Livestock breeding information data management system based on internet

Abstract

This invention discloses an internet-based livestock farming information data management system, belonging to the field of livestock farming technology. The invention includes a constraint prediction module, a segmented feeding curve generation module, a feedback correction module, a dynamic resource reallocation module, and an iteration module. The constraint prediction module uses feed shelf life and target market time as dual constraints to solve for feasible solution intervals. The segmented feeding curve generation module constructs constraint corridors based on feasible solution intervals to generate adaptive segmented feeding curves. The feedback correction module forces upstream recalculation when accumulated corrections penetrate the interval boundary, forming a forced closed loop of execution and strategy. The dynamic resource reallocation module forces inventory optimization when there is no solution and synchronizes the results upstream. The iteration module forces full-link recalculation when new data is added. This invention solves the problem of mismatch between feed shelf life and growth cycle through dual constraint coupling and forced linkage between modules, achieving a dual improvement in feed utilization and farming efficiency.

Description

Technical Field

[0001] This invention relates to the field of livestock breeding technology, and in particular to an Internet-based livestock breeding information data management system. Background Technology

[0002] In modern livestock farming, IoT sensors and cloud platforms are typically used to monitor and statistically analyze livestock weight, feed intake, and environmental parameters in real time. Daily feeding is carried out according to a preset fixed feeding plan. In farming scenarios with stable feed supply and relatively fixed stock structure, such systems can improve farming efficiency and reduce the cost of manual intervention to a certain extent.

[0003] However, in actual farming, feed, as a major component of farming costs, is usually managed through bulk purchasing and centralized storage. But feed itself has a clear shelf life, especially for high-oil feeds. Long-term storage can lead to nutrient loss, quality decline, or even spoilage. If it cannot be consumed within the shelf life, it will cause direct economic losses. At the same time, the market time of livestock needs to be dynamically adjusted according to factors such as growth progress and market conditions. Traditional feeding strategies are mostly fixed feeding amounts or simple phased feeding, which makes it difficult to optimize in real time based on the dynamic relationship between existing feed inventory, remaining shelf life of feed, current growth status of livestock, and target market time. As a result, in the current technology, when the feed inventory deviates from the expected fixed matching progress, it is difficult to achieve a dual improvement in feed utilization and farming efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide an Internet-based livestock breeding information data management system to solve the problems of low feed utilization and lack of closed-loop linkage between feeding plans and stock adjustments caused by the mismatch between feed shelf life and livestock growth cycle in the existing technology.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution: This invention is an internet-based livestock farming information and data management system, comprising: The constrained prediction module is used to obtain feed inventory, feed shelf life, livestock inventory structure and target market time, and construct a livestock growth prediction model. The feed shelf life and target market time form a double constraint boundary to predict the remaining feeding cycle and theoretical nutritional requirement sequence. At the same time, it calculates the theoretical maximum daily feeding amount sequence for consuming inventory before the feed shelf life expires and the theoretical minimum daily feeding amount sequence for reaching the target weight before market, and solves them in a coupled manner to determine the feasible solution interval. The segmented feeding curve generation module is used to construct a feeding amount constraint corridor based on the upper and lower limits of the feasible solution interval. Within the constraint corridor, the remaining feeding cycle is divided into three stages: nutrient accumulation, growth stabilization, and slaughter adjustment. The shelf life urgency coefficient is introduced to dynamically adjust the duration and feeding slope of each stage in order to generate an adaptive segmented feeding curve limited within the corridor. The feedback correction module is used to collect feed consumption rate, group weight gain rate and individual dispersion in real time, construct a dynamic residual function between theoretical demand and actual consumption, trigger variable structure PID control when the residual exceeds the threshold, adaptively select PID parameters according to the stage to compensate for the daily feeding amount, and include the correction cumulative value in the validity judgment of the feasible solution interval. When the correction cumulative value causes the original interval boundary to be penetrated, the constraint prediction module is triggered to resolve the feasible interval and output it. The resource dynamic reallocation module is used to differentiate feed allocation based on individual weights and calculate the growth lag index. When the feasible solution interval is empty, it receives the stock adjustment instruction forcibly output by the constraint prediction module, performs optimization operation on the stock structure based on the growth lag index, and synchronizes the optimized stock structure as a forced boundary condition to the constraint prediction module. The iteration module is used to issue feeding instructions and control the iterative execution of each module.

[0006] Furthermore, in the segmented feeding curve generation module, the duration of the nutrient accumulation stage, the growth stabilization stage, and the slaughter adjustment stage is determined as follows: The end time of the nutrient accumulation stage is shown in equation (1): (1) The end time of the stable growth phase is shown in equation (2): (2) in, To predict the remaining feeding cycle, When the urgency coefficient of shelf life increases, Decrease Increase when the urgency coefficient of shelf life decreases. Increase Decrease.

[0007] Furthermore, the ratio of the absolute value of the increasing slope of the nutrient accumulation stage to the decreasing slope of the slaughter adjustment stage is not less than 2:1, and the curve presents an asymmetrical shape with a steep left side and a gentle right side.

[0008] Furthermore, the feedback correction module includes: Stage identification unit: used to determine which adjustment stage of the three consecutive stages in the segmented feeding curve the current moment is in; Deviation Calculation Unit: Used to calculate feed residue deviation rate, inventory weight deviation rate, and body weight gain rate deviation rate; Feed residue deviation rate:

[0009] Inventory weight deviation rate:

[0010] Deviation rate of weight gain:

[0011] Correction factor selection unit: used to select the corresponding deviation to generate correction factor k based on the current stage. In the nutrient accumulation stage, Based on the feed residue deviation rate as the correction basis, priority is given to controlling the feed consumption rhythm during the stable growth stage. The correction is based on the deviation rate of the stock weight, prioritizing ensuring that the weight gain of the herd meets the target, and adjusting the slaughter volume during the slaughter adjustment phase. Based on the deviation rate of weight gain, the slaughter time is prioritized for matching. , , The preset adjustment coefficient, k, is used to correct the basic feeding amount for the day, so as to obtain the actual total feeding amount for the day; Feeding amount correction unit: used to adjust the daily basic feeding amount Multiply by the correction factor k to obtain the actual total feeding amount for the day. , ,in, The basic feeding amount for the day in the segmented feeding curve is k, which is calculated by the correction factor selection unit based on the current stage and the corresponding deviation.

[0012] Furthermore, in the dynamic resource reallocation module, the basic maintenance needs of each livestock are given priority. The remaining feed is allocated according to the growth lag index, which is the degree of deviation between the current livestock weight and the target growth curve. When the weight of a certain livestock is lower than the preset growth threshold for a fixed period of time, a culling suggestion is automatically generated and pushed to the operation terminal.

[0013] Furthermore, when a new batch of feed is put into storage, the iterative module enters the storage information through the operation terminal, and the system automatically updates the feed inventory data and shelf-life data, forcibly clears all module caches and re-executes the entire process.

[0014] Furthermore, the data sources for the constrained prediction module include: Feed inventory data is collected in real time by weight sensors and level sensors installed in the feed warehouse to record the current feed inventory and link it with the purchase and warehousing information to obtain the warehousing time, shelf life expiration date and initial inventory of each batch of feed. Individual livestock data is collected in real time through electronic ear tags, RFID tags and automatic weighing systems installed in the breeding pens. This includes individual number, weight, daily weight gain and historical health score. The data is uploaded to a cloud database and a local server to form an individual profile. Environmental and growth model data: The system has a built-in livestock growth model library. Combined with breeding environment parameters, livestock breed, and age, it calculates and predicts the remaining feeding period required to reach the target market weight. The target launch date is automatically generated by inputting it into the operating terminal.

[0015] Furthermore, the theoretical maximum allowable daily feeding sequence is the maximum daily feeding amount to be consumed before the feed shelf life expires, and the theoretical minimum required daily feeding sequence is the minimum daily feeding amount to be reached before the target market time. The feasible solution interval is the allowable range of daily feeding amount that simultaneously satisfies the dual constraints. When the feasible solution interval is empty, the stock structure adjustment instruction is output.

[0016] Furthermore, the curve data generated by the segmented feeding curve generation module is stored in the system database in the form of a time series, serving as the baseline input for the feedback correction module. The actual total feeding amount generated by the feedback correction module for the day is stored in the execution instruction queue for the resource dynamic reallocation module to call. The individual feeding instructions generated by the resource dynamic reallocation module are pushed to the execution module, and the changes in the stock structure are synchronized to the constraint prediction module. The execution module feeds back the execution results to the system database for subsequent deviation calculation and model correction.

[0017] Furthermore, when the feedback correction module accumulates corrections that penetrate the boundary of the feasible solution interval, it forces the constraint prediction module to resolve and uses the resolved constraint corridor as the sole input to the piecewise feeding curve generation module.

[0018] The present invention has the following beneficial effects: 1. This invention constructs a coupled prediction model with feed shelf life and target market time as dual constraints, solves the feasible solution interval, and forcibly triggers stock optimization when the two conflict. This effectively solves the problem of feed waste or substandard growth caused by the mismatch between feed shelf life and growth cycle in the prior art, and significantly improves feed utilization and breeding efficiency.

[0019] 2. This invention incorporates the accumulated deviation in actual execution into the validity determination of the feasible solution interval through a feedback correction module. When the deviation penetrates the boundary, the upstream module is forcibly triggered to recalculate the strategy, forming a closed loop from execution deviation to strategy reconstruction. This avoids the problem of only performing daily compensation and the disconnect between planning and execution in the prior art, and improves the system's adaptability.

[0020] 3. This invention uses a resource dynamic reallocation module to forcibly bind the stock structure adjustment command with the empty solution state of the feasible solution interval, and uses the stock optimization result as the forced boundary condition of the upstream module. This makes the stock adjustment no longer dependent on manual decision-making, but is automatically triggered by the system and reacts back to the overall strategy, thus realizing the deep coupling between the stock structure and the feeding plan.

[0021] 4. This invention constructs a feeding amount constraint corridor by using the upper and lower limits of the feasible solution interval, so that the generated feeding curve is limited to the constraint boundary jointly defined by the feed shelf life and the market time within the feeding cycle, avoiding the possibility of feed expiration and waste or failure to meet growth standards; at the same time, the feasible solution interval of the upstream constraint prediction module is used as the forced boundary, and its output is used as the benchmark input of the downstream feedback correction module, forming a complete set of strategy transmission chains from constraints to the final execution of planning. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a system block diagram of the present invention. Detailed Implementation

[0024] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0025] See Figure 1 This invention is an internet-based livestock farming information data management system, comprising: The constrained prediction module is used to obtain feed inventory, feed shelf life, livestock inventory structure and target market time, and construct a livestock growth prediction model. The feed shelf life and target market time form a double constraint boundary to predict the remaining feeding cycle and theoretical nutritional requirement sequence. At the same time, it calculates the theoretical maximum daily feeding amount sequence for consuming inventory before the feed shelf life expires and the theoretical minimum daily feeding amount sequence for reaching the target weight before market, and solves them in a coupled manner to determine the feasible solution interval. It should be noted that the data sources for the constrained prediction module include: Feed inventory data is collected in real time by weight sensors and level sensors installed in the feed warehouse to record the current feed inventory and link it with the purchase and warehousing information to obtain the warehousing time, shelf life expiration date and initial inventory of each batch of feed. Individual livestock data is collected in real time through electronic ear tags, RFID tags and automatic weighing systems installed in the breeding pens. This includes individual number, weight, daily weight gain and historical health score. The data is uploaded to a cloud database and a local server to form an individual profile. Environmental and growth model data: The system has a built-in livestock growth model library. Combined with breeding environment parameters, livestock breed, and age, it calculates and predicts the remaining feeding period required to reach the target market weight. The target launch date is automatically generated by inputting it into the operating terminal.

[0026] The theoretical maximum allowable daily feeding sequence is the maximum daily feeding amount to be consumed before the feed shelf life expires. The theoretical minimum required daily feeding sequence is the minimum daily feeding amount to be reached before the target market time. The feasible solution interval is the allowable range of daily feeding amount that simultaneously satisfies the dual constraints. When the feasible solution interval is empty, the stock structure adjustment instruction is output.

[0027] The segmented feeding curve generation module is used to construct a feeding amount constraint corridor based on the upper and lower limits of the feasible solution interval. Within the constraint corridor, the remaining feeding cycle is divided into three stages: nutrient accumulation, growth stabilization, and slaughter adjustment. The shelf life urgency coefficient is introduced to dynamically adjust the duration and feeding slope of each stage in order to generate an adaptive segmented feeding curve limited within the corridor. It should be noted that the duration of the nutrient accumulation stage, the growth stabilization stage, and the slaughter adjustment stage in the segmented feeding curve generation module are determined as follows: The end time of the nutrient accumulation stage is shown in equation (1): (1) The end time of the stable growth phase is shown in equation (2): (2) in, To predict the remaining feeding cycle, When the urgency coefficient of shelf life increases, Decrease Increase when the urgency coefficient of shelf life decreases. Increase Decrease.

[0028] The ratio of the absolute value of the increasing slope of the nutrient accumulation stage to the decreasing slope of the slaughter adjustment stage is not less than 2:1, and the curve shows an asymmetrical shape with a steep left side and a gentle right side.

[0029] The feedback correction module is used to collect feed consumption rate, group weight gain rate and individual dispersion in real time, construct a dynamic residual function between theoretical demand and actual consumption, trigger variable structure PID control when the residual exceeds the threshold, adaptively select PID parameters according to the stage to compensate for the daily feeding amount, and include the correction cumulative value in the validity judgment of the feasible solution interval. When the correction cumulative value causes the original interval boundary to be penetrated, the constraint prediction module is triggered to resolve the feasible interval and output it. It should be noted that when the feedback correction module accumulates corrections that penetrate the boundary of the feasible solution interval, it forces the constraint prediction module to resolve and uses the resolved constraint corridor as the sole input to the piecewise feeding curve generation module. The feedback and correction module includes: Stage identification unit: used to determine which adjustment stage of the three consecutive stages in the segmented feeding curve the current moment is in; Deviation Calculation Unit: Used to calculate feed residue deviation rate, inventory weight deviation rate, and body weight gain rate deviation rate; Feed residue deviation rate:

[0030] Inventory weight deviation rate:

[0031] Deviation rate of weight gain:

[0032] Correction factor selection unit: used to select the corresponding deviation to generate correction factor k based on the current stage. In the nutrient accumulation stage, Based on the feed residue deviation rate as the correction basis, priority is given to controlling the feed consumption rhythm during the stable growth stage. The correction is based on the deviation rate of the stock weight, prioritizing ensuring that the weight gain of the herd meets the target, and adjusting the slaughter volume during the slaughter adjustment phase. Based on the deviation rate of weight gain, the slaughter time is prioritized for matching. , , The preset adjustment coefficient, k, is used to correct the basic feeding amount for the day, so as to obtain the actual total feeding amount for the day; Feeding amount correction unit: used to adjust the daily basic feeding amount Multiply by the correction factor k to obtain the actual total feeding amount for the day. , ,in, The basic feeding amount for the day in the segmented feeding curve is k, which is calculated by the correction factor selection unit based on the current stage and the corresponding deviation.

[0033] The resource dynamic reallocation module is used to differentiate feed allocation based on individual weights and calculate the growth lag index. When the feasible solution interval is empty, it receives the stock adjustment instruction forcibly output by the constraint prediction module, performs optimization operation on the stock structure based on the growth lag index, and synchronizes the optimized stock structure as a forced boundary condition to the constraint prediction module. It should be noted that in the dynamic resource reallocation module, the basic maintenance needs of each livestock are given priority. The remaining feed is allocated according to the growth lag index, which is the degree of deviation between the current weight of the livestock and the target growth curve. When the weight of a certain livestock is lower than the preset growth threshold for a fixed period of time, a culling suggestion is automatically generated and pushed to the operation terminal.

[0034] The iteration module is used to issue feeding instructions and control the iterative execution of each module.

[0035] It should be noted that when a new batch of feed is put into storage, the iterative module enters the storage information through the operation terminal, and the system automatically updates the feed inventory data and shelf life data, forcibly clears all module caches and re-executes the entire process.

[0036] The curve data generated by the segmented feeding curve generation module is stored in the system database in the form of a time series, serving as the baseline input for the feedback correction module. The actual total feeding amount generated by the feedback correction module for the day is stored in the execution instruction queue for the resource dynamic reallocation module to call. The individual feeding instructions generated by the resource dynamic reallocation module are pushed to the execution module, and the changes in the stock structure are synchronized to the constraint prediction module. The execution module feeds back the execution results to the system database for subsequent deviation calculation and model correction.

[0037] In this invention, upon system startup, the constraint prediction module acquires feed inventory, shelf life, livestock inventory structure, and target market time through sensors and the operating terminal. It then constructs a growth prediction model, using shelf life and market time as dual constraints, to calculate the theoretical maximum and minimum daily feeding sequence and coupled solutions to the feasible solution interval. If the interval is empty, a forced inventory adjustment command is output. The segmented feeding curve generation module constructs a constraint corridor based on the upper and lower limits of the feasible solution interval, dividing the remaining feeding cycle into three stages: nutrient accumulation, growth stabilization, and market adjustment. A shelf life urgency coefficient is introduced to dynamically adjust the stage duration and feeding slope, generating an adaptive segmented feeding curve strictly confined within the corridor. The feedback correction module collects feed consumption rate and herd weight gain rate in real time, constructs a dynamic residual function, and triggers variable structure PID control for daily compensation when the residual exceeds the threshold. The cumulative correction value is included in the interval validity judgment. If it penetrates the original interval boundary, the constraint prediction module is forced to recalculate. The resource dynamic reallocation module allocates feed according to the growth lag index. After receiving the stock adjustment instruction, it performs stock optimization and synchronizes the optimized stock structure to the constraint prediction module as a forced boundary condition. The iteration module issues feeding instructions and forcibly clears all module caches when a new batch of feed is put into storage or when the stock changes, and re-executes the entire process with the updated data as the only input.

[0038] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. An internet-based livestock farming information data management system, characterized in that, include: The constrained prediction module is used to obtain feed inventory, feed shelf life, livestock inventory structure and target market time, and construct a livestock growth prediction model. The feed shelf life and target market time form a double constraint boundary to predict the remaining feeding cycle and theoretical nutritional requirement sequence. At the same time, it calculates the theoretical maximum daily feeding amount sequence for consuming inventory before the feed shelf life expires and the theoretical minimum daily feeding amount sequence for reaching the target weight before market, and solves them in a coupled manner to determine the feasible solution interval. The segmented feeding curve generation module is used to construct a feeding amount constraint corridor based on the upper and lower limits of the feasible solution interval. Within the constraint corridor, the remaining feeding cycle is divided into three stages: nutrient accumulation, growth stabilization, and slaughter adjustment. The shelf life urgency coefficient is introduced to dynamically adjust the duration and feeding slope of each stage in order to generate an adaptive segmented feeding curve limited within the corridor. The feedback correction module is used to collect feed consumption rate, group weight gain rate and individual dispersion in real time, construct a dynamic residual function between theoretical demand and actual consumption, trigger variable structure PID control when the residual exceeds the threshold, adaptively select PID parameters according to the stage to compensate for the daily feeding amount, and include the correction cumulative value in the validity judgment of the feasible solution interval. When the correction cumulative value causes the original interval boundary to be penetrated, the constraint prediction module is triggered to resolve the feasible interval and output it. The resource dynamic reallocation module is used to differentiate feed allocation based on individual weights and calculate the growth lag index. When the feasible solution interval is empty, it receives the stock adjustment instruction forcibly output by the constraint prediction module, performs optimization operation on the stock structure based on the growth lag index, and synchronizes the optimized stock structure as a forced boundary condition to the constraint prediction module. The iteration module is used to issue feeding instructions and control the iterative execution of each module.

2. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, In the segmented feeding curve generation module, the duration of the nutrient accumulation stage, the growth stabilization stage, and the slaughter adjustment stage is determined as follows: The end time of the nutrient accumulation stage is shown in equation (1): (1) The end time of the stable growth phase is shown in equation (2): (2) in, To predict the remaining feeding cycle, When the urgency coefficient of shelf life increases, Decrease Increase when the urgency coefficient of shelf life decreases. Increase Decrease.

3. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, The ratio of the absolute value of the increasing slope of the nutrient accumulation stage to the decreasing slope of the slaughter adjustment stage is not less than 2:1, and the curve shows an asymmetrical shape with a steep left side and a gentle right side.

4. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, The feedback correction module includes: Stage identification unit: used to determine which adjustment stage of the three consecutive stages in the segmented feeding curve the current moment is in; Deviation Calculation Unit: Used to calculate feed residue deviation rate, inventory weight deviation rate, and body weight gain rate deviation rate; Feed residue deviation rate: ; Inventory weight deviation rate: ; Deviation rate of weight gain: ; Correction factor selection unit: used to select the corresponding deviation to generate correction factor k based on the current stage. In the nutrient accumulation stage, Based on the feed residue deviation rate as the correction basis, priority is given to controlling the feed consumption rhythm during the stable growth stage. The correction is based on the deviation rate of the stock weight, prioritizing ensuring that the weight gain of the herd meets the target, and adjusting the slaughter volume during the slaughter adjustment phase. Based on the deviation rate of weight gain, the slaughter time is prioritized for matching. , , The preset adjustment coefficient, k, is used to correct the basic feeding amount for the day, so as to obtain the actual total feeding amount for the day; Feeding amount correction unit: used to adjust the daily basic feeding amount Multiply by the correction factor k to obtain the actual total feeding amount for the day. , ,in, The basic feeding amount for the day in the segmented feeding curve is k, which is calculated by the correction factor selection unit based on the current stage and the corresponding deviation.

5. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, In the resource dynamic reallocation module, the basic maintenance needs of each livestock are given priority. The remaining feed is allocated according to the growth lag index, which is the degree of deviation between the current weight of the livestock and the target growth curve. When the weight of a certain livestock is lower than the preset growth threshold for a fixed period of time, a culling suggestion is automatically generated and pushed to the operation terminal.

6. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, When a new batch of feed is put into storage, the iterative module enters the storage information through the operation terminal, and the system automatically updates the feed inventory data and shelf life data, forcibly clears all module caches and re-executes the entire process.

7. The Internet-based livestock breeding information data management system according to claim 1, characterized in that, The data sources for the constraint prediction module include: Feed inventory data is collected in real time by weight sensors and level sensors installed in the feed warehouse to record the current feed inventory and link it with the purchase and warehousing information to obtain the warehousing time, shelf life expiration date and initial inventory of each batch of feed. Individual livestock data is collected in real time through electronic ear tags, RFID tags and automatic weighing systems installed in the breeding pens. This includes individual number, weight, daily weight gain and historical health score. The data is uploaded to a cloud database and a local server to form an individual profile. Environmental and growth model data: The system has a built-in livestock growth model library. Combined with breeding environment parameters, livestock breed, and age, it calculates and predicts the remaining feeding period required to reach the target market weight. The target launch date is automatically generated by inputting it into the operating terminal.

8. A livestock breeding information data management system based on the Internet according to claim 7, characterized in that, The theoretical maximum allowable daily feeding sequence is the maximum daily feeding amount to be consumed before the expiration of the feed shelf life. The theoretical minimum required daily feeding sequence is the minimum daily feeding amount to be reached before the target market time. The feasible solution interval is the allowable range of daily feeding amount that simultaneously satisfies the dual constraints. When the feasible solution interval is empty, the stock structure adjustment instruction is output.

9. A livestock breeding information data management system based on the Internet according to claim 1, characterized in that, The curve data generated by the segmented feeding curve generation module is stored in the system database in the form of a time series, serving as the baseline input for the feedback correction module. The actual total feeding amount generated by the feedback correction module for the day is stored in the execution instruction queue for the resource dynamic reallocation module to call. The individual feeding instructions generated by the resource dynamic reallocation module are pushed to the execution module, and the changes in the stock structure are synchronized to the constraint prediction module. The execution module feeds back the execution results to the system database for subsequent deviation calculation and model correction.

10. A livestock breeding information data management system based on the Internet according to claim 1, characterized in that, When the feedback correction module accumulates corrections that penetrate the boundary of the feasible solution interval, it forces the constraint prediction module to resolve and uses the resolved constraint corridor as the sole input to the segmented feeding curve generation module.

Images