Artificial intelligence-based goat breeding cost estimation method and system

Abstract

The invention provides a goat breeding cost estimation method and system based on artificial intelligence. The method comprises the following steps: determining a plurality of conventional cost data related to goat breeding according to a goat breeding number, and estimating a preliminary breeding cost according to each conventional cost data; wherein the conventional cost data comprises breeding sheep cost data, feed cost data, sheep house construction cost data and labor cost data; inputting the conventional cost data and the zero-carbon breeding plan data into a breeding cost reduction prediction model based on artificial intelligence, and outputting a breeding cost reduction value by the breeding cost reduction prediction model; and calculating the target breeding cost according to the initial breeding cost and the breeding cost reduction value. According to the method, a traditional goat breeding cost factor and a breeding cost reduction value after a zero-carbon breeding technology are considered at the same time, so that more accurate target breeding cost is obtained, and more valuable guidance can be provided for breeding behaviors of farmers.

Description

Technical Field

[0001] The present application relates to the field of smart breeding technology, and specifically, to a method and system for estimating goat breeding costs based on artificial intelligence. Background Art

[0002] Goats are a common domestic animal known for their ability to adapt to a variety of environments and to feed on grasses and other plants. They belong to the bovine family and come in a variety of breeds, including those raised for meat, dairy, and wool. Goats' meat and milk are important food sources in many cultures, while their wool is used to make textiles, such as wool sweaters and carpets.

[0003] Before or during goat breeding, it is necessary to calculate the breeding cost. The existing calculation methods are all based on manual analysis based on empirical values, and the estimation accuracy of the breeding cost is low, which is not conducive to providing breeding guidance for breeders. The present invention aims to solve this technical problem. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present application provides a method, system, electronic device, computer storage medium and computer program product for estimating goat breeding costs based on artificial intelligence.

[0005] The present application provides a method for estimating goat breeding costs based on artificial intelligence, the method comprising: Determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; Inputting each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, the farming cost reduction prediction model outputting a farming cost reduction value; The target breeding cost is calculated based on the preliminary breeding cost and the breeding cost reduction value.

[0006] Optionally, the conventional cost data related to goat breeding is determined based on the number of goats raised, and the preliminary breeding cost is estimated based on each of the conventional cost data, including: Acquire multiple sets of conventional cost big data related to goat breeding costs by using web crawling technology, each set of conventional cost big data corresponds to the breeding goat cost data, the feed cost data, the goat house construction cost data, and the labor cost data; Use a large language model to perform semantic analysis on each of the conventional cost big data to obtain corresponding breeding quantity-cost corresponding feature data; Using a fitting model to fit the characteristic data corresponding to the breeding quantity and cost to obtain a control relationship, wherein the control relationship includes a breeding sheep cost control relationship, a feed cost control relationship, a sheep house construction cost control relationship, and a labor cost control relationship; According to the number of goats raised and the control relationship, several conventional cost data related to goat breeding are determined, and the preliminary breeding cost is obtained by adding up the various conventional cost data.

[0007] Optionally, the method of obtaining multiple sets of conventional cost big data related to goat breeding costs through web crawling technology includes: Setting time fluctuation sensitivity coefficients corresponding to the breeding sheep cost data, the feed cost data, the sheep house construction cost data, and the labor cost data respectively; The data acquisition time span is calculated according to the time fluctuation sensitivity coefficient and the corresponding conversion formula, and each group of conventional cost big data corresponding to the acquisition time span is acquired through network crawling technology.

[0008] Optionally, the conversion formula is expressed as: ; in, Get the time span for the data, is the unit span duration, is the number of unit spans, is the time fluctuation sensitivity coefficient corresponding to any cost type, is the average value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type, It is the maximum value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type.

[0009] Optionally, the conventional cost data and the zero-carbon farming plan data are input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value, including: The breeding cost reduction prediction model calls the large language model to perform semantic analysis on the zero-carbon breeding plan data based on the conventional cost data to obtain zero-carbon breeding feature data, wherein the zero-carbon breeding feature data includes the number of zero-carbon equipment, the conversion rate of each zero-carbon equipment, and the association number between zero-carbon equipment and each cost type; The zero-carbon farming characteristic data is input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value.

[0010] Optionally, the breeding cost reduction prediction model includes a calling module and a Transformer core module, wherein the calling module is used to call the large language model and transmit each of the conventional cost data to the large language model; the Transformer core module is used to use a self-attention mechanism to process and predict the zero-carbon breeding feature data to obtain the breeding cost reduction value.

[0011] The present application also provides a goat breeding cost estimation system based on artificial intelligence, the system comprising a first estimation module, a second estimation module, and an accounting module; The first estimation module is used to determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; The second estimation module is used to input each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, and the farming cost reduction prediction model outputs a farming cost reduction value; The calculation module is used to calculate the target breeding cost based on the preliminary breeding cost and the breeding cost reduction value.

[0012] The present application also provides an electronic device, which includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0013] The present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present application also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program implements the method as described in any of the preceding items when executed by a processor.

[0015] The beneficial effect of the present invention is that: on the basis of considering the cost factors of traditional goat breeding, the present invention also considers the cost reduction of the farm after adopting zero-carbon breeding technology, and estimates the corresponding breeding cost reduction value, thereby obtaining a more accurate target breeding cost, which can provide more valuable guidance for the breeding behavior of breeders. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a method for estimating goat breeding costs based on artificial intelligence disclosed in an embodiment of the present application.

[0018] Figure 2 It is a structural schematic diagram of a goat breeding cost estimation system based on artificial intelligence disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] In the description of the present application, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear to indicate an orientation or position relationship, it is based on the orientation or position relationship shown in the drawings, or is the orientation or position relationship in which the product of the invention is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0023] In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. It should be noted that the features in the embodiments of the present application can be combined with each other without conflict.

[0024] See also Figure 1 , the embodiment of the present application discloses a method for estimating goat breeding costs based on artificial intelligence, the method comprising: Determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; Inputting each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, the farming cost reduction prediction model outputting a farming cost reduction value; The target breeding cost is calculated based on the preliminary breeding cost and the breeding cost reduction value.

[0025] In an embodiment of the present application, the present invention first determines several conventional cost data related to goat breeding based on the determined number of goats raised and the corresponding quantity-cost comparison relationship, including breeding sheep cost data, feed cost data, sheep house construction cost data, and labor cost data. These types of cost data are added up to obtain the preliminary breeding cost.

[0026] The above is the existing conventional breeding cost estimation method. The improvement of the present invention is that zero-carbon breeding technology is used in the goat breeding process, and a breeding cost reduction prediction model based on artificial intelligence is used. On the basis of the conventional cost data determined above, the expected zero-carbon breeding plan data is analyzed to determine the breeding cost reduction value corresponding to the conventional cost data. The initial breeding cost obtained above is subtracted from the breeding cost reduction value to get the target breeding cost.

[0027] Among them, zero-carbon farming technology refers to the use of technology, model, and equipment innovation to process the tail vegetables and straw (from the organic farm set up inside the farm) in the goat breeding farm as goat feed; and crush and mix the tail vegetables and straw from the organic farm with goat manure and urine in a certain proportion for composting, and use microbial degradation under aerobic conditions to make organic fertilizer for base vegetable planting; waste comprehensive utilization points can also be set up in the goat farm, and the organic fertilizer produced can be returned to the field to improve the soil environment and inhibit secondary soil salinization. That is, zero-carbon farming in the goat farm is achieved through internal circulation, which is conducive to reducing the cost of goat farming.

[0028] Therefore, the present invention not only considers the cost factors of traditional goat farming, but also considers the cost reduction of the farm after adopting zero-carbon farming technology, and estimates the corresponding reduction in farming costs, thereby obtaining a more accurate target farming cost, which can provide more valuable guidance for the farmers' farming behavior.

[0029] Optionally, the conventional cost data related to goat breeding is determined based on the number of goats raised, and the preliminary breeding cost is estimated based on each of the conventional cost data, including: Acquire multiple sets of conventional cost big data related to goat breeding costs by using web crawling technology, each set of conventional cost big data corresponds to the breeding goat cost data, the feed cost data, the goat house construction cost data, and the labor cost data; Use a large language model to perform semantic analysis on each of the conventional cost big data to obtain corresponding breeding quantity-cost corresponding feature data; Using a fitting model to fit the characteristic data corresponding to the breeding quantity and cost to obtain a control relationship, wherein the control relationship includes a breeding sheep cost control relationship, a feed cost control relationship, a sheep house construction cost control relationship, and a labor cost control relationship; According to the number of goats raised and the control relationship, several conventional cost data related to goat breeding are determined, and the preliminary breeding cost is obtained by adding up the various conventional cost data.

[0030] In the embodiment of the present application, multiple groups of conventional cost big data related to the cost type of goat breeding can be obtained by using network crawling technology. Since these conventional cost big data are basically unstructured data, it is difficult to directly extract the corresponding relationship between the breeding quantity and the corresponding type of cost. Therefore, the present invention first uses a large language model to perform semantic analysis and semantic understanding on each conventional cost big data, so as to determine the breeding quantity, corresponding cost type and the corresponding relationship between the two, that is, the breeding quantity-cost corresponding feature data involved, and then the fitting model is used to fit each breeding quantity-cost corresponding feature data, that is, to obtain the breeding sheep cost comparison relationship, feed cost comparison relationship, sheep house construction cost comparison relationship, and labor cost comparison relationship. Based on the aforementioned determined breeding quantity, a comparative analysis is performed in the above-mentioned corresponding comparison relationship, and the breeding sheep cost data, feed cost data, sheep house construction cost data, and labor cost data can be obtained. These types of costs are added together to obtain the preliminary breeding cost.

[0031] Among them, Large Language Models (LLM) refer to models with semantic understanding and semantic dialogue generation built based on models such as BERT, XLNet, and RoBERTa.

[0032] Optionally, the method of obtaining multiple sets of conventional cost big data related to goat breeding costs through web crawling technology includes: Setting time fluctuation sensitivity coefficients corresponding to the breeding sheep cost data, the feed cost data, the sheep house construction cost data, and the labor cost data respectively; The data acquisition time span is calculated according to the time fluctuation sensitivity coefficient and the corresponding conversion formula, and each group of conventional cost big data corresponding to the acquisition time span is acquired through network crawling technology.

[0033] In the embodiments of the present application, different types of costs have different sensitivities to time fluctuations. For example, labor costs have the highest stability and are unlikely to fluctuate significantly in the short term; breeding sheep costs, feed costs, and sheep house construction costs are more affected by market factors and are relatively more prone to fluctuations. In this regard, the present invention sets corresponding time fluctuation sensitivity coefficients for the above-mentioned cost types according to their fluctuation characteristics. The higher the degree of volatility of the corresponding cost type, the greater the corresponding time fluctuation sensitivity coefficient, and vice versa. Based on the time fluctuation sensitivity coefficient and the corresponding conversion formula, the data acquisition time span corresponding to each cost type is determined (based on the current moment or the specified moment, and acquired in the historical direction), and the corresponding data volume is obtained using web crawling technology. Conventional cost big data. Therefore, by analyzing the time volatility of different cost types, the amount of big data used for data fitting is correspondingly determined, thereby ensuring the stability of the above-mentioned control relationship of various cost types.

[0034] It should be noted that the time fluctuation sensitivity coefficient of the above-mentioned labor cost is the largest, while the time fluctuation sensitivity coefficients of breeding sheep cost, feed cost and sheep house construction cost can be determined separately based on historical laws, and the details will not be repeated here.

[0035] Optionally, the conversion formula is expressed as: ;

[0036] in, Get the time span for the data, is the unit span duration, is the number of unit spans, is the time fluctuation sensitivity coefficient corresponding to any cost type, is the average value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type, It is the maximum value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type.

[0037] In an embodiment of the present application, the time fluctuation sensitivity coefficient of each cost type is evaluated and calculated periodically, for example, once a year or half a year, so that historical data containing multiple time fluctuation sensitivity coefficients can be obtained, and the above-mentioned average value and maximum value are calculated based on this, and substituting them into the above-mentioned conversion formula can obtain the data acquisition time span corresponding to a certain cost type.

[0038] Optionally, the conventional cost data and the zero-carbon farming plan data are input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value, including: The breeding cost reduction prediction model calls the large language model to perform semantic analysis on the zero-carbon breeding plan data based on the conventional cost data to obtain zero-carbon breeding feature data, wherein the zero-carbon breeding feature data includes the number of zero-carbon equipment, the conversion rate of each zero-carbon equipment, and the association number between zero-carbon equipment and each cost type; The zero-carbon farming characteristic data is input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value.

[0039] In an embodiment of the present application, the breeding cost reduction prediction model first calls the aforementioned large language model, which uses the determined conventional cost data as a reference to perform semantic analysis on the input zero-carbon breeding plan data to obtain zero-carbon breeding feature data, including the number of zero-carbon equipment, the conversion rate of each zero-carbon equipment, and the association number between zero-carbon equipment and each cost type. Among them, the number of zero-carbon equipment refers to the zero-carbon equipment to be used mentioned in the zero-carbon farming plan, such as equipment for crushing and mixing tail vegetables and straw, equipment for mixing crushed and mixed materials with sheep manure and urine in a certain proportion for composting, sheep manure and urine collection equipment, etc.; the conversion rate of zero-carbon equipment refers to the conversion ratio of the corresponding equipment, for example, crushing and mixing equipment has a certain overflow loss rate (for example, some straw cannot be collected after being crushed), the organic matter produced by the mixed composting equipment also has a certain loss rate, and the sheep manure and urine collection equipment cannot collect all the sheep manure and urine when collecting sheep manure and urine, and there is a certain loss rate. The above loss rate can be determined in advance, and then the corresponding conversion rate is obtained; the association number of zero-carbon equipment and each cost type refers to the total number of associations between each zero-carbon equipment and the cost of breeding sheep, feed cost, sheep house construction cost, and labor cost. For example, the sheep manure and urine collection equipment is associated with the sheep house construction cost and labor cost, and the corresponding association number is 2, and the crushing and mixing is associated with the feed cost, sheep house construction cost, and labor cost, and the corresponding association number is 3. Adding the association numbers corresponding to all zero-carbon equipment will obtain the above total number of associations.

[0040] The above-obtained zero-carbon farming characteristic data is input into the farming cost reduction prediction model to obtain the predicted farming cost reduction value, for example, a reduction of 30%. In this way, the target farming cost is the initial farming cost multiplied by 70%.

[0041] Optionally, the breeding cost reduction prediction model includes a calling module and a Transformer core module, wherein the calling module is used to call the large language model and transmit each of the conventional cost data to the large language model; the Transformer core module is used to use a self-attention mechanism to process and predict the zero-carbon breeding feature data to obtain the breeding cost reduction value.

[0042] In the embodiment of the present application, corresponding to the above functions, the breeding cost reduction prediction model in the present invention includes two main modules: a calling module and a Transformer core module. The calling module is only used to call the aforementioned large language model and transmit the conventional cost data to the large language model, so that the large language model can extract zero-carbon breeding feature data. The Transformer core module is the core module of the breeding cost reduction prediction model of the present invention, which is used to conduct in-depth analysis of the zero-carbon breeding feature data extracted by the large language model, so as to predict the breeding cost reduction value.

[0043] The Transformer core module in the present invention can be obtained by self-construction, but the present invention is preferably obtained based on an existing general model (such as a BERT model), and it is necessary to use selected training samples to fine-tune the existing general model in a supervised manner until the training end conditions are met. The details will not be repeated.

[0044] See also Figure 2 , the embodiment of the present application also discloses a goat breeding cost estimation system based on artificial intelligence, the system includes a first estimation module, a second estimation module, and an accounting module; The first estimation module is used to determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; The second estimation module is used to input each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, and the farming cost reduction prediction model outputs a farming cost reduction value; The calculation module is used to calculate the target breeding cost based on the preliminary breeding cost and the breeding cost reduction value.

[0045] The present application also provides an electronic device, which includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0046] The present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0047] The present application also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program implements the method as described in any of the preceding items when executed by a processor.

[0048] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for estimating goat breeding costs based on artificial intelligence, characterized in that: The method comprises: Determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; Inputting each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, the farming cost reduction prediction model outputting a farming cost reduction value; The target breeding cost is calculated based on the preliminary breeding cost and the breeding cost reduction value.

2. A method for estimating goat breeding costs based on artificial intelligence according to claim 1, characterized in that: The conventional cost data related to goat breeding are determined based on the number of goats raised, and the preliminary breeding cost is estimated based on the conventional cost data, including: Acquire multiple sets of conventional cost big data related to goat breeding costs by using web crawling technology, each set of conventional cost big data corresponds to the breeding goat cost data, the feed cost data, the goat house construction cost data, and the labor cost data; Use a large language model to perform semantic analysis on each of the conventional cost big data to obtain corresponding breeding quantity-cost corresponding feature data; Using a fitting model to fit the characteristic data corresponding to the breeding quantity and cost to obtain a control relationship, wherein the control relationship includes a breeding sheep cost control relationship, a feed cost control relationship, a sheep house construction cost control relationship, and a labor cost control relationship; According to the number of goats raised and the control relationship, several conventional cost data related to goat breeding are determined, and the preliminary breeding cost is obtained by adding up the various conventional cost data.

3. A method for estimating goat breeding costs based on artificial intelligence according to claim 2, characterized in that: The method of obtaining multiple sets of conventional cost big data related to goat breeding costs through web crawling technology includes: Setting time fluctuation sensitivity coefficients corresponding to the breeding sheep cost data, the feed cost data, the sheep house construction cost data, and the labor cost data respectively; The data acquisition time span is calculated according to the time fluctuation sensitivity coefficient and the corresponding conversion formula, and each group of conventional cost big data corresponding to the acquisition time span is acquired through network crawling technology.

4. The method for estimating goat breeding costs based on artificial intelligence according to claim 3, characterized in that: The conversion formula is expressed as: ； in, Get the time span for the data, is the unit span duration, is the number of unit spans, is the time fluctuation sensitivity coefficient corresponding to any cost type, is the average value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type, It is the maximum value of the time fluctuation sensitivity coefficient in the historical data corresponding to the cost type.

5. The method for estimating goat breeding costs based on artificial intelligence according to claim 2, characterized in that: The conventional cost data and the zero-carbon farming plan data are input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value, including: The breeding cost reduction prediction model calls the large language model to perform semantic analysis on the zero-carbon breeding plan data based on the conventional cost data to obtain zero-carbon breeding feature data, wherein the zero-carbon breeding feature data includes the number of zero-carbon equipment, the conversion rate of each zero-carbon equipment, and the association number between zero-carbon equipment and each cost type; The zero-carbon farming characteristic data is input into a farming cost reduction prediction model based on artificial intelligence, and the farming cost reduction prediction model outputs a farming cost reduction value.

6. A method for estimating goat breeding costs based on artificial intelligence according to claim 5, characterized in that: The breeding cost reduction prediction model includes a calling module and a Transformer core module, wherein the calling module is used to call the large language model and transmit each conventional cost data to the large language model; the Transformer core module is used to use a self-attention mechanism to process and predict the zero-carbon breeding feature data to obtain the breeding cost reduction value.

7. A goat breeding cost estimation system based on artificial intelligence, characterized by: The system includes a first estimation module, a second estimation module, and a calculation module; The first estimation module is used to determine several conventional cost data related to goat breeding according to the number of goats raised, and estimate the preliminary breeding cost according to each of the conventional cost data; wherein the conventional cost data includes breeding goat cost data, feed cost data, goat house construction cost data, and labor cost data; The second estimation module is used to input each of the conventional cost data and the zero-carbon farming plan data into an artificial intelligence-based farming cost reduction prediction model, and the farming cost reduction prediction model outputs a farming cost reduction value; The calculation module is used to calculate the target breeding cost based on the preliminary breeding cost and the breeding cost reduction value.

8. An electronic device, characterized in that: The electronic device comprises: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images