Livestock breeding KPI automatic generation system and method based on multi-source data management
By implementing multi-source data governance and dynamic correction mechanisms, the fragmentation and rigidity of the traditional livestock farming KPI system have been resolved, enabling the quantification of ecological benefits and adaptive KPI generation, thereby enhancing the scientific nature and flexibility of the industrial chain.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHONGQING JIEJIARUN TECHNOLOGY CO LTD
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-10
AI Technical Summary
Traditional livestock farming KPI setting relies on human experience, resulting in fragmented data silos, an inability to adapt to environmental changes, and difficulty in reflecting ecological value. Furthermore, the existing system is rigid and cannot achieve global optimization and material balance.
A multi-source data governance approach is adopted, which defines parameters through process decomposition, constructs an objective function and solves a constrained optimization problem, generates dynamic adaptive KPIs, and makes corrections by combining ecological benefit quantification and market factors.
It has enabled the scientific planning of the ecological livestock industry chain, improved the efficiency and flexibility of resource allocation, dynamically adjusted KPI targets, reflected ecological benefits, and overcome the limitations of traditional KPIs.
Smart Images
Figure CN122367271A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of smart agriculture technology, and in particular to an automatic KPI generation system and method for livestock farming based on multi-source data governance. Background Technology
[0002] With the continuous development of the ecological animal husbandry industry, it is crucial to construct a scientific and reasonable key performance indicator (KPI) system to improve the efficiency of the entire industry chain.
[0003] However, traditional livestock farming KPI setting relies heavily on manual experience, a method that has revealed numerous limitations in practical application. First, the livestock industry chain encompasses multiple complex stages, including forage or feed cultivation, ecological farming, slaughtering and processing, and manure treatment and resource utilization. Traditional methods often isolate these stages, creating data silos and making it difficult to achieve global optimization and material balance within the industry chain under multiple constraints such as production targets, carbon emission quotas, and water resource budgets. Second, traditional KPIs are typically static and rigid, unable to adapt to changes in the farming environment and market supply and demand. Furthermore, in the field of ecological livestock farming, environmental constraints are becoming increasingly stringent, and existing KPI systems fail to reflect the ecological value in production assessments and economic decision-making.
[0004] Therefore, there is a need for an automatic KPI generation system and method for livestock farming based on multi-source data governance that can coordinate multiple resource constraints and achieve adaptive adjustment of indicators. Summary of the Invention
[0005] One of the objectives of this invention is to provide an automatic KPI generation system and method for livestock farming based on multi-source data governance, which can coordinate multiple resource constraints and achieve adaptive adjustment of indicators.
[0006] To solve the above-mentioned technical problems, this application provides the following technical solution: A method for automatically generating livestock farming KPIs based on multi-source data governance includes the following steps: S1. Decompose the beef cattle ecological farming industry chain into links, define multi-dimensional parameters for each link, and determine the technical feasibility range of each parameter; S2. Receive the target input from the terminal, including quarterly beef sales target, carbon emission quota, and water resource budget; construct the objective function based on the target input; calculate the initial values of the KPIs at the stage based on the objective function; S3. After completing an execution cycle, obtain the actual completion data of each stage, compare it with the initial KPI target value generated in step S2, calculate the deviation rate, and dynamically adjust the KPI target for the next cycle according to the preset rules.
[0007] Furthermore, in step S1, the process includes forage / feed planting, feed processing and storage, ecological farming, slaughtering and processing, manure treatment and resource utilization, and brand sales and traceability; the parameters include benefit parameters, cost parameters and constraint parameters.
[0008] Furthermore, step S2 specifically includes: S201. Calculate the revenue and cost of each stage based on the parameters defined in S1. S202. Calculate the converted value of each individual ecological benefit and sum them up to obtain the converted ecological benefit value; the individual benefits include carbon sink and emission reduction, soil improvement, water footprint reduction, and biodiversity conservation; S203. Construct the objective function and set constraints. The objective function is: ; in, This is a value converted from ecological benefits; S204. By solving the constrained objective optimization problem, we obtain the parameter values of each link that maximize the total profit, and obtain the initial values of the KPIs of each link.
[0009] Furthermore, the calculation of revenue and cost at each stage in step S201 includes: Forage planting stage: Income = ; in For planting area, The market price for silage corn is (yuan / ton). Cost = Seed cost + Irrigation cost + Fertilizer cost + Labor cost; Among them, irrigation costs and Related, fertilization costs and Related; Ecological farming process: Revenue = Live cattle weight at slaughter × Live cattle price per unit, Live cattle weight at slaughter = ; Cost = Feed cost + Veterinary drug cost + Labor cost; Feed cost = Total weight gain × × Feed unit price; Slaughtering and processing: Revenue = Beef sales volume × Beef unit price; Beef sales volume = Live cattle weight at slaughter × ; Cost = Slaughtering and processing costs + Cold chain storage costs; Wastewater treatment and resource utilization: Revenue = Organic fertilizer sales revenue + Carbon sequestration revenue; Cost = Depreciation of processing equipment + Operating energy costs; Brand sales and traceability: Revenue = Brand premium revenue; Cost = Traceability system operation and maintenance cost.
[0010] Furthermore, in step S202, calculating the converted value of each individual ecological benefit specifically includes: Carbon sinks and emission reduction: Emission reduction × Carbon trading price; Soil improvement: Reduce fertilizer costs + Increase yield and premium; Water footprint reduction: Water savings × Water rights price; Biodiversity conservation: Ecological product premium.
[0011] Furthermore, in step S203, the constraints include: Production constraint: Final beef sales volume ≥ market demand ; Carbon emission constraints: ; Water resource constraints: Total water consumption ; Technical constraints: Parameter values for each stage ∈ [lower technical limit, upper technical limit]; Material balance constraint: The inputs and outputs of each link satisfy the material conservation principle.
[0012] Furthermore, step S3 specifically includes: S301. For each KPI indicator, calculate the deviation rate between the actual completed value and the original target value: ; S302. Execute the corresponding adjustment strategy based on the range of the deviation rate; S303. Introduce market impact factors to revise the target a second time: ; The market influencing factors are determined based on a combination of price indices and supply and demand factors. S304. Use the CLAMP function to ensure that the corrected target value remains within the technically feasible range: ; The final target value will be used as the KPI target for the next period.
[0013] Furthermore, in step S302, the deviation adjustment strategy includes: When the deviation rate is > +10%, the new target i = the original target i × (1 + min(deviation rate × 0.5, 0.15)); When -15% ≤ deviation rate ≤ +10%, the new target i = the original target i; When the deviation rate is less than -15%, the new target i is equal to the original target i × 0.85, and an early warning is sent.
[0014] The second objective of this invention is to provide an automatic KPI generation system for livestock farming based on multi-source data governance, using the method described above.
[0015] This invention constructs a total profit maximization objective function that incorporates quantified ecological benefits, and combines this with macro-level constraints such as carbon emission quotas and water resource budgets. This enables precise reverse derivation from end-market beef sales targets to production indicators such as planting area, feed demand, and initial livestock inventory. Compared to traditional manual decomposition methods, this solution not only scientifically transforms the ecological values of carbon sequestration and emission reduction, soil improvement, and water conservation into calculable economic equivalents, thus quantifying the real benefits of ecological animal husbandry in the KPI system, but also establishes a dynamic correction mechanism. This allows the generated KPI targets to be automatically adjusted in a closed loop based on production performance and changes in the external market environment. While ensuring technical feasibility, this significantly improves the scientific rigor, flexibility, and resource allocation efficiency of livestock farming industry chain planning. Attached Figure Description
[0016] Figure 1 This is a flowchart of an embodiment of a livestock farming KPI automatic generation system and method based on multi-source data governance. Detailed Implementation
[0017] Example 1 like Figure 1 As shown in the figure, this embodiment illustrates an automatic KPI generation method for livestock farming based on multi-source data governance, taking beef cattle ecological farming as an example, and includes the following steps: S1. Define key parameters for each stage. The beef cattle ecological farming industry chain is broken down into stages, including forage / feed planting, feed processing and storage, ecological farming, slaughtering and processing, manure treatment and resource utilization, and brand sales and traceability. Multi-dimensional parameters are defined for each stage, including benefit-related parameters, cost-related parameters, and constraint-related parameters, and the technical feasibility range of each parameter is determined. For example, some core stages are shown in Table 1.
[0018] Table 1 ; S2. Automatically calculate initial values for stage-level KPIs. Receive terminal target input, including quarterly beef sales targets. Carbon emission quotas Water resources budget And use this to construct the objective function.
[0019] Specifically, it includes: S201, Revenue and Cost Calculation for Each Stage Calculate the revenue and cost for each stage based on the parameters defined in S1: Forage planting stage: Income = ; in For planting area, The market price for silage corn is (yuan / ton). Cost = Seed cost + Irrigation cost + Fertilizer cost + Labor cost; Among them, irrigation costs and Related, fertilization costs and Related Ecological farming process: Revenue = Live cattle weight at slaughter × Live cattle price per unit, Live cattle weight at slaughter = ; Cost = Feed cost + Veterinary drug cost + Labor cost; Feed cost = Total weight gain × × Feed unit price; Slaughtering and processing: Revenue = Beef sales volume × Beef unit price; Beef sales volume = Live cattle weight at slaughter × ; Cost = Slaughtering and processing costs + Cold chain storage costs; Wastewater treatment and resource utilization: Revenue = Organic fertilizer sales revenue + Carbon sequestration revenue; Cost = Depreciation of processing equipment + Operating energy costs; Brand sales and traceability: Revenue = Brand premium revenue; Cost = Traceability system operation and maintenance cost; S202, Calculation of Ecological Benefit Conversion Value Ecological benefit conversion value The sum of the converted values of each individual ecological benefit:
[0020] in, This is a carbon sink and emission reduction conversion value. This is the converted value for soil improvement. To reduce the equivalent value of the water footprint, Value converted to biodiversity conservation; The specific calculation methods for the converted values of each individual ecological benefit are shown in Table 2: Table 2 ; S203, Objective Function and Constraints The objective function is constructed as follows: ; The constraints include: Production constraint: Final beef sales volume ≥ market demand ; Carbon emission constraints: ; Water resource constraints: Total water consumption ; Technical constraints: Parameter values for each stage ∈ [lower technical limit, upper technical limit], for example: ; ; ; ; Material balance constraints: The inputs and outputs of each stage must satisfy the principle of material conservation, for example: Feed supply ≥ livestock demand; Livestock output = Slaughtering and processing input; S204. Objective Solving and KPI Initial Value Generation By solving the constrained objective optimization problem described above, the parameter values for each stage that maximize total profit are obtained, which are the initial KPI values for each stage. The solution process employs linear programming or nonlinear programming algorithms to find the optimal solution while satisfying all constraints.
[0021] In this embodiment, if both the objective function and constraints are linear, the simplex method or interior point method is used (e.g., using open-source solvers like lp_solve, GLPK, or commercial solvers like Gurobi, CPLEX). If there are nonlinear terms (e.g., nonlinear coupling terms in ecological benefit calculations), sequential quadratic programming (SQP) or genetic algorithms (GA) are used.
[0022] Based on the technically feasible range in Table 1, set an initial feasible range for each decision variable (e.g., Area, ADG, FCR, Ymeat); By utilizing the material conservation principle, the search space for variables can be reduced, for example: Feed supply = Planting area × Yield per mu Livestock demand = Stock size × ADG × Days × FCR Both must satisfy conservation constraints.
[0023] Set the maximum number of iterations (e.g., 1000) and the convergence accuracy (e.g., the rate of change of the objective function < ); Each iteration calculates the total profit and constraint violation amount under the current parameter combination; Using the penalty function method to handle constraint violations:
[0024] Where F is the corrected objective function value. For the original total profit, This is the penalty factor (in this example, it is a positive number, which can be dynamically adjusted according to the degree of violation). To constrain violations, such as excessive carbon emissions or excessive water use.
[0025] When the objective function value no longer increases significantly after multiple consecutive iterations, and all constraints are satisfied, the function is considered converged.
[0026] The output of the parameter combination of each link that maximizes the total profit is the initial value of the KPI for each link; Optional outputs include sensitivity analysis results, such as the percentage decrease in total profit for every 1% reduction in carbon emission allowances, helping managers understand the impact of stricter or looser constraints on KPIs.
[0027] For example, in a given terminal target ton, tons, CO2e, Given m3, the initial KPI values for each stage are shown in Table 3. Table 3 ; S3. Dynamic feedback adjustment to achieve closed-loop iteration of KPI targets. After completing an execution cycle (such as last month), the actual completion data of each stage is obtained, compared with the initial KPI target value generated by S2, the deviation rate is calculated, and the KPI target for the next cycle is dynamically adjusted according to the preset rules.
[0028] S301, Calculation of Performance Deviation Rate For each KPI indicator, calculate the deviation rate between the actual completed value and the original target value: ; S302, Deviation Adjustment Rules Different adjustment strategies are implemented based on the range of the deviation rate, as shown in Table 4: Table 4 ; S303, Market Factors Adjustment Considering external factors such as market price fluctuations, this embodiment also introduces a market impact factor to further refine the target: ; The market impact factor is determined based on a comprehensive consideration of factors such as price indices and supply and demand. For example, when the beef market price increases by 10% compared to the previous quarter, the market impact factor for the sales volume target can be +0.05; when the feed price index increases by 15%, the impact factor for the feed cost control target can be -0.03; and when the beef supply-demand ratio (supply / demand) is below 0.9, the impact factor for the slaughter volume target can be +0.08.
[0029] S304, Technical Feasibility Constraints Use the CLAMP function to ensure that the corrected target value remains within the technically feasible range:
[0030] The final target value is used as the KPI target for the next period to achieve closed-loop iterative optimization. This embodiment also provides an automatic KPI generation system for livestock farming based on multi-source data governance, using the above method.
[0031] This embodiment of the solution scientifically decomposes the beef cattle ecological farming industry chain into its constituent segments and uses terminal inputs such as quarterly beef sales targets, carbon emission quotas, and water resource budgets as constraints to construct a total profit maximization objective function that incorporates ecological benefit conversion values. This transforms traditional manual experience-based decomposition into an automated system-solved constrained objective optimization problem. It not only achieves the decomposition from macro-level objectives to micro-level operational indicators but also innovatively quantifies ecological benefits such as carbon sequestration and emission reduction, soil improvement, water footprint reduction, and biodiversity conservation into economic value and incorporates them into the decision-making model. This effectively solves the problem of difficulty in measuring and assessing ecological value in the ecological livestock industry, allowing ecological benefits to directly participate in financial and production planning.
[0032] This embodiment further refines the KPI targets for the next cycle by calculating the deviation rate between the actual completed values and the target values at each stage after completing an execution cycle. This is done in conjunction with a preset deviation adjustment strategy and market influencing factors. Finally, the CLAMP function is used to ensure that the revised targets remain within a technically feasible range. This overcomes the shortcomings of traditional static and rigid KPIs, which are detached from reality. The resulting KPI system possesses strong adaptability and fault tolerance, significantly improving the scientific nature of supply chain production management and target planning.
[0033] Example 2 This embodiment summarizes the method of Embodiment 1 into a general KPI calculation process, and takes the example of an ecological ranch that needs to formulate production KPIs for the third quarter of 2024 for specific explanation.
[0034] General KPI calculation process: Terminal target inputs: obtain macro-constraints such as market demand, carbon emission quotas, and water resource budgets.
[0035] Reverse calculation: Determine the demand for live cattle to be slaughtered based on meat yield → Determine the initial inventory based on survival rate → Calculate the total weight gain based on daily weight gain and breeding cycle → Calculate feed demand based on feed conversion ratio → Determine the planting area based on concentrate-to-roughage ratio and yield per acre.
[0036] Multi-objective optimization: Under multiple constraints such as output, carbon emissions, water resources, and technical feasibility, solve for the parameters of each link that maximize total profit.
[0037] Ecological benefits quantification: Ecological benefits such as carbon sequestration, soil improvement, water footprint reduction, and biodiversity conservation are converted into economic value and incorporated into the objective function.
[0038] KPI Output: Generate KPI target values for each stage.
[0039] Dynamic adjustment: KPI targets are periodically adjusted based on actual performance data, market fluctuations, and policy changes.
[0040] Application examples: The input terminal targets are: quarterly beef sales of 50 tons; carbon emission allowance of 200 tons CO2e; and water resource budget based on planting area constraints.
[0041] The required number of live cattle can be determined by working backwards from terminal sales volume and meat yield:
[0042] Based on an average slaughter weight of 600 kg / head:
[0043] Considering the survival rate of the livestock (assuming 97%), calculate the initial stock level by working backwards:
[0044] Calculate total weight gain and feed requirements based on stock levels, daily weight gain, and the rearing cycle (90 days):
[0045]
[0046] Based on feed requirements (concentrate-to-roughage ratio 40:60) and yield per acre, calculate the planting area by working backwards:
[0047]
[0048] Taking into account both carbon emission constraints and water resource constraints, the above calculation results were optimized and adjusted to obtain the final KPI target values as shown in Table 5: Table 5 ; The above are merely embodiments of the present invention. The invention is not limited to the fields covered by these embodiments. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are able to access all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.
Claims
1. A method for automatically generating livestock farming KPIs based on multi-source data governance, characterized in that, Includes the following steps: S1. Decompose the beef cattle ecological farming industry chain into links, define multi-dimensional parameters for each link, and determine the technical feasibility range of each parameter; S2. Receive the target input from the terminal, including quarterly beef sales target, carbon emission quota, and water resource budget; construct the objective function based on the target input; Calculate the initial values of KPIs at the stage based on the objective function; S3. After completing an execution cycle, obtain the actual completion data of each stage, compare it with the initial KPI target value generated in step S2, calculate the deviation rate, and dynamically adjust the KPI target for the next cycle according to the preset rules.
2. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 1, characterized in that: In step S1, the process includes forage / feed planting, feed processing and storage, ecological farming, slaughtering and processing, manure treatment and resource utilization, and brand sales and traceability; the parameters include benefit parameters, cost parameters and constraint parameters.
3. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 2, characterized in that: Step S2 specifically includes: S201. Calculate the revenue and cost of each stage based on the parameters defined in S1. S202. Calculate the converted value of each individual ecological benefit and sum them up to obtain the converted ecological benefit value; the individual benefits include carbon sink and emission reduction, soil improvement, water footprint reduction, and biodiversity conservation; S203. Construct the objective function and set constraints. The objective function is: ； in, This is a value converted from ecological benefits; S204. By solving the constrained objective optimization problem, we obtain the parameter values of each link that maximize the total profit, and obtain the initial values of the KPIs of each link.
4. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 3, characterized in that: The calculation of revenue and cost at each stage in step S201 includes: Forage planting stage: Income = ; in For planting area, The market price for silage corn is (yuan / ton). Cost = Seed cost + Irrigation cost + Fertilizer cost + Labor cost; Among them, irrigation costs and Related, fertilization costs and Related; Ecological farming process: Revenue = Live cattle weight at slaughter × Live cattle price per unit, Live cattle weight at slaughter = ; Cost = Feed cost + Veterinary drug cost + Labor cost; Feed cost = Total weight gain × × Feed unit price; Slaughtering and processing: Revenue = Beef sales volume × Beef unit price; Beef sales volume = Live cattle weight at slaughter × ; Cost = Slaughtering and processing costs + Cold chain storage costs; Wastewater treatment and resource utilization: Revenue = Organic fertilizer sales revenue + Carbon sequestration revenue; Cost = Depreciation of processing equipment + Operating energy costs; Brand sales and traceability: Revenue = Brand premium revenue; Cost = Traceability system operation and maintenance cost.
5. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 4, characterized in that: In step S202, calculating the converted value of each individual ecological benefit specifically includes: Carbon sinks and emission reduction: Emission reduction × Carbon trading price; Soil improvement: Reduce fertilizer costs + Increase yield and premium; Water footprint reduction: Water savings × Water rights price; Biodiversity conservation: Ecological product premium.
6. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 5, characterized in that: In step S203, the constraints include: Production constraint: Final beef sales volume ≥ market demand ; Carbon emission constraints: ; Water resource constraints: Total water consumption ; Technical constraints: Parameter values for each stage ∈ [lower technical limit, upper technical limit]; Material balance constraint: The inputs and outputs of each link satisfy the material conservation principle.
7. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 6, characterized in that: Step S3 specifically includes: S301. For each KPI indicator, calculate the deviation rate between the actual completed value and the original target value: ； S302. Execute the corresponding adjustment strategy based on the range of the deviation rate; S303. Introduce market impact factors to revise the target a second time: ； The market influencing factors are determined based on a combination of price indices and supply and demand factors. S304. Use the CLAMP function to ensure that the corrected target value remains within the technically feasible range: ； The final target value will be used as the KPI target for the next period.
8. The method for automatically generating livestock farming KPIs based on multi-source data governance according to claim 7, characterized in that: In step S302, the deviation adjustment strategy includes: When the deviation rate is > +10%, the new target i = the original target i × (1 + min(deviation rate × 0.5, 0.15)); When -15% ≤ deviation rate ≤ +10%, the new target i = the original target i; When the deviation rate is less than -15%, the new target i is equal to the original target i × 0.85, and an early warning is issued.
9. A livestock farming KPI automatic generation system based on multi-source data governance, characterized in that, Use the method described in any one of claims 1-8.