Analytical device, analytical method, and analytical program

Abstract

Analyze the factors that cause changes in the financial situation of livestock farming. [Solution] The analysis device 1 comprises an analysis request receiving unit that receives requests for analysis of financial data related to livestock farming, an instruction input unit that inputs into the LLM instructions specifying the prerequisites for analysis and what to analyze, which are included in the analysis request, and an analysis result acquisition unit that acquires the financial analysis results output from the LLM. The instruction input unit inputs at least the following instructions to the LLM: to consider, as prerequisite knowledge when analyzing financial data, a data set that defines the relationship between patterns that combine data related to livestock production performance and events related to finances; to use actual values ​​of data related to the patterns and events when analyzing financial data; and, if the actual value differs from the value of a data item included in the event associated with the data item of the actual value, to analyze the factors that led to the difference.

Description

[Technical Field]

[0001] The present invention relates to an analysis device, an analysis method, and an analysis program. [Background technology]

[0002] Patent Document 1 below discloses a livestock management system that estimates the meat quality and health condition of livestock and predicts the sales amount of a livestock farmer based on the estimated condition of the livestock. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] WO2016 / 181604 publication Summary of the Invention [Problem to be solved by the invention]

[0004] In general, in order to stabilize management, it is important for managers to keep an eye on fluctuations in financial conditions, such as increases or decreases in sales and profits. The system in Patent Document 1 predicts future sales amounts based on the estimated condition of livestock, but it is not able to estimate the factors behind fluctuations in financial conditions.

[0005] The factors that cause fluctuations in the financial situation of livestock farming are a complex intertwining of various conditions related to production performance, such as the condition of livestock products and breeding conditions. It takes a great deal of effort to manage these various conditions and accurately grasp the factors that cause fluctuations in the financial situation.

[0006] Therefore, an object of the present invention is to provide an analytical device, an analytical method, and an analytical program that can analyze the factors that cause changes in the financial situation related to livestock farming. [Means for solving the problem]

[0007] An analysis system according to one embodiment of the present invention comprises an analysis request receiving unit that receives a request for analysis of financial data related to livestock farming; an instruction input unit that inputs into a language model the prerequisites for analysis and instructions specifying what to analyze, which are included in the received analysis request; and an analysis result acquisition unit that acquires the financial analysis results output from the language model. The instruction input unit inputs into the language model at least the following instructions: to consider, as prerequisite knowledge when analyzing financial data, a data set that defines the relationship between a pattern that combines data related to livestock production performance and financial-related events, which is stored in a memory unit; to use the actual values ​​of the data related to the patterns and events stored in the memory unit when analyzing financial data; and, if the actual value differs from the value of a data item included in the event associated with the data item of the actual value, to analyze the factors that caused the difference.

[0008] In addition, an analysis method according to another aspect of the present invention is a method executed by a processor, and includes a first step of receiving a request for analysis of financial data related to livestock farming, a second step of inputting into a language model the prerequisites for the analysis and instructions specifying what to analyze, which are included in the received analysis request, and a third step of acquiring the financial analysis results output from the language model, in which the second step inputs into the language model at least the following instructions: to consider, as prerequisite knowledge when analyzing financial data, a data set that defines the relationship between patterns that combine data related to livestock production performance and events related to finance, which is stored in a memory unit; to use the actual values ​​of the data related to the patterns and events stored in the memory unit when analyzing financial data; and, if the actual value differs from the value of a data item included in the event associated with the data item of the actual value, to analyze the factors that caused the difference.

[0009] Furthermore, an analysis program according to another aspect of the present invention causes a computer to function as an analysis request receiving unit that receives a request for analysis of financial data related to livestock farming, an instruction input unit that inputs into a language model the prerequisites for analysis and instructions specifying what to analyze, which are included in the received analysis request, and an analysis result acquisition unit that acquires the financial analysis results output from the language model, and the instruction input unit inputs into the language model at least the following instructions: to consider, as prerequisite knowledge when analyzing financial data, a data set that defines the relationship between a pattern that combines data related to livestock production performance and financial-related events, which is stored in the memory unit; to use the actual values ​​of the data related to the patterns and events stored in the memory unit when analyzing financial data; and, if the actual value differs from the value of a data item included in the event associated with the data item of the actual value, to analyze the factors that caused the difference.

[0010] According to these aspects, when instructions specifying the prerequisites for analysis and what to analyze are input into a language model based on a request for financial analysis, the instructions can include at least considering a dataset that defines the relationship between a pattern combining data on livestock production performance and financial-related events as prerequisite knowledge when analyzing the finances, using the actual values ​​of the data related to the patterns and events when analyzing the finances, and, if the actual values ​​differ from the values ​​of the data items included in the events associated with the data items of the actual values, analyzing the factors that led to the difference, and the financial analysis results can be output from the language model into which these instructions have been input.

[0011] This makes it possible to obtain financial analysis results that analyze the factors that led to the difference when actual values ​​differ from values ​​included in financial events, taking into account a data set that defines the relationship between patterns that combine data on livestock production performance and financial events. [Effects of the Invention]

[0012] According to the present invention, it is possible to provide an analysis device, an analysis method, and an analysis program that can analyze the factors that cause changes in the financial situation related to livestock farming when the situation changes. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 2 is a block diagram illustrating a physical configuration of an analysis device according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the functional configuration of the analysis device. [Figure 3] 10 is a flowchart illustrating the operation of the analysis device. DETAILED DESCRIPTION OF THE INVENTION

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A preferred embodiment of the present invention will be described with reference to the accompanying drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0015] [Analytical equipment configuration] An example of the physical configuration of an analysis device 1 according to an embodiment will be described with reference to Fig. 1. The analysis device 1 has a function of inputting actual results into a large language model (hereinafter also referred to as "LLM") to which a data set that defines the relationship between patterns combining data on production performance of livestock farming (including dairy farming) and events related to finance is added as background knowledge for analyzing finances related to livestock farming, and if the actual results differ from the values ​​of a data set registered in advance, having the LLM analyze the factors that caused the difference. Details of this function will be described later. The analysis device 1 is connected to one or more user terminals 2 via a network N.

[0016] The analysis device 1 includes, as its physical components, a processor 11, a storage device 12, and a communication interface 13, for example.

[0017] The processor 11 is, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), etc. The processor 11 executes a program 121 stored in the storage device 12 to realize various functions described below.

[0018] The storage device 12 is a computer-readable recording medium such as a disk drive or a semiconductor memory. The storage device 12 functions as a storage unit that stores a program 121 for implementing various functions of the analysis device 1, various data 122 used by the program 121, an LLM 123, and the like. Note that the LLM 123 does not necessarily have to be provided in the analysis device 1, but may also be provided in an external device or system.

[0019] The various data 122 includes, for example, data related to livestock farming and data sets described below.

[0020] Data related to livestock farming includes, for example, data on individual livestock, the number of individuals comprising a livestock herd such as a cow herd, livestock product data, production performance data (data related to the production performance of livestock farming), environmental data such as livestock sheds, feed data, breeding data, and financial data.

[0021] Individual livestock data can be managed for each identification information for identifying an individual livestock, and can include data items related to the individual livestock, such as test results and pedigree. Test results can include data items such as weight, body condition score (BCS), blood, feed intake (including feed design), genome, feces, medication, disease, and treatment.

[0022] In this embodiment, the description will be made mainly using cows as an example of livestock, but the livestock is not limited to cows. For example, the present invention can be applied to other livestock including pigs, birds, fish, etc. in the same way as cows.

[0023] The production performance data may include, as data items, data related to production performance, such as the quality of livestock products, production volume of livestock products, grading of livestock products, weight of livestock products, and reproductive performance. In the case of cattle, livestock products include, for example, beef, milk, and dairy products. Here, production performance data for dairy cattle includes, for example, milk quality, milk volume, milk price, number of culled head, number of shipped head, diseases, and herd dynamics. In the case of beef cattle, production performance data includes, for example, number of shipped head, grading, carcass unit price, carcass weight, number of culled head, diseases, and herd dynamics.

[0024] The financial data may include, as data items, data relating to finances, such as sales and expenses.

[0025] LLM123 is a generative AI model that generates and outputs content such as responses to input instructions (hereinafter also referred to as "prompts"). Note that the model is not limited to a large-scale language model, and may be a language model including a small language model, or a generative AI model that handles images and sounds in addition to language.

[0026] The communication interface 13 functions as a communication unit that connects to the network N and communicates with other devices on the network N. In this embodiment, it controls communication with one or more user terminals 2 operated by a user.

[0027] The functional configuration of the analysis device 1 according to the embodiment will be described with reference to Fig. 2. The analysis device 1 includes, as functional components for realizing various functions, a data collection unit 111, a data set setting unit 112, a performance data acquisition unit 113, an analysis request reception unit 114, an instruction input unit 115, an analysis result acquisition unit 116, an analysis result presentation unit 117, and an alert output unit 118. Each unit will be described below.

[0028] [Data Collection Department] The data collection unit 111 collects data related to livestock farming and stores it in the storage device 12. The collected data may include data managed by various systems related to livestock farming, such as a farm management system, data acquired by an IoT sensor, data recognized by an OCR (Optical Character Recognition / Reader), etc. The IoT sensor may be provided in a livestock barn or attached to the livestock. The collected data may be directly input from a user terminal 2 by a data manager or the like and stored in the storage device 12.

[0029] [Dataset Settings] The data set setting unit 112 stores a data set that defines the relationship between patterns of combining data on livestock production performance and events related to finances in the storage device 12. The data set is set based on collected data and is a collection of data that organizes how fluctuations in data on livestock production performance affect finances.

[0030] Patterns that combine data on livestock production performance can be set by arbitrarily combining, for example, data showing the unit carcass price, carcass weight, feed costs, etc. based on an understanding of market structure, data showing the shipping time, etc. based on knowledge of production technology, and data showing the unit carcass price, carcass weight, feed costs, etc. based on a financial indicator system.

[0031] For financial events, it is possible to set values ​​for, for example, sales and expenses, based on patterns that combine data on livestock production performance.

[0032] [Actual data acquisition section] The performance data acquisition unit 113 acquires data related to livestock farming, including data corresponding to the data items set in the dataset, as performance data, and stores it in the storage device 12. The performance data can be acquired from various systems, IoT sensors, OCR, etc., similar to the data related to livestock farming collected by the data collection unit 111 described above.

[0033] [Analysis Request Reception Department] The analysis request receiving unit 114 receives a request for financial analysis related to livestock farming. The financial analysis request includes, for example, instructions specifying the prerequisites for analyzing the financials and what to analyze. The analysis may also include predictions. The analysis request may be received from a user, or may be automatically received from the system based on the judgment of a program built into the analysis device 1, etc. Users include users who manage or operate the system, as well as users who receive the analysis results.

[0034] [Instruction input section] Based on the accepted analysis request, the instruction input unit 115 inputs instructions specifying the prerequisites for the analysis and what to analyze as prompts to the LLM 123. As instructions to be input to the LLM 123, it is preferable to use, for example, the instructions shown in (a) to (f) below.

[0035] (a) Considering a data set stored in the memory device 12, which defines the relationship between patterns of data on livestock production performance and financial-related events, as background knowledge when analyzing finances.

[0036] (b) Using the combined patterns of data on livestock production performance stored in the storage device 12 and the actual values ​​of data related to financial events when analyzing finances.

[0037] (c) When the actual value differs from the value of the data item in the data set associated with the data item of the actual value, analyze the factors that led to the difference.

[0038] (d) Building predictive models to forecast financial data.

[0039] (e) Proposing measures to improve the financial position.

[0040] (f) Suggest data that should be monitored to prevent a deterioration in financial status.

[0041] Here, specific examples of instructions to be input as prompts to the LLM 123 are described below in (1) to (5). Note that the instructions described in (1) to (5) are merely examples, and are not limited to the described contents.

[0042] (1) The instruction for the “Objective of the Analysis” was, “Conduct a comprehensive financial analysis to analyze the factors that affect the financial performance of fattening farms from multiple angles and support strategic decision-making to improve profitability. Quantify the interaction between market and production factors and propose feasible improvement strategies, including risk assessment and future forecasts.”

[0043] (2) The following instructions as a "Data Summary": The following dataset describes the financial performance of a fattening farm and related production and market data. Use this data and the background knowledge provided below to identify the root causes of financial fluctuations and conduct an analysis to optimize profitability. Data for the period covered: - Current Period Data ($[currentPeriod]): $[JSON.stringify(marketData, productionData, financialData, null, 2)] - Previous period data ($[previousPeriod]):$[JSON.stringify($[JSON.stringify(marketData, productionData, financialData, null, 2)]"

[0044] (3) The "analysis steps" are divided into five steps: "Phase 0: Confirmation of prerequisite knowledge," "Phase 1: Data exploration and preprocessing," "Phase 2: Decomposition and quantification of variable factors," "Phase 3: Multidimensional factor analysis," "Phase 4: Profitability and risk analysis," and "Phase 5: Construction of a predictive model." The instructions include instructions to list and input the elements belonging to each step as follows:

[0045] Phase 0: Check your prerequisite knowledge: Please refer to the following industry-specific prerequisites for your fattening financial analysis: **Understanding market structure** - Mechanism of price formation in the carcass market (price differences by grade, seasonal fluctuation patterns) - Supply and demand balance factors (domestic production volume, import volume, consumption trends) - Market fluctuation factors (exchange rates, feed prices, impact of epidemics) **Production technology knowledge** - Growth patterns by fattening stage (introduction → rearing → finishing) - Grading factors (BMS, yield, weight, defects) - Relationship between feeding management and economic efficiency (feed efficiency, optimization of shipping age) **Financial indicator system** - Sales revenue = number of animals x average carcass weight x average unit price - Variable cost structure (feed costs, introduction costs, other direct costs) - Fixed cost structure (depreciation, labor costs, utility costs) - Profitability indicators (gross profit margin, operating profit margin, profit per head)

[0046] Here, the prerequisite knowledge for Phase 0 is composed of industry-specific prerequisite knowledge broken down into three elements: understanding of market structure, knowledge of production technology, and financial indicator systems. The three elements interact with each other to form a "logic that organizes how fluctuations in production performance affect finances." This logic is used to construct a dataset that defines the relationship between patterns that combine data on livestock production performance and financial-related events.

[0047] For example, when looking at profitability per animal, if you want to make causal inferences about cases where carcass performance has improved compared to the previous month despite no change, you first need to identify which elements of the financial indicator system (e.g., carcass price, carcass weight, feed costs, etc.) are responsible for the improvement. If the explanation cannot be given by the financial indicator system alone, or if verification of the accuracy is unclear, you will need to further deepen your analysis by incorporating elements such as an understanding of market structure and knowledge of production technology.

[0048] Specifically, the causal inference for the improvement in profitability can be analyzed as follows: (i) in addition to the increase in the unit price of carcass meat (financial indicator system), differences in unit price due to meat quality (market structure understanding) have had an impact; and (ii) in addition to the decrease in feed costs (financial indicator system), early shipping (production technology knowledge) has led to a decrease in the unit price of carcass meat (market structure understanding), but the improvement in feed costs (financial indicator system) has had an impact.

[0049] Phase 1: Data exploration and preprocessing **Data Quality Check** - Identifying missing and outlier values ​​and proposing treatment strategies - Verify data integrity (number of animals x weight x unit price = sales) - Check for period comparability (consistency of data range and aggregation method) **Calculation of basic statistics** - Descriptive statistics of sales, head count, weight and unit price - Changes in grade composition - Changes in distribution of shipping age - Stability assessment using coefficient of variation

[0050] Phase 2: Decomposition and quantification of variability factors **Factor breakdown of sales fluctuations** The contribution of each factor is quantified based on the following formula: … Sales fluctuation = Number effect + Weight effect + Unit price effect + Cross effect Number effect = (Number of heads in the current period - Number of heads in the previous period) × Average weight in the previous period × Average unit price in the previous period Weight effect = Number of heads in the current period × (Average weight in the current period - Average weight in the previous period) × Average unit price in the previous period Unit price effect = Number of animals in the current period × Average weight in the current period × (Average unit price in the current period - Average unit price in the previous period) … **Detailed analysis of unit price fluctuations** - Contribution analysis of unit price fluctuations by grade - Impact of changes in grade structure - Separation of market factors vs. quality factors - Monetary impact of changes in defect rates

[0051] “Phase 3; Multidimensional factor analysis: **Market Factor Analysis** - Correlation analysis: Calculation of correlation coefficient between market index and realized unit price - Regression analysis: Quantifying the impact of market fluctuations on unit prices - Benchmark analysis: Comparison with regional and national averages - Seasonal analysis: Seasonal adjustment based on historical data **Production Factor Analysis** - Correlation analysis between feeding management indicators and performance - Identifying important factors through multiple regression analysis - Calculation of production efficiency indicators (feed conversion rate, daily weight gain, etc.) - Measuring the effectiveness of shipping strategies (profitability analysis by age) **Integrated Analysis** - Extraction of latent factors using principal component analysis - Categorization of shipment groups through cluster analysis - Calculating feature importance using machine learning methods (random forest, etc.)

[0052] Phase 4: Profitability and Risk Analysis **Revenue Structure Analysis** - Breakdown of factors affecting gross profit margin - Analysis of profit per head components - Calculation of fixed cost recovery rate - Break-even analysis (by number of animals and unit price) **Risk Assessment** - Quantification of price fluctuation risk (VaR calculation) - Production risk assessment (standard deviation of weight and grade) - Analysis of correlation risk (relationship between market conditions and production performance) - Scenario analysis (optimistic, pessimistic, realistic scenarios)

[0053] Phase 5: Building a predictive model - Short-term forecast (next sales and profitability) - Medium-term trend forecast (seasonally adjusted) - Sensitivity analysis (effect of changes in key variables) - Model accuracy evaluation (MAPE, RMSE)

[0054] Here, the Phase 5 predictive model is constructed by LLM123 using the datasets listed in the "Data Overview" and the results of the analyses in the "Analysis Steps" from Phase 0 to Phase 4.

[0055] (4) The "Output Request" includes four output items: "A. Executive Summary," "B. Detailed Analysis Results," "C. Strategic Improvement Proposals," and "D. Proposals for Monitoring and Management Indicators," and the instructions to input the elements belonging to each item as follows: After the "Output Request" is input, LLM123 will generate and output the information specified in the "Output Request" using the data set listed in the "Data Summary" and the results of the analysis in the "Analysis Steps."

[0056] A. Executive Summary: - Core factors of financial fluctuations (3-5 points) - Urgent measures (immediate measures to improve profitability) - Profit improvement potential (quantitative target value) - Risk warning (variable factors to be aware of)

[0057] Detailed analysis results: **Ranking of factors affecting change** - Display the contribution of each factor to sales fluctuations in monetary and percentage terms - Demonstration of statistical significance (p-value < 0.05) - Display of confidence intervals **Profitability Analysis** - Decomposition of fluctuations in gross profit margin - Factors affecting profit per head - Benchmark comparison (standard deviation display) - Time series changes in profit efficiency index **Interaction of market and production factors** - The impact of market factors on profits (β coefficient) - Quantify the impact of production improvements on profitability - Numerical evidence for optimal shipping strategies

[0058] C. Strategic Improvement Proposals: **Immediate Improvements** - **Shipping timing optimization**: Proposal of optimal shipping month based on monthly market price analysis - **Grade improvement measures**: Expected profit increase through specific improvements in feeding management - **Defect reduction measures**: Defect cause analysis and cost-effectiveness of countermeasures **Medium- to Long-Term Strategy** - **Production planning optimization**: Strategic allocation of head count and shipping time - **Strengthening risk management**: Price fluctuation risk hedging strategy - **Investment decision index**: ROI calculation for capital investment and technology introduction

[0059] D. Proposed monitoring and management indicators: **Daily monitoring indicators** - Daily weight gain per head (target value: 1.0 kg or more) - Feed conversion ratio (target value: 8.0 or less) - Grade A or higher ratio (target: 70% or higher) **Monthly management indicators** - Gross profit margin (within ±5% compared to the same month last year) - Sales per head (within ±10% of benchmark) - Shipping age (target: 28-30 months) **Alert Settings** - The unit price decline rate is more than -10% compared to the previous month - Less than 60% of students are grade A or above - Profit per head is -20% or more compared to the same month last year

[0060] (5) Instructions to enter the following points as "Points to Note when Analyzing and Proposing":

[0061] Statistical rigor - Always display statistical significance (p-value) - Sample size validation - Correction for multiple testing **Practicality First** - Limited to proposals that are feasible for farm management - Specify the payback period (recommended within 3 years) - Present a phased implementation plan **Economic considerations** - Quantify the cost-effectiveness of improvement measures - Calculating opportunity loss - Clearly articulate investment risks and returns **Consideration of industry characteristics** - Proposals taking into account the fattening cycle (24-30 months) - Measures to deal with seasonal and market fluctuations - Adjustment of proposals based on size and location

[0062] [Analysis result acquisition section] The analysis result acquisition unit 116 acquires the financial analysis results output from the LLM 123 to which instructions specifying the preconditions for analysis and what to analyze have been input.

[0063] [Analysis result presentation section] The analysis result presentation unit 117 visualizes and presents the financial analysis results output from the LLM 123 in a format desired by the user. Users to whom the analysis results are presented may include, for example, livestock producers, livestock farmers, financial institutions, feed companies, logistics companies, veterinarians, and animal pharmaceutical companies.

[0064] The analysis results can be output in the form of a report, for example. In this case, based on values ​​such as financial data output as the analysis results, causal inferences such as what specifically is happening and what is presumed to be the cause can be presented in the form of a report. Note that the display format is not limited to a report; for example, the analysis results can be displayed on the screen of the user terminal 2, and when a specific numerical value is hovered over, a summarized causal inference can be displayed as text.

[0065] [Alert output section] The alert output unit 118 outputs an alert when alert information indicating that an abnormality has been found in the data being monitored is output from the LLM 123. The alert may be output as a message such as text, or may be output using sound, video, or the like.

[0066] The data to be monitored and the thresholds may be arbitrarily set by the user, or may be set in a system program. For example, a user may input a monitoring instruction specifying the data to be checked and the thresholds as a prompt to the LLM 123. Alternatively, the monitoring instruction may be input to the LLM 123 by executing a program incorporating the monitoring instruction in which predetermined data and thresholds are set as the data to be monitored and the thresholds.

[0067] [Analyzer operation] An example of the operation of the analysis device 1 according to the embodiment will be described with reference to FIG.

[0068] First, the analysis request receiving unit 114 of the analysis device 1 receives a request for analysis of finances related to livestock farming from the user terminal 2 operated by the user (step S101).

[0069] Next, the instruction input unit 115 of the analysis device 1 inputs instructions specifying the prerequisites for analyzing the finances and what to analyze as a prompt to the LLM 123 based on the financial analysis request received in step S101 above (step S102).

[0070] Next, the analysis result acquisition unit 116 of the analysis device 1 acquires the financial analysis results output from the LLM 123 to which the instruction was input in step S102 (step S103).

[0071] Next, the analysis result presentation unit 117 of the analysis device 1 visualizes and presents the financial analysis results acquired in step S103 in a format desired by the user (step S104), and then ends this operation.

[0072] As described above, according to the analysis device 1 of the embodiment, when instructions specifying the prerequisites for analysis and what to analyze are input to the LLM123 based on a financial analysis request, the instructions can include at least the following: to consider a data set that defines the relationship between patterns combining data on livestock production performance and events related to finances as prerequisite knowledge when analyzing finances; to use actual values ​​of data related to patterns and events when analyzing finances; and, if the actual values ​​differ from the values ​​of data items included in the events associated with the data items of the actual values, to analyze the factors that led to the difference; and the financial analysis results can be output from the LLM123 to which these instructions have been input.

[0073] This makes it possible to obtain financial analysis results that analyze the factors that led to the difference when actual values ​​differ from values ​​included in financial events, taking into account a data set that defines the relationship between patterns that combine data on livestock production performance and financial events.

[0074] Therefore, with the analysis device 1 according to the embodiment, when the financial situation of livestock farming changes, it becomes possible to analyze the factors that caused the change.

[0075] The present invention is not limited to the above-described embodiment, and can be embodied in various other forms without departing from the spirit of the present invention. Therefore, the above-described embodiment is merely an example in all respects and should not be interpreted as being limiting. For example, the order of the above-described processing steps can be arbitrarily changed or executed in parallel as long as no contradiction occurs in the processing content. [Explanation of symbols]

[0076] 1...analysis device, 2...user terminal, 11...processor, 12...storage device, 13...communication interface, 111...data collection unit, 112...data set setting unit, 113...performance data acquisition unit, 114...analysis request reception unit, 115...instruction input unit, 116...analysis result acquisition unit, 117...analysis result presentation unit, 118...alert output unit, 121...program, 122...data, 123...large-scale language model (LLM), N...network

Claims

1. an analysis request reception unit that receives a request for analysis of finances related to livestock farming; an instruction input unit that inputs, into a language model, prerequisites for analysis and instructions specifying what to analyze, which are included in the accepted analysis request; an analysis result acquisition unit that acquires the financial analysis result output from the language model; Equipped with The instruction input unit inputs at least the following as the instruction: Considering a data set that defines the relationship between a pattern of combined data on livestock production performance and the financial events stored in a storage unit as background knowledge when analyzing the financial results; using the actual values ​​of the data related to the patterns and the events stored in the storage unit when analyzing the finances; and When the performance value differs from the value of a data item included in the event associated with the data item of the performance value, analyzing the cause of the difference; input into the language model; Analyzer.

2. the instruction input unit further inputs, as the instruction, to the language model, an instruction to construct a prediction model for predicting the financial data; The analytical device according to claim 1 .

3. the instruction input unit further inputs, as the instruction, to the language model, a suggestion of an improvement measure for improving the financial situation. The analytical device according to claim 1 .

4. the instruction input unit further inputs, as the instruction, to the language model, a suggestion of a data item that should be monitored in order to prevent a deterioration in the financial situation; The analytical device according to claim 1 .

5. A data collection unit that collects data related to livestock farming, including data related to production performance; A data set setting unit that stores the data set set based on the collected data related to livestock farming in the storage unit; The analytical device of claim 1 further comprising:

6. Further provided is a performance data acquisition unit that acquires performance values ​​of data related to livestock farming including data related to production performance and stores them in the storage unit, The analytical device according to claim 1 .

7. an analysis result presentation unit that visualizes and presents the financial analysis results output from the language model in a format desired by a user; The analytical device according to claim 1 .

8. an alert output unit that outputs an alert when alert information indicating that an abnormality has been found in data of a predetermined monitoring target is output from the language model; The analytical device according to claim 1 .

9. The production performance includes any one of livestock product quality, livestock product production, livestock product grading, livestock product weight, and reproductive performance; The analytical device according to claim 1 .

10. The financial information includes sales and expenses. The analytical device according to claim 1 .

11. 1. A processor-implemented method comprising: The first step is to receive a request for a financial analysis of livestock farming. a second step of inputting into a language model the preconditions for analysis and instructions specifying what to analyze, which are included in the accepted analysis request; a third step of obtaining the financial analysis results output from the language model; Including, The second step includes, as the instruction, at least: Considering a data set that defines the relationship between a pattern of combined data on livestock production performance and the financial events stored in a storage unit as background knowledge when analyzing the financial results; using the actual values ​​of the data related to the patterns and the events stored in the storage unit when analyzing the finances; and When the performance value differs from the value of a data item included in the event associated with the data item of the performance value, analyzing the cause of the difference; input into the language model; Analysis method.

12. an analysis request reception department that receives requests for analysis of financial matters related to livestock farming; an instruction input unit that inputs into a language model the prerequisites for analysis and instructions specifying what to analyze, which are included in the accepted analysis request; an analysis result acquisition unit that acquires the financial analysis results output from the language model; and make the computer function as The instruction input unit inputs at least the following as the instruction: Considering a data set that defines the relationship between a pattern of combined data on livestock production performance and the financial events stored in a storage unit as background knowledge when analyzing the financial results; using the actual values ​​of the data related to the patterns and the events stored in the storage unit when analyzing the finances; and When the performance value differs from the value of a data item included in the event associated with the data item of the performance value, analyzing the cause of the difference; input into the language model; Analysis program.

Images