Method, medium and device based on AI agent and low-code generation model

Abstract

The present invention is a method, medium and device for generating models based on AI agents and low-code, and relates to the field of data processing technology, including: building a target AI agent and configuring an output API interface format for the target AI agent, obtaining target demand data, inputting the target model data into a low-code platform, formatting the target model data based on the API interface format to generate candidate model fields, the low-code platform fills the generated candidate model fields into a graphical candidate model definition interface, and displays the target AI agent's related thinking process and attached reference documents and recommended questions, the target user determines the final model through the generated candidate model, it can be seen that the AI ​​agent is integrated with the low-code platform development, and interacts with the interface of the low-code platform and the AI ​​agent to realize the AI ​​agent's learning of the database and adaptation to the low-code platform, thereby improving the efficiency and accuracy of business model creation.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to methods, media and devices based on AI agents and low-code generation models. Background Art

[0002] In the digital age, the express construction of engineering management projects in the engineering industry through the integrated development environment of the low-code platform is becoming increasingly widespread. Among them, the construction of business forms is roughly divided into several modules, such as creating business models, building form lists, and configuring process services. In the process of creating business models, users need to sort out relevant business needs and be familiar with relevant engineering industry business knowledge, so as to abstract and extract corresponding attributes for business model configuration. However, the business of the engineering industry is often very complicated, and it is often difficult for developers to understand the meaning and association of the data, so as to abstract reasonable model objects. In addition, the business objects in the engineering industry need to contain more attributes. Therefore, developers usually need to spend a lot of time in the design and configuration of business models through low-code, and cannot create business models based on specific needs. At the same time, due to the complexity of the data, the obtained business model takes a long time and has low accuracy. Therefore, it is an urgent problem to propose a method for obtaining business models with high efficiency and high accuracy. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is a method based on AI agent and low-code generation model, and the method comprises the following steps:

[0004] Build a target AI agent and configure an output API interface format for the target AI agent, wherein the target AI agent includes several trained generation models, each generation model corresponding to an industry field.

[0005] Target demand data is obtained, wherein the target demand data is data input by a target user for a certain project to achieve a certain goal.

[0006] The target demand data is processed by the target AI agent to obtain target model data corresponding to the target demand data, wherein the target model data is formatted data generated by answering the target demand data after parsing and retrieval using the generative model in the target AI agent.

[0007] Input the target model data into the low-code platform, format the target model data based on the API interface format to generate candidate model fields.

[0008] The low-code platform fills the generated candidate model fields into the graphical candidate model definition interface, and displays the relevant thinking process of the target AI agent and the associated reference documents and recommended questions.

[0009] The target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model. When the candidate model field needs to be adjusted, the change is made in the candidate model definition list, and the Save button is clicked to create the candidate model.

[0010] Based on the generated candidate models, the final model is confirmed. When the generated candidate model is correct, the candidate model is determined to be the final model. When the generated candidate model does not meet the preset conditions, the target demand data is adjusted and then the process returns to execute the above-mentioned step of processing the target demand data through the target AI agent.

[0011] The present invention also provides a non-transitory computer-readable storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned method based on AI agent and low-code model generation.

[0012] The present invention also provides an electronic device, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0013] The present invention has at least the following beneficial effects: building a target AI agent and configuring an output API interface format for the target AI agent, obtaining target demand data, inputting target model data into a low-code platform, formatting the target model data based on the API interface format to generate candidate model fields, the low-code platform fills the generated candidate model fields into a graphical candidate model definition interface, and displays the target AI agent's relevant thinking process and attached reference documents and recommended questions, the target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model, and confirms the final model based on the generated candidate model. It can be seen that the AI ​​agent is integrated with the low-code platform development, breaking the boundary between AI and low-code development, and interacting with the interface of the low-code platform and the AI ​​agent to achieve AI agent learning of the database and adaptation to the low-code platform, thereby improving the efficiency and accuracy of business model creation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1A flow chart of a method for generating a model based on an AI agent and low code provided in Embodiment 1 of the present invention;

[0016] Figure 2 This is a flow chart of S100 provided in the first embodiment of the present invention;

[0017] Figure 3 This is a flowchart of S300 provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment 1,

[0021] This embodiment provides a method for generating a model based on an AI agent and a low-code, the method comprising the following steps: Figure 1 As shown:

[0022] S100, building a target AI agent and configuring an output API interface format for the target AI agent, wherein the target AI agent includes several trained generation models, each generation model corresponding to an industry field.

[0023] Specifically, in S100, the target AI agent is built through the following steps: Figure 2 As shown:

[0024] S101, obtaining an AI model, wherein the AI ​​model is a model for intelligent agent learning.

[0025] Specifically, those skilled in the art know that the selection of AI models can be carried out according to actual needs, which all fall within the protection scope of the present invention and will not be described in detail here, for example: an AI model within a company.

[0026] S102, constructing a target database, wherein the target database is a database storing learning information data obtained from an engineering industry knowledge base and provided to the intelligent agent.

[0027] Specifically, the engineering industry knowledge base includes data included in historical projects and engineering industry documents, wherein the engineering industry documents include relevant industry field specifications, relevant industry standards, relevant industry terminology explanations and relevant engineering process documents.

[0028] S103, constructing a retrieval module, wherein the retrieval module uses a retrieval algorithm to obtain relevant information from a target database.

[0029] Specifically, those skilled in the art know that the search algorithm can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here, such as BM25, TF-IDF, vector search and other search algorithms.

[0030] S104, using the generation model to perform training to construct a generation module, wherein the generation module automatically generates field attributes required for the project based on the relevant information obtained by the retrieval module.

[0031] Specifically, the field attributes include but are not limited to the field English name, field name, field type, field description, field recommended size, association relationship, index relationship, etc.

[0032] S200, obtaining target demand data, wherein the target demand data is data input by a target user for a certain project to achieve a certain goal.

[0033] Specifically, the target users are users in a certain industry field, such as water conservancy engineering, bridge construction and other industry fields.

[0034] Specifically, the input forms of the target demand data include: uploading engineering industry-related documents with semantic descriptions, uploading documents in paper or table form, inputting a field list, specifying documents in an authorized knowledge base, and textual input of requirements.

[0035] S300, processing the target demand data through the target AI agent to obtain the target model data corresponding to the target demand data, wherein the target model data is formatted data generated after answering the target demand data after parsing and retrieval using the generative model in the target AI agent.

[0036] Specifically, S300 also includes the following steps: Figure 3 As shown:

[0037] S301, performing data preprocessing on target demand data to obtain target text data, wherein the data preprocessing at least includes denoising, word segmentation and tagging.

[0038] Specifically, those skilled in the art know that any method for denoising, word segmentation and tagging data in the prior art falls within the protection scope of the present invention and will not be described in detail here.

[0039] S302, based on the target text data, obtaining target search data, wherein the target search data is data obtained by integrating data obtained by searching based on the target text data.

[0040] Specifically, step S302 also includes the following steps:

[0041] S3021: When the number of characters corresponding to the target text data exceeds a preset character number threshold, a search is performed using the TF-IDF algorithm to obtain target search data.

[0042] Specifically, those skilled in the art know that the preset character quantity threshold can be selected according to actual needs, which falls within the protection scope of the present invention and will not be described in detail here.

[0043] S3022: When the number of characters corresponding to the target text data does not exceed a preset character number threshold, a search is performed using a vector search algorithm to obtain the target search data.

[0044] S303, the target retrieval data is processed through the target generation model to obtain the target model data, wherein, when the industry field corresponding to the target demand data is consistent with the industry field corresponding to a generation model in the AI ​​agent, the generation model is determined to be the target generation model.

[0045] S400, input the target model data into the low-code platform, format the target model data based on the API interface format to generate candidate model fields.

[0046] Specifically, the candidate model is a business model of the project corresponding to the target demand data.

[0047] S500, the low-code platform fills the generated candidate model fields into the graphical candidate model definition interface, and displays the relevant thinking process of the target AI agent and the attached reference documents and recommended questions.

[0048] S600, the target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model, wherein when the candidate model field needs to be adjusted, the change is made in the candidate model definition list, and the save button is clicked to create the candidate model.

[0049] S700, based on the generated candidate models, confirm the final model, wherein, when the generated candidate model is correct, determine the candidate model as the final model, when the generated candidate model does not meet the preset conditions, adjust the target demand data and return to execute the above-mentioned step of processing the target demand data through the target AI agent.

[0050] Specifically, the preset condition is the target user's requirement for the project.

[0051] From the above content, we can see that the integration of AI agents and low-code platform development has broken the boundaries between AI and low-code development. Through the interaction between the low-code platform and the AI ​​agent's interface, the AI ​​agent can learn the database and adapt to the low-code platform, thereby improving the efficiency and accuracy of business model creation.

[0052] This embodiment can build a target AI agent and configure the output API interface format for the target AI agent, obtain target demand data, input the target model data into the low-code platform, and format the target model data based on the API interface format to generate candidate model fields. The low-code platform fills the generated candidate model fields into the graphical candidate model definition interface, and displays the relevant thinking process of the target AI agent and the attached reference documents and recommended questions. The target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model, and confirms the final model based on the generated candidate model. It can be seen that the AI ​​agent is integrated with the low-code platform development, breaking the boundary between AI and low-code development, and interacting with the interface of the low-code platform and the AI ​​agent to achieve AI agent learning of the database and adaptation to the low-code platform, thereby improving the efficiency and accuracy of business model creation.

[0053] Embodiment 2:

[0054] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the steps:

[0055] Build a target AI agent and configure an output API interface format for the target AI agent, wherein the target AI agent includes several trained generation models, each generation model corresponding to an industry field.

[0056] Target demand data is obtained, wherein the target demand data is data input by a target user for a certain project to achieve a certain goal.

[0057] The target demand data is processed by the target AI agent to obtain target model data corresponding to the target demand data, wherein the target model data is formatted data generated by answering the target demand data after parsing and retrieval using the generative model in the target AI agent.

[0058] Input the target model data into the low-code platform, format the target model data based on the API interface format to generate candidate model fields.

[0059] The low-code platform fills the generated candidate model fields into the graphical candidate model definition interface, and displays the relevant thinking process of the target AI agent and the associated reference documents and recommended questions.

[0060] The target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model. When the candidate model field needs to be adjusted, the change is made in the candidate model definition list, and the Save button is clicked to create the candidate model.

[0061] Based on the generated candidate models, the final model is confirmed. When the generated candidate model is correct, the candidate model is determined to be the final model. When the generated candidate model does not meet the preset conditions, the target demand data is adjusted and then the process returns to execute the above-mentioned step of processing the target demand data through the target AI agent.

[0062] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0063] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0064] Embodiment 3,

[0065] An embodiment of the present invention provides an electronic device, which includes a processor and the non-transitory computer-readable storage medium in the second embodiment of the present invention.

[0066] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technician familiar with this profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method based on AI agent and low-code model generation, characterized in that: The method comprises the following steps: Build a target AI agent and configure an output API interface format for the target AI agent, wherein the target AI agent includes several trained generation models, each generation model corresponds to an industry field; Acquire target demand data, wherein the target demand data is data input by a target user to achieve a certain goal of a certain project; The target demand data is processed by the target AI agent to obtain target model data corresponding to the target demand data, wherein the target model data is formatted data generated by answering the target demand data after parsing and retrieving using the generative model in the target AI agent; Input the target model data into the low-code platform, format the target model data based on the API interface format to generate candidate model fields; The low-code platform fills the generated candidate model fields into the graphical candidate model definition interface and displays the relevant thinking process of the target AI agent and the attached reference documents and recommended questions; The target user confirms the filled candidate model definition through the graphical candidate model definition interface to determine the candidate model. When the candidate model field needs to be adjusted, the change is made in the candidate model definition list, and the save button is clicked to create the candidate model. Based on the generated candidate models, the final model is confirmed. When the generated candidate model is correct, the candidate model is determined to be the final model. When the generated candidate model does not meet the preset conditions, the target demand data is adjusted and then the process returns to execute the above-mentioned step of processing the target demand data through the target AI agent.

2. The method for generating a model based on an AI agent and low code according to claim 1, characterized in that: The construction of the target AI agent includes the following steps: Acquire an AI model, wherein the AI ​​model is a model for agent learning; Constructing a target database, wherein the target database is a database storing learning information data obtained from an engineering industry knowledge base for providing learning information to the intelligent agent; Constructing a retrieval module, wherein the retrieval module uses a retrieval algorithm to obtain relevant information from a target database; The generation model is used for training to construct a generation module, wherein the generation module automatically generates field attributes required for the project based on the relevant information obtained by the retrieval module.

3. The method for generating a model based on an AI agent and low code according to claim 2, characterized in that: The engineering industry knowledge base includes data included in historical projects and engineering industry documents, wherein the engineering industry documents include relevant industry field specifications, relevant industry standards, relevant industry terminology explanations and relevant engineering process documents.

4. The method for generating a model based on an AI agent and low code according to claim 1, characterized in that: The target AI agent processes the target demand data to obtain the target model data corresponding to the target demand data, including the following steps: Performing data preprocessing on the target demand data to obtain target text data, wherein the data preprocessing at least includes denoising, word segmentation and tagging; Based on the target text data, target search data is obtained, wherein the target search data is data obtained by integrating the data obtained by searching based on the target text data; The target retrieval data is processed through the target generation model to obtain the target model data, wherein, when the industry field corresponding to the target demand data is consistent with the industry field corresponding to a generation model in the AI ​​agent, this generation model is determined to be the target generation model.

5. The method for generating a model based on an AI agent and low code according to claim 4, characterized in that: The candidate model is a business model of the project corresponding to the target demand data.

6. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for generating a model based on an AI agent and a low-code program as described in any one of claims 1-5.

7. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 6.

Images