Agricultural and pastoral whole industry chain scene service intelligent linkage method based on farming cycle identification

Abstract

The invention discloses an agricultural and pastoral whole industry chain scene service intelligent linkage method based on agricultural cycle identification, and relates to the technical field of agricultural informatization. Performing farming cycle identification through a preset behavior-cycle correlation model based on the farming condition data, and obtaining a farming cycle state where the user is currently located; according to the farming cycle state of the user, matching and triggering a predefined chained service rule, and generating an initial service recommendation sequence; the chained service rule adopts a state-event-action structure, a completion event of a previous service action is a condition for triggering a next service action, and a final service recommendation is generated through a preset parameterization model based on an initial service recommendation sequence; the final service recommendation is actively pushed to the user terminal; obtaining execution feedback data of the user terminal on the final recommendation service; and optimizing the behavior-cycle correlation model and / or the parameterized model according to the execution feedback data. According to the invention, the accuracy, controllability and intelligent level of agricultural services are improved.

Description

Technical Field

[0001] This invention relates to the field of agricultural information technology, and in particular to a method, device, equipment and medium for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle identification. Background Technology

[0002] With the rapid development of agricultural information technology, various agricultural service platforms have emerged, providing farmers with single or partially integrated services such as agricultural input e-commerce, agricultural machinery dispatching, agricultural technology consultation, and agricultural product sales. These platforms typically present different service modules in the user interface through menu-style categorization, such as "Buy Agricultural Inputs," "Find Agricultural Machinery," and "Sell Products," etc.

[0003] However, existing technologies merely display various functional service modules, which are independent of each other. Users actively search for and select services based on their own needs, essentially remaining a passive response model to user requests, thus offering limited improvement in production and operational efficiency. For example, even when financial services involve recommendation mechanisms, they are typically based on static tags or simple historical records of individual modules, which are disconnected from users' actual debt repayment ability, production scale, and supply chain performance, leading to mismatched recommendations and poor risk controllability. Summary of the Invention

[0004] This invention provides a method, device, equipment, and medium for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle identification, which solves the problem of how to improve the accuracy, controllability, and intelligence level of agricultural services.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a method for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle recognition is provided, including: Acquire agricultural data; the agricultural data includes static master data, dynamic behavioral data, and production / post-production business data from user terminals, visual data of crops, environmental and meteorological data, and / or market data; Based on the agricultural data, the agricultural cycle is identified through a pre-set behavior-cycle correlation model to obtain the current agricultural cycle status of the user. Based on the user's described agricultural cycle status, predefined chained service rules are matched and triggered to generate an initial service recommendation sequence. These chained service rules adopt a state-event-action structure, where the completion of a previous service action is a condition for triggering the next service action. Based on the initial service recommendation sequence, the final service recommendation is generated through a pre-set parameterized model; The final service recommendation will be proactively pushed to the user's terminal; Obtain the user terminal's execution feedback data for the final recommendation service; optimize the behavior-cycle association model and / or the parameterized model based on the execution feedback data.

[0006] Secondly, a smart linkage device for the entire agricultural and livestock industry chain based on agricultural cycle recognition is provided, including: The agricultural data acquisition module is used to acquire agricultural data; the agricultural data includes static master data, dynamic behavioral data and production / post-production business data of user terminals, visual data of crops, environmental and meteorological data, and / or market data. The agricultural cycle identification module is used to identify the agricultural cycle based on the agricultural data and through a preset behavior-cycle correlation model to obtain the current agricultural cycle status of the user. The initial service recommendation module is used to match and trigger predefined chained service rules based on the user's described agricultural cycle status, generating an initial service recommendation sequence. The chained service rules adopt a state-event-action structure, where the completion of the previous service action is a condition for triggering the next service action. The final service recommendation module is used to generate final service recommendations based on the initial service recommendation sequence using a preset parameterized model. The service recommendation module is used to proactively push the final service recommendation to the user terminal; An execution feedback module is used to obtain execution feedback data from the user terminal for the final recommendation service; and to optimize the behavior-period association model and / or the parameterized model based on the execution feedback data.

[0007] Thirdly, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, performs the steps of the method as described in the first aspect.

[0008] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect. Attached Figure Description

[0009] Figure 1 A schematic flowchart illustrating an intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification, provided for an embodiment of this application; Figure 2 A schematic flowchart illustrating another intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification, provided for an embodiment of this application; Figure 3 This is a schematic diagram of a system architecture provided for an embodiment of this application. Detailed Implementation

[0010] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions in the embodiments of this application are clearly described. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art are within the scope of protection of this application.

[0011] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0012] The steps described in this application and the flowcharts in the accompanying drawings are not necessarily strictly executed according to the step numbers; the execution order of the steps can be changed. Furthermore, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be broken down into multiple steps.

[0013] This specification provides a method for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle identification, and also relates to an intelligent linkage device for agricultural and livestock industry chain scenarios based on agricultural cycle identification, a computer device, and a computer-readable storage medium. The following describes each item in detail with reference to the accompanying drawings and preferred embodiments.

[0014] Please see Figure 1-3 This application provides a method for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle identification, including: Step S1: Obtain agricultural data; The agricultural data includes static master data, dynamic behavioral data, and production / post-production business data from user terminals, visual data of crops, environmental and meteorological data, and / or market data.

[0015] Step S2: Based on the agricultural data, identify the agricultural cycle through a preset behavior-cycle association model to obtain the current agricultural cycle status of the user.

[0016] Step S3: Based on the user's stated agricultural cycle status, match and trigger predefined chained service rules to generate an initial service recommendation sequence; The chained service rules adopt a state-event-action structure, where the completion event of the previous service action is the condition for triggering the next service action.

[0017] Step S4: Based on the initial service recommendation sequence, generate the final service recommendation using a preset parameterized model.

[0018] Step S5: Actively push the final service recommendation to the user terminal.

[0019] Step S6: Obtain the execution feedback data of the user terminal on the final recommendation service; optimize the behavior-cycle association model and / or the parameterized model based on the execution feedback data.

[0020] Furthermore, the behavior-period association model is configured as follows: Construct a knowledge graph of crop-region-standard agricultural calendar; Based on the knowledge graph, a baseline agricultural calendar corresponding to the user's crops and geographical location is obtained; The dynamic behavior data is matched with the preset standard operations in the baseline agricultural calendar to obtain the initial agricultural cycle state.

[0021] Furthermore, the order and / or contract terms in the business data during and / or after production are obtained, and the status of the first agricultural cycle is determined based on the order and / or contract terms. The first agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

[0022] Furthermore, the visual data of crops is obtained through remote sensing image analysis of the user's field. The behavior-cycle association model is also configured to: determine the state of the second agricultural cycle based on the visual data; The second agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

[0023] Furthermore, the behavior-cycle correlation model is also configured to calibrate the initial agricultural cycle state based on environmental and meteorological data.

[0024] Furthermore, the step of generating the final service recommendation based on the initial service recommendation sequence using a pre-set parameterized model includes: Based on the agricultural data and the pre-set credit scoring model, the user's credit score is obtained; Based on the credit score, dynamically configure the transaction terms and / or risk control strategies in specific service options; Based on the credit score, the user's cash flow data, and the pre-set cost model, a precise financial limit matching the user's current production scale is calculated for specific financial services.

[0025] Furthermore, some or all of the rules in the chain rules are encoded into blockchain smart contracts; when the triggering conditions are met, the smart contracts are executed automatically.

[0026] Specifically: For chain service rules involving payment or performance, a first type of blockchain smart contract is generated; the first type of smart contract is configured to automatically execute fund locking, transfer or release operations after a predefined business event is verified. For chain-based service rules involving risks or safeguards, a second type of blockchain smart contract is generated; the second type of blockchain smart contract is configured as follows: Risk rules and thresholds are set based on the aforementioned environmental and meteorological data and / or market data; When the environmental, meteorological and / or market risks associated with the current agricultural cycle state are identified as exceeding a preset threshold, service matching is automatically triggered, and the matched insurance products or financial hedging products are associated with the final service recommendation. With authorization, trigger automatic insurance enrollment and / or automatic claims processing.

[0027] The behavior-cycle association model and / or the parameterized model are optimized based on the execution feedback data using an incremental learning algorithm. The incremental learning is performed within a federated learning framework. The user's local feedback data participates in model training on the local device, and only the encrypted model parameters are updated and uploaded to the server for global model aggregation.

[0028] For example, the system architecture of the intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification in this application embodiment is as follows: Figure 3 As shown, it includes: an application layer, an intelligent decision-making layer, a data processing and identification layer, and a data source layer. Taking Mr. Li, a winter wheat farmer in Province G, as an example: User background: Li, who runs a 200-mu family farm in a major agricultural county in G province, mainly grows winter wheat, and is a heavy user of the platform.

[0029] Agricultural cycle identification is based on an agricultural cycle identification engine, which is the foundation of the platform's intelligence. It accurately identifies the agricultural stage that the user is in through multi-source data fusion and dynamic calibration mechanisms.

[0030] Static master data: This consists of basic data including user geographic location, crop variety, planting scale, etc., and is generally stored in the form of archives. For example: Li's archive {Geographic location: XX County, G Province, Crop type: Winter wheat, Planting area: 200 mu}.

[0031] Dynamic behavioral data: This refers to user action data. For example, Li's action records on the platform, such as his purchase of wheat seeds and base fertilizer in late September.

[0032] Production / Post-Production Business Data: This includes data such as orders and contracts from the production process (procurement, processing, etc.) and post-production process (warehousing, sales, transactions, etc.). For example, a pre-sale agreement signed between Mr. Li and a grain processing company (which specifies the variety, quantity, and delivery time requirements).

[0033] Environmental and meteorological data: Real-time weather forecast data for the G province region, including precipitation, temperature, humidity, and other environmental and meteorological conditions.

[0034] Visual data of crops can be acquired simultaneously with environmental and meteorological data. For example, real-time meteorological data for province G can be combined with multispectral drone or satellite remote sensing imagery. Using an AI image recognition model, the crop growth (such as leaf area index and vegetation cover) of Li's field can be analyzed to form a "visual agricultural condition" state vector.

[0035] Market data: including market prices of relevant crops, relevant policies, and other data.

[0036] A knowledge graph of crop-region-standard agricultural calendar serves as the knowledge base data. For example, the sowing period for winter wheat in Province G is from late September to early October. This knowledge graph can be further used to construct a cross-crop, cross-regional agricultural strategy association network through graph neural networks, supporting transfer learning.

[0037] The method and process for identifying the agricultural cycle for user Li are as follows: Baseline prediction: Based on Li's winter wheat variety and the location of XX County, G Province, the engine retrieved the baseline agricultural calendar from the knowledge graph: Sowing period: September 25 - October 10.

[0038] Dynamic calibration: Based on visual calibration: The system analyzes remote sensing images. If it identifies a field that has been plowed and has no crops (visual status "awaiting sowing"), this high-confidence visual signal will be used as an independent input and fed into the fusion algorithm in parallel with behavioral data, significantly improving the accuracy of "sowing period" determination.

[0039] Based on behavioral calibration: On September 20th, the system detected that Li had purchased wheat seeds and base fertilizer. This behavior was identified as a strong signal through a pre-trained behavior-cycle association model (e.g., the "correlation weight between seed purchase and sowing period" learned from historical data). The engine used a weighted fusion algorithm to adjust the state judgment from "sowing preparation period" to "sowing period" in advance.

[0040] Based on business data calibration: The engine also analyzes Li's pre-sale agreement and identifies that "the order requires early-maturing varieties", thereby further adjusting the agricultural cycle: sowing ahead of time.

[0041] Based on environmental and meteorological calibration: Combining meteorological data indicating "recent precipitation", the engine adds the suggestion "sow while the soil is moist" to the output status.

[0042] Status output: The engine finally outputs a structured recognition result for Li: {User ID: Li, Current period: sowing period; Crop: winter wheat; Expected remaining days: 15 days; Next period: seedling emergence period; Calibration information: sowing while the soil is moist}.

[0043] The agricultural cycle identification process in this application introduces a new data dimension of "visual agricultural conditions," achieving collaborative perception between land and space through remote sensing AI. This upgrades cycle identification from a single time-based logical judgment to a multi-dimensional verification based on "spatiotemporal-visual" factors. Furthermore, by utilizing knowledge graphs and graph neural networks, cross-regional and cross-crop transfer learning of agricultural strategies can be achieved, enabling the system to quickly adapt to new users and new varieties.

[0044] This application proposes a service linkage and closed-loop control mechanism that triggers a series of linked services based on the identified agricultural cycle, forming an intelligent closed loop.

[0045] Construction and triggering of the linkage rule base: The rule base adopts a chain structure of "state-event-action," with dependencies between rules. To ensure transparent and trustworthy execution, key chain rules are encoded into blockchain smart contracts. For example: Rule 1: IF Period = "Sowing Period" THEN Trigger Services: ① Recommended Seeder Service; ② Recommended Soil Moisture Monitor.

[0046] Rule 1.1 (Smart Contract): IF planting service order confirmation THEN locks the farmer's prepayment on the blockchain and generates an execution pending state.

[0047] Rule 2: IF event = "Sowing operation completed" (automatically confirmed by data returned from agricultural machinery IoT device or manually confirmed by user) & period = "Sowing period" THEN Trigger services: ① Recommend agricultural input packages for seedling pest and disease control; ② Prompt users to apply for "Seedling Management Loan".

[0048] Rule 2.1 (Smart Contract): IF job completion verification passes THEN, automatically release the funds locked on the blockchain to the service provider, and trigger the next service contract.

[0049] Based on the output "sowing period" status, the system automatically matches and triggers preset chained service rules. First, rule 1 is triggered, generating an initial service list for Mr. Li: "Recommended Seeder Service" and "Recommended Soil Moisture Monitor." At this point, the rule engine enters a waiting state, and the trigger condition for rule 2 (recommended agricultural supplies and loans) is set to depend on the occurrence of the event "sowing operation completed." This establishes a dependency relationship between services, ensuring service continuity and timing. After the system pushes the seeder service to Mr. Li, he completes sowing and confirms "operation completed." The system then triggers rule 2, pushing agricultural supply packages and loan application portals. Through the chained rule design of "status-event-action," it transforms service recommendations from a parallel stack into an ordered, flowing "service stream."

[0050] Trusted execution layer trigger: For services involving payment or key performance (such as agricultural machinery dispatch), the system will generate corresponding blockchain smart contracts to lock in the obligations and financial status of relevant parties.

[0051] Real-time processing of credit and funding coupling: Dynamic and chain-like credit coupling: When recommending services, the system calls upon the user's credit scoring model in real time, based not only on the user's history but also on real-time supply chain credit. For example, the system analyzes the buyer's creditworthiness, logistics information in transit, and warehousing records of the pre-sale agreement signed by Mr. Li, forming a "supply chain credit IOU." For Mr. Li, with an AA credit rating and healthy supply chain transactions, the system recommends "full-chain credit sales" services. For example, the system dynamically adds a credit transaction clause of "payment within 7 days after operation" to the seeder service option.

[0052] Coupling of fund management: The system integrates fund flow data and uses cost models (such as a standard cost library based on planting area and crop type) to calculate precise loan amounts. For example, it calculates a loan amount of 50,000 yuan for Mr. Li's "seedling management loan," rather than a general range.

[0053] Risk-Insurance Linkage Innovation: If the credit funding module identifies a high meteorological risk in the current period, it will simultaneously trigger the insurance product matching engine, generating insurance recommendations and integrating them into the final service recommendation list. Furthermore, when the system identifies that a user has entered a critical agricultural stage (such as the flowering period) and an abnormal weather warning is issued, it automatically triggers a "weather index insurance" recommendation and can automatically complete the insurance purchase through a smart contract based on user authorization. When meteorological conditions reach the claim threshold, the claims process can be automatically initiated, achieving a closed loop of "risk warning - insurance - automatic claims." This is not simply a combination of functions, but a deep, real-time linkage based on period identification, environmental data, and financial products.

[0054] The service linkage and closed-loop control mechanism of this application combines chain-based service rules with blockchain smart contracts to create a traceable, tamper-proof, and automatically executed "trustworthy service pipeline," solving the trust and payment automation challenges in multi-party collaboration. It pioneers a real-time automatic triggering mechanism for "agricultural cycle - abnormal weather - insurance products," achieving second-level linkage between production risk management and financial instruments. Risk control actions (credit and fund verification) are seamlessly embedded into the service recommendation process through a parameterized model, realizing real-time, flexible risk control within the service flow.

[0055] Optimized and personalized service information was proactively pushed to Li's APP interface, such as: "It's the perfect time for sowing! We recommend deposit-free sowing services for you. Enjoy a discount on agricultural supplies after sowing >>".

[0056] Meanwhile, the interface design guides users through the entire process from calling in agricultural machinery to purchasing agricultural supplies, and then to applying for financial assistance, providing a seamless service loop. User feedback (such as Mr. Li confirming "sowing operation completed") is recorded and fed back by the system. First, this event immediately triggers rule 2, which is in a waiting state, pushing the service flow to the next step. Second, this feedback data is fed into an incremental learning algorithm for: Optimize the association weight between the behavior of "purchasing base fertilizer" and "sowing period" in the agricultural cycle recognition engine to make future recognition more accurate.

[0057] Update the parameters of the credit scoring model; for example, Li's timely confirmation of the task may have a positive impact on his credit score.

[0058] Compared to a simple "feedback loop", this process uses feedback data to simultaneously drive the automatic advancement of business processes and the continuous optimization of core algorithms, enabling the system to have self-evolution capabilities.

[0059] In existing technologies, solutions are merely a "physical accumulation" of services, not a "chemical fusion." Platforms passively respond to user requests rather than proactively plan the entire production and operation process. For example, they don't automatically plan sales and revenue collection during harvest, failing to create an intelligent closed loop that improves user operational efficiency and financial security. Because existing platforms lack the ability to automatically identify the user's agricultural cycle and haven't established linkage rules between services, they can only provide discrete, passive services, unable to offer users a comprehensive "concierge-style" intelligent solution throughout the entire production cycle. This ultimately leads to poor user experience, low platform stickiness, and low service conversion rates. Furthermore, because service recommendations are not linked to users' credit and financial data, recommended financial services may not match the user's actual qualifications and needs (e.g., recommending high-amount loans to users with low credit scores), ultimately resulting in ineffective recommendations and increased financial risk.

[0060] The advantages of this application are: The agricultural cycle identification engine not only processes natural production data but also accesses and analyzes business data such as orders and contracts from the production (procurement, processing, etc.) and post-production (warehousing, sales, transactions, etc.) stages, using this data as key parameters for cycle judgment and service triggering. Simultaneously, a service-scenario-based service rule base dynamically binds these parameters to financial service terms. This breaks down the data barriers between the "production cycle" and the "operation cycle," integrating agricultural production with industrial economic activities at the technological level for the first time. Through technologies such as the Internet of Things, big data, blockchain, artificial intelligence, and cloud computing, it integrates with the entire industrial chain of planting and animal husbandry, encompassing seeds, pesticides, fertilizers, mulch film, forage, plant protection aerial spraying, harvesting, agricultural product production, processing, transportation, and transactions. This enables deep integration of production and finance, allowing data to be used as an asset for credit enhancement in lending, eliminating reliance on traditional collateral and guarantees. The platform is no longer just a production assistant but a collaborative scheduling center for the entire micro-industrial chain. For example, when the system recognizes the end of the "harvest period", it automatically triggers not only the sales channels, but also the "accounts receivable financing" service based on real orders, forming a linkage mechanism based on real-time perception and decision-making of data across the entire industry chain.

[0061] Agricultural cycle identification encompasses the entire agricultural and livestock industry chain, from pre-production to post-production. The identification engine processes pre-production big data (cultivated land area, planting structure, planting costs, etc.), production big data (agricultural product procurement, processing, etc.), and post-production big data (warehousing, logistics, transactions, market prices, etc.), achieving dynamic calibration through weighted fusion algorithms and pre-trained models. Its output cycle status directly triggers chain rules in the service linkage rule base, driving the service recommendation engine to execute precise push notifications. This multi-source data fusion and dynamic precision calibration mechanism across the entire agricultural cycle chain—including "cultivation, planting, management, harvesting, processing, storage, sales, and transportation"—surpasses the limitations of existing technologies that rely solely on standard calendars or single data sources, achieving precise, synchronous, and efficient perception of each stage of the agricultural cycle. Combined with chain rule triggering, it forms an automated "perception-decision-execution" pipeline, solving the problem of "fragmented" agricultural services.

[0062] The introduced remote sensing visual agricultural data stream is deeply coupled with traditional business data streams. For example, when visual recognition detects signs of localized pests and diseases, it not only triggers plant protection service recommendations but also links to previously sown seed batch information and pesticide purchase records, achieving integrated processing of "pest and disease tracing - precision pesticide application - insurance loss assessment." This paradigm upgrades the platform from a passive response relying on "post-event data reporting" to a proactive perception and intervention system with "sky eyes." By using visual AI to detect crop stresses that are difficult for the human eye to perceive several days in advance, and cross-validating this with data from various links in the industry chain, it enables proactive production decisions and risk management. Data shows that this application can provide disaster warnings 3-5 days in advance, reducing potential losses by more than 20%.

[0063] The credit and funding coupling module is invoked in real time during the service recommendation process. It dynamically adjusts service options through parameterized models (such as credit scoring models and cost calculation models) without interrupting the service flow. Risk control is embedded in the service flow. By real-time invocation of various data and models from the agricultural and livestock production, circulation, and consumption processes—representing "small, flexible, authentic, and comprehensive" data—a multi-party mutual trust mechanism is established across the upstream, midstream, and downstream of the agricultural and livestock industry chain. This addresses the issues of precise user needs, precise loan purposes, and precise bank lending, enabling credit funds to operate in a closed loop throughout the entire agricultural and livestock industry chain. This achieves precise risk control across the entire chain, providing "precise drip irrigation" of credit funds to the entire agricultural and livestock industry chain. Simultaneously, it eliminates the problem of "using money for trivial matters," ensuring "dedicated funds for specific purposes" and "invisible risk control," breaking through the reliance on traditional collateral and guarantees. This design avoids the rigid interruption of traditional risk control, improving user experience while ensuring the security of funds and the platform.

[0064] By solidifying chain-based services onto the blockchain through smart contracts, the service process becomes automated, transparent, and tamper-proof, significantly reducing the trust costs of multi-party collaboration. Simultaneously, the risk control system has evolved from "entity credit" to "dynamic supply chain credit," enabling precise allocation and closed-loop management of credit funds within a closed, trustworthy chain. The immediate identification of agricultural production risks and the automatic matching of financial hedging tools have pioneered a new model of deep integration between "agricultural services + insurance technology," significantly enhancing the resilience and sustainability of agricultural operations.

[0065] User feedback data is fed back into the system, where incremental learning algorithms update the agricultural cycle identification model and credit model, optimizing the behavior-cycle correlation weights and credit parameters. The system not only relies on preset rules but also utilizes artificial intelligence machine learning algorithms and continuous learning from user behavior to dynamically improve the accuracy of identification and recommendations. This breakthrough achieves the goal of precise matching of the capital chain, credit chain, and industrial chain, unlocking the value of big data across the entire industrial chain, reconstructing digital credit across the upstream, midstream, and downstream of the industrial chain, reshaping the accuracy of user profiles, and consequently adjusting the agricultural and livestock production structure.

[0066] Furthermore, a federated learning framework is introduced into the closed-loop feedback and incremental learning process. While strictly adhering to data privacy regulations, it aggregates dispersed farmer experiences and behavioral patterns to continuously optimize the platform's core AI model, forming a virtuous cycle of "becoming smarter with use and without data migration." This provides innovative technological infrastructure for the secure flow and value release of agricultural data elements. Farmers' local behavioral data participates in the optimization and training of global models (such as agricultural cycle identification models and credit models) without leaving their devices. Only model parameter updates are encrypted and uploaded for aggregation. This mechanism ensures farmer data privacy (complying with increasingly stringent data regulations) while achieving "data remaining within its domain, value circulating freely," enabling the platform to continuously evolve using dispersed collective intelligence.

[0067] Corresponding to the above-described embodiment of the intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification, this application embodiment provides an intelligent linkage device for agricultural and livestock industry chain scenarios based on agricultural cycle identification, comprising: The agricultural data acquisition module is used to acquire agricultural data; the agricultural data includes static master data, dynamic behavioral data and production / post-production business data of user terminals, visual data of crops, environmental and meteorological data, and / or market data. The agricultural cycle identification module is used to identify the agricultural cycle based on the agricultural data and through a preset behavior-cycle correlation model to obtain the current agricultural cycle status of the user. The initial service recommendation module is used to match and trigger predefined chained service rules based on the user's described agricultural cycle status, generating an initial service recommendation sequence. The chained service rules adopt a state-event-action structure, where the completion of the previous service action is a condition for triggering the next service action. The final service recommendation module is used to generate final service recommendations based on the initial service recommendation sequence using a preset parameterized model. The service recommendation module is used to proactively push the final service recommendation to the user terminal; An execution feedback module is used to obtain execution feedback data from the user terminal for the final recommendation service; and to optimize the behavior-period association model and / or the parameterized model based on the execution feedback data.

[0068] Furthermore, the behavior-period association model is configured as follows: Construct a knowledge graph of crop-region-standard agricultural calendar; Based on the knowledge graph, a baseline agricultural calendar corresponding to the user's crops and geographical location is obtained; The dynamic behavior data is matched with the preset standard operations in the baseline agricultural calendar to obtain the initial agricultural cycle state.

[0069] Furthermore, the order and / or contract terms in the business data during and / or after production are obtained, and the status of the first agricultural cycle is determined based on the order and / or contract terms. The first agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

[0070] Furthermore, the behavior-cycle association model is also configured to: determine the state of the second agricultural cycle based on the visual data; The second agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

[0071] Furthermore, the behavior-cycle correlation model is also configured to calibrate the initial agricultural cycle state based on environmental and meteorological data.

[0072] Furthermore, the step of generating the final service recommendation based on the initial service recommendation sequence using a pre-set parameterized model includes: Based on the agricultural data and the pre-set credit scoring model, the user's credit score is obtained; Based on the credit score, dynamically configure the transaction terms and / or risk control strategies in specific service options; Based on the credit score, the user's cash flow data, and the pre-set cost model, a precise financial limit matching the user's current production scale is calculated for specific financial services.

[0073] Furthermore, some or all of the rules in the chain rules are encoded into blockchain smart contracts; when the triggering conditions are met, the smart contracts are automatically executed. For chain service rules involving payment or performance, a first type of blockchain smart contract is generated; the first type of smart contract is configured to automatically execute fund locking, transfer or release operations after a predefined business event is verified. For chain-based service rules involving risks or safeguards, a second type of blockchain smart contract is generated; the second type of blockchain smart contract is configured as follows: Risk rules and thresholds are set based on the aforementioned environmental and meteorological data and / or market data; When the environmental, meteorological and / or market risks associated with the current agricultural cycle state are identified as exceeding a preset threshold, service matching is automatically triggered, and the matched insurance products or financial hedging products are associated with the final service recommendation. With authorization, trigger automatic insurance enrollment and / or automatic claims processing.

[0074] The above-mentioned intelligent linkage device for agricultural and livestock industry chain scenario services based on agricultural cycle recognition implements the steps and processes of the above-mentioned intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle recognition, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0075] Corresponding to the above-described embodiment of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification, this application embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps and processes of the above-described embodiment of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0076] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM). The memory in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0077] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0078] Corresponding to the above-described embodiment of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification, this application embodiment also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the steps and processes of the above-described embodiment of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0079] The processor is the processor in the electronic device described in the above embodiments of this application. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0080] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0082] It is understood that the embodiments of this application have been described above in conjunction with the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. As those skilled in the art will know, various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the invention. Furthermore, those skilled in the art, under the guidance or instruction of this application, can modify these features and embodiments to adapt to specific situations and materials without departing from the spirit and scope of the invention. Therefore, this invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of this invention.

Claims

1. A method for intelligent linkage of agricultural and livestock industry chain scenarios based on agricultural cycle recognition, characterized in that, include: Obtain agricultural data; The agricultural data includes static master data, dynamic behavioral data, and production / post-production business data from user terminals, visual data of crops, environmental and meteorological data, and / or market data. Based on the agricultural data, the agricultural cycle is identified through a pre-set behavior-cycle correlation model to obtain the current agricultural cycle status of the user. Based on the user's described agricultural cycle status, predefined chained service rules are matched and triggered to generate an initial service recommendation sequence. These chained service rules adopt a state-event-action structure, where the completion of a previous service action is a condition for triggering the next service action. Based on the initial service recommendation sequence, the final service recommendation is generated through a pre-set parameterized model; The final service recommendation will be proactively pushed to the user's terminal; Obtain the user terminal's execution feedback data for the final recommendation service; Optimize the behavior-cycle correlation model and / or the parameterized model based on the execution feedback data.

2. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 1, characterized in that, The behavior-period association model is configured as follows: Construct a knowledge graph of crop-region-standard agricultural calendar; Based on the knowledge graph, a baseline agricultural calendar corresponding to the user's crops and geographical location is obtained; The dynamic behavior data is matched with the preset standard operations in the baseline agricultural calendar to obtain the initial agricultural cycle state.

3. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 2, characterized in that, Obtain order and / or contract terms from business data during and / or after production, and determine the status of the first agricultural cycle based on the order and / or contract terms; The first agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

4. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 3, characterized in that, The behavior-cycle association model is also configured to: determine the state of the second agricultural cycle based on the visual data; The second agricultural cycle state is dynamically configured and weighted based on a weighted fusion algorithm to calibrate the initial agricultural cycle state.

5. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 4, characterized in that, The behavior-cycle correlation model is also configured to calibrate the initial agricultural cycle state based on environmental and meteorological data.

6. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 1, characterized in that, The process of generating final service recommendations based on the initial service recommendation sequence using a pre-defined parameterized model includes: Based on the agricultural data and the pre-set credit scoring model, the user's credit score is obtained; Based on the credit score, dynamically configure the transaction terms and / or risk control strategies in specific service options; Based on the credit score, the user's cash flow data, and the pre-set cost model, a precise financial limit matching the user's current production scale is calculated for specific financial services.

7. The intelligent linkage method for agricultural and livestock industry chain scenarios based on agricultural cycle identification as described in claim 1, characterized in that, Some or all of the rules in the chain rules are encoded into blockchain smart contracts; when the triggering conditions are met, the smart contracts are executed automatically. For chain service rules involving payment or performance, a first type of blockchain smart contract is generated; the first type of smart contract is configured to automatically execute fund locking, transfer or release operations after a predefined business event is verified. For chain-based service rules involving risks or safeguards, a second type of blockchain smart contract is generated; the second type of blockchain smart contract is configured as follows: Risk rules and thresholds are set based on the aforementioned environmental and meteorological data and / or market data; When the environmental, meteorological and / or market risks associated with the current agricultural cycle state are identified as exceeding a preset threshold, service matching is automatically triggered, and the matched insurance products or financial hedging products are associated with the final service recommendation. With authorization, trigger automatic insurance enrollment and / or automatic claims processing.

8. An intelligent linkage device for agricultural and livestock industry chain scenarios based on agricultural cycle recognition, characterized in that, include: The agricultural data acquisition module is used to acquire agricultural data; the agricultural data includes static master data, dynamic behavioral data and production / post-production business data of user terminals, visual data of crops, environmental and meteorological data, and / or market data. The agricultural cycle identification module is used to identify the agricultural cycle based on the agricultural data and through a preset behavior-cycle correlation model to obtain the current agricultural cycle status of the user. The initial service recommendation module is used to match and trigger predefined chained service rules based on the user's described agricultural cycle status, generating an initial service recommendation sequence. The chained service rules adopt a state-event-action structure, where the completion of the previous service action is a condition for triggering the next service action. The final service recommendation module is used to generate final service recommendations based on the initial service recommendation sequence using a preset parameterized model. The service recommendation module is used to proactively push the final service recommendation to the user terminal; An execution feedback module is used to obtain execution feedback data of the user terminal on the final recommendation service; Optimize the behavior-cycle correlation model and / or the parameterized model based on the execution feedback data.

9. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the intelligent linkage method for agricultural and livestock industry chain scenario services based on agricultural cycle identification as described in any one of claims 1 to 7.

Images