Method and system for building agricultural artificial intelligence agent based on zero-code configuration

Abstract

The application provides an agricultural artificial intelligence agent construction method and system based on zero code configuration, and belongs to the technical field of agricultural artificial intelligence. The method verifies by collecting user identity information, enters the editing background after verification, collects basic configuration information to configure the basic functions of the agent, collects agricultural data to build a private knowledge base, collects related information to complete the access of third-party agricultural systems, the connection of external databases, and the configuration of software and hardware control instructions, binds the execution capability to the trigger entrance, builds multi-round dialogue logic, and generates an access link or a two-dimensional code for terminal users to access after testing, debugging, and auditing. The application realizes rapid construction of agricultural agents through zero code configuration without writing code, adapts to the non-professional operation needs of agricultural users, realizes multi-system interconnection and efficient interaction, and improves the efficiency of agricultural intelligent application.

Description

Technical Field

[0001] This application relates to the field of agricultural artificial intelligence technology, and more specifically, to a method and system for constructing agricultural artificial intelligence agents based on zero-code configuration. Background Technology

[0002] In the current development of intelligent agriculture, artificial intelligence agents are increasingly being used in agricultural production and management. However, their construction largely relies on coding by professional technicians, resulting in high technical barriers and making it difficult for non-professional users in the agricultural field to independently build agents tailored to their specific needs. Existing methods for building agricultural agents suffer from complex configurations, poor flexibility, and an inability to quickly adapt to different agricultural scenarios. Furthermore, they struggle to achieve efficient interoperability with third-party agricultural systems and external databases, and lack convenient methods for establishing dialogue logic. This leads to low efficiency in agent construction and high application costs, failing to meet the actual needs of agricultural users for rapid and flexible agent construction and configuration, thus hindering the widespread adoption and application of agricultural artificial intelligence technology in grassroots agricultural settings. Summary of the Invention

[0003] This invention discloses a method and corresponding system for constructing agricultural AI agents based on zero-code configuration. The method involves: collecting user identity information to complete identity verification and allow authorized users to enter the agent editing backend; collecting basic configuration information to configure the agent's basic information, welcome message, top custom menu, and shortcut buttons; collecting agricultural-related data to build a private knowledge base; collecting third-party agricultural system interface information, external database connection information, and hardware / software control-related data to complete interface access, database connection, and control command configuration; collecting execution capability information and binding it to the corresponding trigger entry point; collecting dialogue logic configuration data to build multi-turn dialogue logic using a drag-and-drop node editor; collecting configuration completion information for testing and debugging; and generating a unique access link or QR code for end-user access after successful testing and approval. This method allows for the construction of agricultural AI agents without writing code, adapting to the needs of non-professional agricultural users, achieving interoperability across multiple systems, improving the efficiency and ease of application of agricultural AI agent construction, and ensuring the method's implementation through a corresponding system and computer-readable storage media.

[0004] This application provides a method for constructing agricultural artificial intelligence agents based on zero-code configuration, including the following steps: Collect user identity information to verify the user's identity, and allow the user to enter the intelligent agent editing backend after successful verification; Collect the basic configuration information of the intelligent agent, and configure the basic information, welcome message, top custom menu and shortcut button of the intelligent agent; Collect agricultural-related data and build the agent's private knowledge base by batch uploading documents or manual data entry. Collect interface information from third-party agricultural systems and configure interface authentication information through the API connector to access the third-party agricultural systems; Collect external database connection information and configure the connection to the external database through database queries; Collect relevant data on hardware and software control, and configure hardware and software control commands through the command executor; Collect the execution capability information of the API connector, database query and command executor, and bind it to the top custom menu, shortcut button or preset keyword trigger entry; Collect multi-turn dialogue logic configuration data, build multi-turn dialogue logic through drag-and-drop node editor, and connect user question node, knowledge base retrieval node, API call node, database query node, command execution node and response generation node; The system collects configuration completion information of the intelligent agent, performs online testing and debugging, collects the test and debugging results, submits the document for release review if the test passes, and generates a unique chat link or QR code for end users to access if the review is approved.

[0005] In the agricultural AI agent construction method based on zero-code configuration described in this application, the step of collecting user identity information to verify the user's identity, and allowing the user to enter the agent editing backend after successful verification, specifically involves: Collect user identity information, including user identity data, permission level data and identity verification credentials, and verify the legality of user identity and operation permissions through a preset verification algorithm to obtain identity verification results; Based on the identity verification result, if the verification is successful, the corresponding access permission to the intelligent agent editing backend is assigned, allowing the user to enter the intelligent agent editing backend; If the verification fails, a verification failure message will be displayed, and the user will be prohibited from accessing the intelligent agent editing backend. At the same time, a verification failure log will be recorded for administrators to view.

[0006] In the agricultural AI agent construction method based on zero-code configuration described in this application, the step of collecting the basic configuration information of the agent and configuring the agent's basic information, welcome message, top custom menu, and shortcut buttons specifically includes: Collect basic configuration data of the intelligent agent, including name, identifier, application scenario, agricultural field, welcome text data, function identifiers and display order data of the top custom menu, and trigger instructions and associated function data of the shortcut button; Enter and save the basic configuration data as described above; Configure the welcome message display rules for the intelligent agent based on the welcome message text data; Based on the menu and button data, configure the hierarchical structure of the top custom menu and the triggering method of the shortcut buttons to ensure that the operation logic of the menu and buttons meets the needs of agricultural scenarios.

[0007] In the method for constructing an agricultural AI agent based on zero-code configuration described in this application, the step of collecting agricultural-related data and building the agent's private knowledge base through batch document uploads or manual data entry specifically includes: Collect agricultural-related data, including agricultural production technology, crop pest and disease control, soil fertility management, and agricultural meteorological early warning; Based on the format and type of the agricultural data, the data is classified, deduplicated, and standardized to obtain standardized agricultural data. The agent's private knowledge base is built by batch uploading documents and importing data in batches or by manually importing data into each directory one by one, and a data index is established.

[0008] In the method for constructing agricultural AI agents based on zero-code configuration described in this application, the step of collecting interface information of third-party agricultural systems and configuring interface authentication information through an API connector to access the third-party agricultural systems specifically includes: Collect interface information from third-party agricultural systems, including interface address, interface protocol, data interaction format, and interface call permissions; Based on the interface information, configure the interface authentication parameters through the API connector. The authentication parameters include a key, a token, and an access code. Based on the authentication parameters, establish a communication connection between the intelligent agent and the third-party agricultural system, and complete interface debugging.

[0009] In the method for constructing agricultural AI agents based on zero-code configuration described in this application, the step of collecting multi-turn dialogue logic configuration data and building the multi-turn dialogue logic through a drag-and-drop node editor specifically includes: Collect data on common user questions, dialogue flow rules, and the logical relationships between nodes in agricultural scenarios; The user question node, knowledge base retrieval node, API call node, database query node, command execution node, and response generation node can be visually dragged and stitched together using a drag-and-drop node editor. Based on the association logic of each node, configure the trigger conditions and flow order between nodes to achieve automatic flow of multi-turn dialogues.

[0010] In the agricultural AI agent construction method based on zero-code configuration described in this application, the step of collecting the execution capability information of the API connector, database query, and command executor, and binding it to the top custom menu, shortcut button, or preset keyword trigger entry point, specifically includes: Collect the execution capability information of the API connector, including interface call capability, database query and filtering capability, and software and hardware control instruction execution capability of the command executor. Based on the execution capability information, each execution capability is associated and bound with the menu items, shortcut buttons, and preset keyword triggering entries of the top custom menu; Configure trigger response rules based on the binding relationship to ensure that when a user clicks the corresponding menu, button, or enters a preset keyword, the corresponding execution capability can be quickly invoked.

[0011] In the agricultural AI agent construction method based on zero-code configuration described in this application, the steps of collecting the configuration completion information of the agent, conducting online testing and debugging, collecting the test and debugging results, submitting for publication review if the test passes, and generating a unique chat link or QR code for end users to access if the review passes are as follows: Collect all configuration items of the intelligent agent to complete the status data, and start online testing and debugging after confirming that all configurations are completed; Collect functional response data, data interaction accuracy data, and anomaly feedback data during the testing and debugging process to obtain the testing and debugging results; Based on the test and debugging results, if all functions are normal and there is no abnormal feedback, submit for release review. Collect and publish review comments and results. If the review is approved, a unique chat link and QR code will be generated.

[0012] Secondly, this application provides a zero-code configuration-based agricultural artificial intelligence agent construction system, including: The identity verification module is used to collect user identity information and complete identity verification. The configuration editing module is used to collect basic configuration information and configure the basic functions related to the intelligent agent; The knowledge base building module is used to collect agricultural-related data and build a private knowledge base; The interface and database connection module is used to collect interface and database information and complete the connection configuration. The execution capability binding module is used to collect execution capability information and complete the binding. The dialogue logic orchestration module is used to collect dialogue logic configuration data and build multi-turn dialogue logic. The test review module is used to collect configuration and test data and complete testing and review. The access generation module is used to generate unique access links and QR codes for end users to access.

[0013] The system also includes a memory and a processor, wherein the memory includes a program for constructing an agricultural AI agent based on zero-code configuration, and when the program for constructing an agricultural AI agent based on zero-code configuration is executed by the processor, it implements the agricultural AI agent construction method based on zero-code configuration as described in any of the first aspects.

[0014] As can be seen from the above, this invention discloses a method and corresponding system for constructing agricultural artificial intelligence agents based on zero-code configuration. This method involves: collecting user identity information to complete identity verification and allowing authorized users to enter the agent editing backend; collecting basic configuration information to configure the agent's basic information, welcome message, top custom menu, and shortcut buttons; collecting agricultural-related data to build a private knowledge base; collecting third-party agricultural system interface information, external database connection information, and software and hardware control-related data to complete interface access, database connection, and control command configuration; collecting execution capability information and binding it to the corresponding trigger entry point; collecting dialogue logic configuration data to build multi-turn dialogue logic through a drag-and-drop node editor; collecting configuration completion information for online testing and debugging; and submitting for release review after successful testing. Upon successful review, a unique access chain is generated. Access is provided to end users via a link or QR code. This method requires no coding from professionals and adopts a zero-code visual configuration mode to meet the operational needs of non-professional users in the agricultural field. It effectively reduces the technical threshold for building agricultural intelligent agents, achieves efficient interoperability with third-party agricultural systems and external databases, and enables flexible construction of multi-turn dialogue logic through drag-and-drop node editing, greatly improving the construction efficiency and ease of application of agricultural intelligent agents. The corresponding construction system, through the coordinated cooperation of various functional modules, accurately corresponds to each implementation step of the method, and the computer-readable storage medium stores the corresponding method program, ensuring that the construction method provided by this invention can be stably and efficiently implemented. It effectively solves the problems of high construction difficulty, poor adaptability, and difficult implementation of existing agricultural intelligent agents, and helps to popularize and apply agricultural artificial intelligence technology in grassroots agricultural scenarios.

[0015] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A high-level flowchart of the method for constructing an agricultural artificial intelligence agent based on zero-code configuration, provided in the embodiments of this application.

[0018] Figure 2 A flowchart illustrating the method for constructing an agricultural artificial intelligence agent based on zero-code configuration, as provided in this application embodiment; Figure 3 This is a structural block diagram of an agricultural artificial intelligence agent construction system based on zero-code configuration, provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0021] Please refer to Figure 1 , Figure 1This is a high-level flowchart of a zero-code configuration-based agricultural AI agent construction method in some embodiments of this application. The high-level flowchart can be summarized as follows: First, user identity information is collected and verified; upon successful verification, the user enters the agent editing backend. Next, various configurations and related data are collected, sequentially completing the basic function configuration of the agent, the construction of a private knowledge base, the access to third-party agricultural systems, the connection to external databases, and the configuration of software and hardware control commands. Execution capabilities are bound to the corresponding trigger entry points, and multi-turn dialogue logic is built. Finally, configuration completion information is collected for testing and debugging; after successful testing and approval, a unique access link or QR code is generated for end-user access.

[0022] Please refer to Figure 2 , Figure 2 This is a flowchart of a method for constructing an agricultural artificial intelligence agent based on zero-code configuration, as described in some embodiments of this application.

[0023] The method for constructing an agricultural AI agent based on zero-code configuration disclosed in the first aspect of this invention is used in terminal devices, such as computers and mobile terminals. This method for constructing an agricultural AI agent based on zero-code configuration includes the following steps: S201. Collect user identity information to verify the user's identity. After successful verification, allow the user to enter the intelligent agent editing backend. S202. Collect the basic configuration information of the intelligent agent, and configure the basic information, welcome message, top custom menu and shortcut button of the intelligent agent; S203. Collect agricultural-related data and build the private knowledge base of the intelligent agent by batch uploading documents or manual input. S204. Collect interface information of third-party agricultural systems and configure interface authentication information through the API connector to access third-party agricultural systems; S205. Collect external database connection information and configure the connection to the external database through database query; S206. Collect relevant data on software and hardware control, and configure software and hardware control commands through the command executor; S207. Collect the execution capability information of the API connector, database query and command executor, and bind it to the top custom menu, shortcut button or preset keyword trigger entry; S208. Collect multi-turn dialogue logic configuration data, build multi-turn dialogue logic through drag-and-drop node editor, and connect user question node, knowledge base retrieval node, API call node, database query node, command execution node and response generation node; S209. Collect the configuration completion information of the intelligent agent, conduct online testing and debugging, collect the test and debugging results, and submit for release review if the test passes. If the review passes, generate a unique chat link or QR code for end users to access.

[0024] The process begins by collecting user identity information, including identifiers, permission levels, and verification credentials, to verify the legitimacy of the user's identity and operational permissions. Once verified, the user is allowed access to the intelligent agent editing backend. Next, basic intelligent agent configuration information, agricultural-related data, third-party agricultural system interface information, external database connection information, and hardware / software control-related data are collected. This process sequentially configures the intelligent agent's basic information, welcome message, top custom menu, and shortcut buttons. A private knowledge base is built through batch document uploads or manual data entry. Authentication information is configured to connect to the third-party agricultural system via API connectors, external database connections are configured via database queries, and hardware / software control commands are configured via command executors. The aforementioned execution capability information is then collected and bound to the corresponding trigger entry points. Simultaneously, dialogue logic configuration data is collected, and a drag-and-drop node editor is used to build multi-turn dialogue logic that connects various functional nodes. Finally, intelligent agent configuration completion information is collected for online testing and debugging. The test and debugging results are collected, and once the test is passed, the system is submitted for release review. Upon approval, a unique chat link or QR code is generated for end-user access.

[0025] According to an embodiment of the present invention, the step of collecting user identity information to verify the user's identity, and allowing the user to enter the intelligent agent editing backend after successful verification, specifically involves: Collect user identity information, including user identity data, permission level data and identity verification credentials, and verify the legality of user identity and operation permissions through a preset verification algorithm to obtain identity verification results; Based on the identity verification result, if the verification is successful, the corresponding access permission to the intelligent agent editing backend is assigned, allowing the user to enter the intelligent agent editing backend; If the verification fails, a verification failure message will be displayed, and the user will be prohibited from accessing the intelligent agent editing backend. At the same time, a verification failure log will be recorded for administrators to view.

[0026] The process involves collecting user identity information, specifically user identification data, permission level data, and identity verification credentials. After collection, the collected user identity information is processed using a preset verification algorithm, focusing on a comprehensive verification of the user's identity legitimacy and operational permissions. The verification results are then used to obtain the corresponding identity verification results. If the verification passes, the user is granted access to the intelligent agent editing backend matching their permission level, allowing them to normally enter the intelligent agent editing backend for subsequent configuration operations. If the verification fails, a clear verification failure message is sent to the user, and access to the intelligent agent editing backend is prohibited. Simultaneously, relevant logs for this verification failure are recorded, including verification time, user identification, and reason for failure, for administrators to review and investigate later, ensuring the security of access to the intelligent agent editing backend and guaranteeing the standardization and security of the entire construction process.

[0027] According to an embodiment of the present invention, the step of collecting the basic configuration information of the intelligent agent and configuring the basic information, welcome message, top custom menu, and shortcut button of the intelligent agent specifically includes: Collect basic configuration data of the intelligent agent, including name, identifier, application scenario, agricultural field, welcome text data, function identifiers and display order data of the top custom menu, and trigger instructions and associated function data of the shortcut button; Enter and save the basic configuration data as described above; Configure the welcome message display rules for the intelligent agent based on the welcome message text data; Based on the menu and button data, configure the hierarchical structure of the top custom menu and the triggering method of the shortcut buttons to ensure that the operation logic of the menu and buttons meets the needs of agricultural scenarios.

[0028] The process involves collecting basic configuration data for the intelligent agent, including core information such as the agent's name, identifier, application scenario, and agricultural field, as well as welcome message text, function identifiers and display order data for the top custom menu, and trigger commands and associated functions for shortcut buttons. After collection, the basic configuration data is fully entered and securely saved to ensure it is not lost and is traceable. Then, based on the collected welcome message text, the welcome message display rules for the intelligent agent are configured to ensure the welcome message accurately adapts to the agricultural scenario and displays correctly. Simultaneously, based on the collected menu and button data, the hierarchical structure of the top custom menu is configured, clarifying the relationships between menu items and the triggering methods for shortcut buttons. This entire process adheres to the technical logic of the zero-code configuration-based agricultural AI intelligent agent construction method, ensuring that the menu and button operation logic aligns with the needs of agricultural scenarios, providing a convenient foundation for subsequent execution capability binding and end-user operation.

[0029] According to an embodiment of the present invention, the collection of agricultural-related data, and the construction of the agent's private knowledge base through batch document uploads or manual data entry, specifically involves: Collect agricultural-related data, including agricultural production technology, crop pest and disease control, soil fertility management, and agricultural meteorological early warning; Based on the format and type of the agricultural data, the data is classified, deduplicated, and standardized to obtain standardized agricultural data. The agent's private knowledge base is built by batch uploading documents and importing data in batches or by manually importing data into each directory one by one, and a data index is established.

[0030] This process involves collecting agricultural-related data, specifically covering core data related to agricultural production technologies, crop pest and disease control, soil fertility management, and agricultural meteorological early warning, comprehensively covering all key aspects of agricultural production and management. After collection, the data is categorized, deduplicated, and standardized according to its specific format and type, eliminating redundant and invalid data, and unifying data formats and specifications to obtain standardized agricultural data, ensuring accuracy and usability. Subsequently, a private knowledge base for the intelligent agent is flexibly built using either batch document uploads or manual entry of data item by item, adapting to the data entry needs of different agricultural users. Simultaneously, corresponding data indexes are established during the knowledge base construction process to facilitate subsequent end-user queries and intelligent agent retrieval, providing solid data support for the intelligent agent to respond to agricultural-related knowledge.

[0031] According to an embodiment of the present invention, the step of collecting interface information of a third-party agricultural system and configuring interface authentication information through an API connector to access the third-party agricultural system specifically includes: Collect interface information from third-party agricultural systems, including interface address, interface protocol, data interaction format, and interface call permissions; Based on the interface information, configure the interface authentication parameters through the API connector. The authentication parameters include a key, a token, and an access code. Based on the authentication parameters, establish a communication connection between the intelligent agent and the third-party agricultural system, and complete interface debugging.

[0032] The process involves collecting interface information from third-party agricultural systems. This information includes the interface address, protocol, data interaction format, and access permissions. This information forms the core foundation for communication between the agent and the third-party agricultural system, ensuring that the collected information is comprehensive, accurate, and meets the data interaction requirements of agricultural scenarios. After collection, based on the interface information, corresponding interface authentication parameters are configured through the API connector used in the agent's configuration process. These authentication parameters include a key, token, and access permission code, ensuring the security and legitimacy of communication between the agent and the third-party agricultural system and preventing unauthorized access. Finally, based on the configured authentication parameters, a stable communication connection is established between the agent and the third-party agricultural system. Simultaneously, interface debugging is performed to identify and resolve communication anomalies and data interaction difficulties, ensuring that the agent can normally call the relevant functions of the third-party agricultural system through the API connector. This provides support for the agent to achieve multi-system data interoperability and improve its adaptability to agricultural scenarios.

[0033] According to an embodiment of the present invention, the step of collecting multi-turn dialogue logic configuration data and building multi-turn dialogue logic through a drag-and-drop node editor specifically includes: Collect data on common user questions, dialogue flow rules, and the logical relationships between nodes in agricultural scenarios; The user question node, knowledge base retrieval node, API call node, database query node, command execution node, and response generation node can be visually dragged and stitched together using a drag-and-drop node editor. Based on the association logic of each node, configure the trigger conditions and flow order between nodes to achieve automatic flow of multi-turn dialogues.

[0034] The process involves collecting multi-turn dialogue logic configuration data in agricultural scenarios. This data includes common user questions, dialogue flow rules, and the associated logic data for each functional node, comprehensively covering the daily interaction needs and dialogue flow scenarios of agricultural users. After collection, the user question nodes, knowledge base retrieval nodes, API call nodes, database query nodes, command execution nodes, and response generation nodes can be visually dragged and pasted together using the drag-and-drop node editor in the intelligent agent editing backend. No coding is required, reducing the operational threshold. Subsequently, based on the collected associated logic data of each node, the trigger conditions and flow order between each node are configured, clarifying the node response logic corresponding to different user questions or operations. This enables automatic flow of multi-turn dialogues, allowing dialogue logic to be built without professional programming skills. It accurately adapts to the operational needs of non-professional users in the agricultural field, providing logical support for smooth interaction between end users and the intelligent agent.

[0035] According to an embodiment of the present invention, the step of collecting the execution capability information of the API connector, database query, and command executor, and binding it to the top custom menu, shortcut button, or preset keyword trigger entry point, specifically includes: Collect the execution capability information of the API connector, including interface call capability, database query and filtering capability, and software and hardware control instruction execution capability of the command executor. Based on the execution capability information, each execution capability is associated and bound with the menu items, shortcut buttons, and preset keyword triggering entries of the top custom menu; Configure trigger response rules based on the binding relationship to ensure that when a user clicks the corresponding menu, button, or enters a preset keyword, the corresponding execution capability can be quickly invoked.

[0036] The process involves collecting execution capability information from the API connector, database query, and command executor. The API connector's execution capability information includes its interface calling capabilities; the database query's execution capability information includes its data query and filtering capabilities; and the command executor's execution capability information includes its software and hardware control instruction execution capabilities. This ensures that the collected execution capability information comprehensively covers the core functions of each module. After collection, based on the execution capability information, the execution capabilities of each module are associated and bound to the menu items, shortcut buttons, and preset keyword trigger entries of the top custom menu of the intelligent agent, clarifying the trigger carrier corresponding to each execution capability. Subsequently, based on the above binding relationship, corresponding trigger response rules are configured to clarify the correspondence between trigger conditions and execution capabilities. This ensures that when end users click on corresponding menu items, shortcut buttons, or enter preset keywords, they can quickly call the corresponding execution capabilities, improving the ease of operation of the intelligent agent and providing support for end users to efficiently use the intelligent agent's functions.

[0037] According to an embodiment of the present invention, the process of collecting configuration completion information of the intelligent agent, performing online testing and debugging, collecting test and debugging results, submitting for release review if the test passes, and generating a unique chat link or QR code for end users to access if the review passes, specifically involves: Collect all configuration items of the intelligent agent to complete the status data, and start online testing and debugging after confirming that all configurations are completed; Collect functional response data, data interaction accuracy data, and anomaly feedback data during the testing and debugging process to obtain the testing and debugging results; Based on the test and debugging results, if all functions are normal and there is no abnormal feedback, submit for release review. Collect and publish review comments and results. If the review is approved, a unique chat link and QR code will be generated.

[0038] The process involves collecting status data on all configuration items of the intelligent agent, comprehensively verifying the completion of all configuration stages, including basic configuration, private knowledge base construction, third-party agricultural system integration, execution capability binding, and multi-turn dialogue logic construction. Once all configuration items are confirmed to be complete and without omissions, the online testing and debugging process is initiated. During testing and debugging, functional response data, data interaction accuracy data, and anomaly feedback data are collected. The operating status of each functional module of the intelligent agent, the accuracy of data interaction, and the presence of any anomalies are comprehensively recorded. The test and debugging results are obtained by combining the collected data. Based on the test and debugging results, if it is determined that all functions of the intelligent agent are operating normally without any anomaly feedback, the test is considered passed, and the application is submitted for release review. Subsequently, the review opinions and results are collected. If the review opinions are satisfactory and the review is passed, a unique chat link and QR code are generated, allowing end users to interact with the zero-code configured agricultural AI intelligent agent by accessing the chat link or scanning the QR code, ensuring the stable and normal operation of the intelligent agent.

[0039] According to an embodiment of the present invention, it further includes: Collect agricultural policy data, industry dynamic data, and end-user demand change data. Based on these data, update and supplement the private knowledge base content, third-party system access types, and shortcut command configuration of the intelligent agent to obtain an updated intelligent agent configuration scheme.

[0040] This process involves collecting agricultural policy data, industry dynamic data, and end-user demand change data. Agricultural policy data covers relevant support policies and industry standards; industry dynamic data includes information on agricultural technological innovations and market development trends; and end-user demand change data reflects the additions and adjustments agricultural users make to the agent's functions and services during actual use, ensuring the collected data is comprehensive and relevant to agricultural scenarios. After collection, based on the various data types and the technical characteristics of the agent's private knowledge base, third-party agricultural system access, and shortcut command configuration, the private knowledge base is updated and improved, supplementing it with new agricultural policy, technology, and demand-related data. Third-party system access types are adapted and adjusted, adding new third-party agricultural system access that meets the requirements. Simultaneously, shortcut command configuration is optimized and supplemented to adapt to changes in policies, industry, and user needs, ultimately resulting in an updated agent configuration scheme that further enhances the agent's scenario adaptability and practicality.

[0041] Please refer to Figure 3 , Figure 3 This is a structural block diagram of the agricultural artificial intelligence agent construction system based on zero-code configuration provided in the embodiments of this application.

[0042] A second aspect of the present invention also discloses an agricultural artificial intelligence agent construction system based on zero-code configuration, comprising: The identity verification module 301 is used to collect user identity information and complete identity verification. The configuration editing module 302 is used to collect basic configuration information and configure the basic functions related to the intelligent agent. The knowledge base building module 303 is used to collect agricultural-related data and build a private knowledge base. The interface and database connection module 304 is used to collect interface and database information and complete the connection configuration. The execution capability binding module 305 is used to collect execution capability information and complete the binding. Dialogue logic orchestration module 306 is used to collect dialogue logic configuration data and build multi-turn dialogue logic; The test audit module 307 is used to collect configuration and test data and complete testing and auditing. Access generation module 308 is used to generate a unique access link and QR code for end users to access.

[0043] The system also includes a memory and a processor, the memory containing a program for a zero-code configured agricultural AI agent construction method, which, when executed by the processor, implements the steps of the zero-code configured agricultural AI agent construction method as described in any one of the first aspects.

[0044] This invention discloses a method and corresponding system for constructing agricultural AI agents based on zero-code configuration. The core of the construction method is to build agricultural AI agents without writing code by collecting various relevant data, completing a series of configurations, and conducting tests and audits. Specifically, this includes: collecting user identity information to complete identity verification, allowing users to enter the agent editing backend after successful verification; collecting basic configuration information to complete the configuration of basic agent information, welcome message, menu, and shortcut buttons; collecting agricultural-related data to build a private knowledge base; collecting third-party agricultural system interface information, external database connection information, and software and hardware control-related data to complete interface access, database connection, and control command configuration respectively; and collecting various execution... The system collects module capability information and binds it to the corresponding trigger entry point. Dialogue logic configuration data is collected, and multi-turn dialogue logic is built using a drag-and-drop node editor. After configuration is completed, online testing and debugging are performed. Once the test is approved, a unique access link or QR code is generated for end-user access. Simultaneously, it can collect data on agricultural policies, industry trends, and changes in user needs to update and supplement the agent's configuration. The corresponding construction system implements the above methods through the collaborative cooperation of various functional modules. Computer-readable storage media stores the corresponding method programs to ensure implementation, aligning with agricultural scenario needs and adapting to non-professional user operations. This solves the problems of high barriers to entry and poor adaptability in the construction of existing agricultural agents, improving the efficiency of intelligent agricultural applications.

[0045] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0046] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0047] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0048] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory, random access memory, magnetic disks, or optical disks.

[0049] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for constructing agricultural artificial intelligence agents based on zero-code configuration, characterized in that, Includes the following steps: Collect user identity information to verify the user's identity, and allow the user to enter the intelligent agent editing backend after successful verification; Collect the basic configuration information of the intelligent agent, and configure the basic information, welcome message, top custom menu and shortcut button of the intelligent agent; Collect agricultural-related data and build the agent's private knowledge base by batch uploading documents or manual data entry. Collect interface information from third-party agricultural systems and configure interface authentication information through the API connector to access the third-party agricultural systems; Collect external database connection information and configure the connection to the external database through database queries; Collect relevant data on hardware and software control, and configure hardware and software control commands through the command executor; Collect the execution capability information of the API connector, database query and command executor, and bind it to the top custom menu, shortcut button or preset keyword trigger entry; Collect multi-turn dialogue logic configuration data, build multi-turn dialogue logic through drag-and-drop node editor, and connect user question node, knowledge base retrieval node, API call node, database query node, command execution node and response generation node; The system collects configuration completion information of the intelligent agent, performs online testing and debugging, collects the test and debugging results, submits the application for release and review if the test passes, and generates a unique chat link or QR code for end users to access if the review is approved.

2. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process of collecting user identity information to verify the user's identity, and then allowing the user to access the intelligent agent editing backend, specifically involves: Collect user identity information, including user identity data, permission level data and identity verification credentials, and verify the legality of user identity and operation permissions through a preset verification algorithm to obtain identity verification results; Based on the identity verification result, if the verification is successful, the corresponding access permission to the intelligent agent editing backend is assigned, allowing the user to enter the intelligent agent editing backend; If the verification fails, a verification failure message will be displayed, and the user will be prohibited from accessing the intelligent agent editing backend. At the same time, a verification failure log will be recorded for administrators to view.

3. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process of collecting the basic configuration information of the intelligent agent, configuring the basic information, welcome message, top custom menu, and shortcut buttons of the intelligent agent, specifically involves: Collect basic configuration data of the intelligent agent, including name, identifier, application scenario, agricultural field, welcome message text data, function identifiers and display order data of the top custom menu, and trigger instructions and associated function data of the shortcut button; Enter and save the basic configuration data as described above; Configure the welcome message display rules for the intelligent agent based on the welcome message text data; Based on the menu and button data, configure the hierarchical structure of the top custom menu and the triggering method of the shortcut buttons to ensure that the operation logic of the menu and buttons meets the needs of agricultural scenarios.

4. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The collection of agricultural-related data involves building a private knowledge base for the intelligent agent through batch document uploads or manual data entry. Specifically: Collect agricultural-related data, including agricultural production technology, crop pest and disease control, soil fertility management, and agricultural meteorological early warning; Based on the format and type of the agricultural data, the data is classified, deduplicated, and standardized to obtain standardized agricultural data. The agent's private knowledge base is built by batch uploading documents and importing data in batches or by manually importing data into each directory one by one, and a data index is established.

5. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process of collecting interface information from third-party agricultural systems and configuring interface authentication information via an API connector to access these systems involves the following steps: Collect interface information from third-party agricultural systems, including interface address, interface protocol, data interaction format, and interface call permissions; Based on the interface information, configure the interface authentication parameters through the API connector. The authentication parameters include a key, a token, and an access code. Based on the authentication parameters, establish a communication connection between the intelligent agent and the third-party agricultural system, and complete interface debugging.

6. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process of collecting multi-turn dialogue logic configuration data and building the multi-turn dialogue logic using a drag-and-drop node editor is as follows: Collect data on common user questions, dialogue flow rules, and the logical relationships between nodes in agricultural scenarios; The user question node, knowledge base retrieval node, API call node, database query node, command execution node, and response generation node can be visually dragged and stitched together using a drag-and-drop node editor. Based on the association logic of each node, configure the trigger conditions and flow order between nodes to achieve automatic flow of multi-turn dialogues.

7. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process of collecting the execution capability information of the API connector, database query, and command executor, and binding it to the top custom menu, shortcut button, or preset keyword trigger entry point, specifically involves: Collect the execution capability information of the API connector, including interface call capability, database query and filtering capability, and software and hardware control instruction execution capability of the command executor. Based on the execution capability information, each execution capability is associated and bound with the menu items, shortcut buttons, and preset keyword triggering entries of the top custom menu; Configure trigger response rules based on the binding relationship to ensure that when a user clicks the corresponding menu, button, or enters a preset keyword, the corresponding execution capability can be quickly invoked.

8. The method for constructing an agricultural artificial intelligence agent based on zero-code configuration according to claim 1, characterized in that, The process involves collecting configuration completion information of the intelligent agent, conducting online testing and debugging, collecting test and debugging results, submitting for release review if the test passes, and generating a unique chat link or QR code for end users to access if the review is approved. Collect all configuration items of the intelligent agent to complete the status data, and start online testing and debugging after confirming that all configurations are completed; Collect functional response data, data interaction accuracy data, and anomaly feedback data during the testing and debugging process to obtain the testing and debugging results; Based on the test and debugging results, if all functions are normal and there is no abnormal feedback, submit for release review. Collect and publish review comments and results. If the review is approved, a unique chat link and QR code will be generated.

9. A zero-code configuration-based agricultural artificial intelligence agent construction system, characterized in that, include: The identity verification module is used to collect user identity information and complete identity verification. The configuration editing module is used to collect basic configuration information and configure the basic functions related to the intelligent agent; The knowledge base building module is used to collect agricultural-related data and build a private knowledge base; The interface and database connection module is used to collect interface and database information and complete the connection configuration. The execution capability binding module is used to collect execution capability information and complete the binding. The dialogue logic orchestration module is used to collect dialogue logic configuration data and build multi-turn dialogue logic. The test review module is used to collect configuration and test data and complete testing and review. The access generation module is used to generate unique access links and QR codes for end users to access.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium includes a method program for constructing an agricultural artificial intelligence agent based on zero-code configuration. When the method program is executed by a processor, it implements the steps of the method for constructing an agricultural artificial intelligence agent based on zero-code configuration as described in any one of claims 1 to 8.

Images