritional level and is suitable for adult cows in the maintenance period or fast-growing replacement cows; the third-level feed may be used for low-yielding cows or cows with special management needs. The "proportion" of each level of feed refers to the proportion of each level of feed in the total feed volume. The establishment of this association means that farm managers need to reasonably allocate the proportion of each level of feed based on the actual needs of the herd (such as age, production stage, health status, etc.) to ensure that each cow can get the best nutritional support. The first influencing factor: Based on the first proportion of the first-level feed, evaluate its direct impact on each sub-indicator. For example, a high proportion of the first-level feed may help improve the 21-day pregnancy rate of adult cows, because high-quality feed helps improve the physical condition and reproductive performance of cows. Similarly, this feed may also reduce mortality rates because it can enhance the immunity and resistance of cattle. Second influencing factor: According to the second proportion of secondary feed, analyze its indirect or supplementary effect on sub-indicators. Secondary feed may not be as nutritious as primary feed, but it plays an important role in cost control and maintaining the overall health of the herd. For example, a reasonable proportion of secondary feed may help reduce premature births because it can provide stable nutritional support and avoid problems with cattle due to nutritional fluctuations. For tertiary feed (if applicable), its tertiary proportion may also have an impact on certain sub-indicators, although this impact may be relatively small or more focused on cost control. Specific correlation examples of sub-indicators: Pregnancy sub-indicator: The 21-day pregnancy rate of adult cows and replacement cows may be affected by feed quality and distribution. High-quality feed helps improve reproductive performance, thereby increasing pregnancy rates.

[0060] Mortality index: Mortality rate at different stages (such as mortality rate of adult cows, mortality rate 60 days after delivery, etc.) is closely related to the nutritional level of feed and the health status of cattle. Appropriate feed ratio can reduce mortality rate and improve the overall survival rate of cattle.

[0061] Production sub-indicators: Production sub-indicators such as abortion rate, surviving calf rate and premature birth rate are also affected by feed management. Reasonable feed distribution can help reduce the occurrence of abortion and premature birth, while improving the survival rate of calves.

[0062] For example, the benchmarks for the first, second, and third proportions may be 30%, 30%, and 40%. When the first proportion increases by one percentage point, the mortality rate can be reduced by a certain value. Of course, the percentage increase in the first proportion and the percentage reduction in the mortality rate are not a linear relationship, and can be specifically calculated through a specific model. This model may be based on historical data, expert experience, or statistical analysis, and it can predict the reduction in the mortality rate based on the specific value of the first proportion. In the model, each percentage point change in the first proportion can be mapped to a specific mortality rate reduction value, which is the first influencing factor. For example, if the model shows that when the first proportion increases from 30% to 31%, the mortality rate decreases by 0.12 percentage points (rather than simply 0.1 percentage points), then this 0.12 is the first influencing factor under the current change. Similar logic: For the second proportion (secondary feed proportion), similar logic is also used to determine its second influencing factor on the mortality rate (or other sub-indicators). However, it should be noted that the impact of secondary feed on the mortality rate may be different from that of primary feed, and may also be nonlinear. In the model, the independence and interaction between the proportions of feed at each level also need to be considered. That is, the change in the second proportion may have a direct impact on the mortality rate, or it may work together with the change in the first proportion to produce a more complex effect. Therefore, when determining the second influencing factor, it is necessary to comprehensively consider the direct effect of the secondary feed and its interaction with the primary feed. This may involve more complex mathematical models or simulation experiments to accurately predict.

[0063] Optionally, the adjusting the control index according to the second association and the first feed data includes: obtaining a fourth proportion of the primary feed in the first feed data, calculating a first difference between the fourth proportion and the first proportion, and calculating a first product of the first difference and the first influencing factor; Obtaining a fifth proportion of the secondary feed in the first feed data, calculating a second difference between the fifth proportion and the second proportion, and calculating a second product of the second difference and the second influencing factor; The corresponding sub-indicator in the control indicator is adjusted according to the first product and the second product.

[0064] The actual proportion of the current primary feed is extracted from the first feed data and recorded as the fourth proportion. This proportion reflects the actual use of the primary feed in the current farm. Then, the fourth proportion is compared with the first proportion of the benchmark (i.e., the preset or ideal primary feed proportion), and the difference between the two is calculated, which is called the first difference. This difference indicates the degree of deviation between the current primary feed proportion and the ideal state. Similarly, the actual proportion of the current secondary feed is extracted from the first feed data and recorded as the fifth proportion. Then, the fifth proportion is compared with the second proportion of the benchmark (i.e., the preset or ideal secondary feed proportion), and the difference between the two is calculated, which is called the second difference. This difference indicates the degree of deviation between the current secondary feed proportion and the ideal state. Using the previously determined first influencing factor (i.e., the degree of influence of the change in the primary feed proportion on the corresponding sub-indicator in the control indicator), the first difference is multiplied by the first influencing factor, and the result is called the first product. This product quantifies the potential impact on the control indicator caused by the deviation of the primary feed proportion from the ideal state. Similarly, using the second influencing factor (i.e., the degree of influence of the change in the secondary feed ratio on the corresponding sub-indicator in the control index), the second difference is multiplied by the second influencing factor, and the result is called the second product. This product quantifies the potential impact on the control index due to the deviation of the secondary feed ratio from the ideal state. Combine the first product and the second product to consider their joint impact on the corresponding sub-indicator in the control index. This may involve a simple addition operation (if the two have the same impact on the sub-indicator) or a more complex mathematical model (if there is an interaction between the two or the impact is in opposite directions). Based on the analysis results of the above comprehensive impact, the corresponding sub-indicator in the control index is adjusted. This adjustment may be to increase or decrease the specific value of the sub-indicator to improve the accuracy of the prediction.

[0065] This embodiment also discloses a prediction system for pasture herd structure. Figure 4 Schematic diagram of a module of a prediction system for pasture herd structure disclosed in an embodiment of the present application. Figure 4 As shown, the system includes a quantity module 401, a feed module 402, an indicator module 403 and a prediction module 404, wherein: The quantity module 401 is configured to obtain first data of the cattle herd status at the current moment, wherein the first data includes data of adult cows and data of replacement cows, wherein the data of adult cows includes data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows, and the number of non-pregnant dry cows, and the data of replacement cows includes data of calves, data of growing cows, data of pregnant young cows, and the number of non-pregnant young cows; A feed module 402 is configured to obtain first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; The indicator module 403 is configured to obtain a control indicator in the historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a production sub-indicator; The prediction module 404 is configured to establish a first association between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, establish a second association between the second feed data and the corresponding sub-indicator in the control index, adjust the control index according to the second association and the first feed data, predict the state of the cattle herd to be predicted according to the adjusted control index, the first association and the first data, and integrate the state of the cattle herd to be predicted to obtain a prediction result.

[0066] Optionally, the prediction module 404 is configured to: Determine a current first cattle herd state associated with a target cattle herd state to be predicted according to a preset relationship, and determine whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group; When the current first cattle herd state and the target cattle herd state to be predicted belong to the same category, selecting a first factor corresponding to the dead-elimination sub-index according to the category of the current first cattle herd state, and establishing an association between the target cattle herd state to be predicted and the first factor; When the current first cattle herd state and the target cattle herd state to be predicted do not belong to the same category, the second factor corresponding to the death sub-indicator is selected according to the category of the target cattle herd state to be predicted, and the third factor corresponding to the pregnancy sub-indicator and the fourth factor corresponding to the production sub-indicator are selected to establish an association between the target cattle herd state to be predicted and the second factor, the third factor and the fourth factor.

[0067] Optionally, the system includes a grouping module, wherein the grouping module is configured to: The non-pregnant lactating cow data are arranged into a plurality of different first groups, wherein the first groups include lactation days and corresponding cow numbers; The data of the pregnant lactating cows are arranged into a plurality of different second groups, wherein the second groups include the number of gestation days and the corresponding number of cows; The data of the pregnant dry cows are arranged into a plurality of different third groups, wherein the third groups include the number of gestation days and the corresponding number of cows; The calf data is arranged into a plurality of different fourth groups, the fourth group including the growth days and the corresponding number of cattle; the growing cattle data is arranged into a plurality of different fifth groups, the fifth group including the growth days and the corresponding number of cattle; the pregnant young cattle data is arranged into a plurality of different sixth groups, the sixth group including the pregnancy days and the corresponding number of cattle.

[0068] Optionally, the prediction module 404 is configured to: When the target cattle herd state to be predicted is 0-30 days after calf birth, determining the current first cattle herd state associated with the target cattle herd state to be predicted includes pregnant lactating cows for 206-235 days, pregnant dry cows for 206-235 days, pregnant dry cows for 236-265 days, pregnant dry cows for more than 265 days, pregnant heifers for 206-235 days, pregnant heifers for 236-265 days, and pregnant heifers for more than 265 days; It is determined that the calves born 0-30 days ago belong to the fourth group, the pregnant lactating cows 206-235 days pregnant belong to the second group, the pregnant dry cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the third group, the pregnant young cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the sixth group, and it is determined that the current first herd status and the target herd status to be predicted do not belong to the same category.

[0069] Optionally, the prediction module 404 is configured to: Select the 60-day-old mortality rate and the replacement cattle mortality rate from the mortality indicators according to the calf category, and the mortality indicators include the mortality rate of adult cows, the mortality rate of 60 days after calving, the mortality rate of replacement cattle and the 60-day-old mortality rate; The production sub-indicators including the abortion rate of adult cows, the abortion rate of reserve cows and the premature birth rate are selected according to the categories of pregnant lactating cows, pregnant dry cows and pregnant heifers. The pregnancy sub-indicators include the 21-day pregnancy rate of adult cows and the 21-day pregnancy rate of reserve cows. The production sub-indicators include the abortion rate of adult cows, the abortion rate of reserve cows, the survival rate of first-born cows, the survival rate of multiparous cows and the premature birth rate.

[0070] Optionally, the prediction module 404 is configured to: Establishing an association between second data of the herd structure and the proportion of feed at each level, wherein the second data includes data of adult cows and data of replacement cows, and the proportion of feed at each level includes a first proportion of primary feed, a second proportion of secondary feed, and a third proportion of tertiary feed; A first influencing factor for a corresponding sub-indicator in the control indicator is determined according to the first proportion, and a second influencing factor for a corresponding sub-indicator in the control indicator is determined according to the second proportion.

[0071] Optionally, the prediction module 404 is configured to: Obtaining a fourth proportion of the first-level feed in the first feed data, calculating a first difference between the fourth proportion and the first proportion, and calculating a first product of the first difference and the first influencing factor; Obtaining a fifth proportion of the secondary feed in the first feed data, calculating a second difference between the fifth proportion and the second proportion, and calculating a second product of the second difference and the second influencing factor; The corresponding sub-indicator in the control indicator is adjusted according to the first product and the second product.

[0072] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0073] This embodiment also discloses an electronic device, referring to Figure 5 The electronic device may include: at least one processor 501 , at least one communication bus 502 , a user interface 503 , a network interface 504 , and at least one memory 505 .

[0074] The communication bus 502 is used to realize the connection and communication between these components.

[0075] The user interface 503 may include a display screen (Display) and a camera (Camera), and the optional user interface 503 may also include a standard wired interface and a wireless interface.

[0076] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0078] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. As Figure 5 As shown, the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a method for predicting pasture herd structure.

[0079] exist Figure 5In the electronic device shown, the user interface 503 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 501 can be used to call the application program of the prediction method of the pasture herd structure stored in the memory 505. When executed by one or more processors 501, the electronic device executes one or more methods in the above-mentioned embodiments.

[0080] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0081] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory 505 and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory 505 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0086] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for predicting cattle herd structure in a pasture, characterized in that: Applied to a pasture management platform, the method includes: Acquire first data of the cattle herd status at the current moment, wherein the first data includes data of adult cows and data of replacement cows, wherein the data of adult cows includes data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows, and the number of non-pregnant dry cows, and the data of replacement cows includes data of calves, data of growing cows, data of pregnant young cows, and the number of non-pregnant young cows; Acquire first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; Acquire a control indicator in historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a birth sub-indicator; A first association is established between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, a second association is established between the second feed data and the corresponding sub-indicator in the control index, the control index is adjusted according to the second association and the first feed data, the state of the cattle herd to be predicted is predicted according to the adjusted control index, the first association and the first data, and the state of the cattle herd to be predicted is integrated to obtain a prediction result.

2. The method for predicting pasture herd structure according to claim 1, characterized in that: The first association between each cattle herd state to be predicted and the corresponding sub-indicator in the control indicator is established, including: Determine a current first cattle herd state associated with a target cattle herd state to be predicted according to a preset relationship, and determine whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group; When the current first cattle herd state and the target cattle herd state to be predicted belong to the same category, selecting a first factor corresponding to the dead-elimination sub-index according to the category of the current first cattle herd state, and establishing an association between the target cattle herd state to be predicted and the first factor; When the current first cattle herd state and the target cattle herd state to be predicted do not belong to the same category, the second factor corresponding to the death sub-indicator is selected according to the category of the target cattle herd state to be predicted, and the third factor corresponding to the pregnancy sub-indicator and the fourth factor corresponding to the production sub-indicator are selected to establish an association between the target cattle herd state to be predicted and the second factor, the third factor and the fourth factor.

3. The method for predicting pasture herd structure according to claim 2, characterized in that: Before judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same type group, the method further includes: The non-pregnant lactating cow data are arranged into a plurality of different first groups, wherein the first groups include lactation days and corresponding cow numbers; The data of the pregnant lactating cows are arranged into a plurality of different second groups, wherein the second groups include the number of gestation days and the corresponding number of cows; The data of the pregnant dry cows are arranged into a plurality of different third groups, wherein the third groups include the number of gestation days and the corresponding number of cows; arranging the calf data into a plurality of different fourth groups, wherein the fourth groups include growth days and corresponding numbers of cattle; The growing cattle data are arranged into a plurality of different fifth groups, wherein the fifth groups include growth days and corresponding cattle numbers; The data of pregnant young cows are arranged into a plurality of different sixth groups, wherein the sixth groups include the number of gestation days and the corresponding number of cows.

4. The method for predicting pasture herd structure according to claim 3, characterized in that: The step of determining the current first cattle herd state associated with the target cattle herd state to be predicted according to the preset relationship, and judging whether the current first cattle herd state and the target cattle herd state to be predicted belong to the same category according to whether the target cattle herd state to be predicted and the current first cattle herd state are in the same category comprises: When the target cattle herd state to be predicted is 0-30 days after calf birth, determining the current first cattle herd state associated with the target cattle herd state to be predicted includes pregnant lactating cows for 206-235 days, pregnant dry cows for 206-235 days, pregnant dry cows for 236-265 days, pregnant dry cows for more than 265 days, pregnant heifers for 206-235 days, pregnant heifers for 236-265 days, and pregnant heifers for more than 265 days; It is determined that the calves born 0-30 days ago belong to the fourth group, the pregnant lactating cows 206-235 days pregnant belong to the second group, the pregnant dry cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the third group, the pregnant young cows 206-235 days pregnant, 236-265 days pregnant, and more than 265 days pregnant belong to the sixth group, and it is determined that the current first herd status and the target herd status to be predicted do not belong to the same category.

5. The method for predicting pasture herd structure according to claim 4, characterized in that: The selecting the second factor corresponding to the death sub-indicator according to the category of the target cattle herd state to be predicted, and selecting the third factor corresponding to the pregnancy sub-indicator and / or the fourth factor corresponding to the production sub-indicator includes: Select the 60-day-old mortality rate and the replacement cattle mortality rate from the mortality indicators according to the calf category, and the mortality indicators include the mortality rate of adult cows, the mortality rate of 60 days after calving, the mortality rate of replacement cattle and the 60-day-old mortality rate; The production sub-indicators including the abortion rate of adult cows, the abortion rate of reserve cows and the premature birth rate are selected according to the categories of pregnant lactating cows, pregnant dry cows and pregnant heifers. The pregnancy sub-indicators include the 21-day pregnancy rate of adult cows and the 21-day pregnancy rate of reserve cows. The production sub-indicators include the abortion rate of adult cows, the abortion rate of reserve cows, the survival rate of first-born cows, the survival rate of multiparous cows and the premature birth rate.

6. The method for predicting pasture herd structure according to claim 1, characterized in that: The establishing of a second association between the second feed data and a corresponding sub-indicator in the control indicator comprises: Establishing an association between second data of the herd structure and the proportion of feed at each level, wherein the second data includes data of adult cows and data of replacement cows, and the proportion of feed at each level includes a first proportion of primary feed, a second proportion of secondary feed, and a third proportion of tertiary feed; A first influencing factor for a corresponding sub-indicator in the control indicator is determined according to the first proportion, and a second influencing factor for a corresponding sub-indicator in the control indicator is determined according to the second proportion.

7. The method for predicting pasture herd structure according to claim 1, characterized in that: The adjusting the control index according to the second association and the first feed data comprises: Obtaining a fourth proportion of the first-level feed in the first feed data, calculating a first difference between the fourth proportion and the first proportion, and calculating a first product of the first difference and the first influencing factor; Obtaining a fifth proportion of the secondary feed in the first feed data, calculating a second difference between the fifth proportion and the second proportion, and calculating a second product of the second difference and the second influencing factor; The corresponding sub-indicator in the control indicator is adjusted according to the first product and the second product.

8. A prediction system for cattle herd structure in a pasture, characterized in that: It includes quantity module, feed module, indicator module and prediction module, among which: a quantity module configured to obtain first data on the state of the cattle herd at a current moment, wherein the first data includes data of adult cows and data of replacement cows, wherein the data of adult cows includes data of non-pregnant lactating cows, data of pregnant lactating cows, data of pregnant dry cows, and the number of non-pregnant dry cows, and the data of replacement cows includes data of calves, data of growing cows, data of pregnant young cows, and the number of non-pregnant young cows; A feed module, configured to obtain first feed data at a current moment and second feed data in historical data, wherein the first feed data and the second feed data both include consumption data of feeds of different levels; An indicator module configured to obtain a control indicator in historical data, wherein the control indicator includes a plurality of sub-indicators, and the sub-indicators include a pregnancy sub-indicator, a death sub-indicator, and a production sub-indicator; A prediction module is configured to establish a first association between the state of the cattle herd to be predicted and the corresponding sub-indicator in the control index, establish a second association between the second feed data and the corresponding sub-indicator in the control index, adjust the control index according to the second association and the first feed data, predict the state of the cattle herd to be predicted according to the adjusted control index, the first association and the first data, and integrate the state of the cattle herd to be predicted to obtain a prediction result.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Citation Information

Patent Citations

  • Method for quantitating non-structural carbohydrates in feedstuffs and ration formulations based thereon

    CA1225273A

  • Fertility prediction in animals

    CA3145516A1

  • Cow inventory structure prediction method

    CN108171368A

  • Cattle flock structure determination method and device and computer readable storage medium

    CN112488403A

  • Cattle herd structure prediction method and device, electronic equipment and medium

    CN118297214A