US-20260127206-A1 - APPLICATION GENERATION SYSTEM BASED ON INGESTED DOCUMENTS USING INTEGRATED PROGRAMMATIC AND SPECIALIZED GUIDED AND CONSTRAINED ARTIFICIAL INTELLIGENCE

Abstract

An application generation system and process using a user query and one or more documents ingested via an online document management platform is disclosed. The application generation process involves automatically ingesting documents from multiple sources, including local and cloud storage, using API bundles to create a vector database. The ingested documents are analyzed to identify patterns and contextual information, generating a priority score for the documents. Upon receiving a natural language input from the user, a prompt is generated based on the analyzed patterns to guide an AI engine. The AI engine utilizes the user query, prompts, and ingested documents to generate, test, and validate the application code in a simulated environment. The finalized application and its code are then presented to the user for execution.

Inventors

• Arthur Michel
• Benji Bizzell
• Neeraj Gupta

Assignees

• TRILOGY ENTERPRISES, INC.

Dates

Publication Date

20260507

Application Date

20251103

Claims (20)

1. 1 . A method of generating an application by utilizing a user query, and one or more ingested documents shared by the user using an online document management platform, the method comprises: executing code using one or more processors of a computer system to cause the computer system to perform operations comprising: automatically ingesting one or more documents from multiple sources via., a plurality of API bundles to generate a vector database, wherein the multiple sources include local storage or cloud storage; analyzing the vector database to identify patterns and contextual information, wherein the patterns and contextual information help in generating a priority score for the ingested documents; receiving a natural language input from the user, wherein the natural language input includes the user query to generate an application; generating a prompt based on the analyzed patterns and contextual information to guide an AI engine to create an application code, wherein the prompt is generated by populating a prompt structure that includes a prompt template along with rules, guidelines, and examples to generate the application; transferring the generated prompt to the AI engine for: generating an application code by utilizing the ingested documents, prompts, and user query; and testing the generated application code in an automated testing environment configured to simulate real-world application usage, identify and resolve any errors; and presenting the generated application to the user along with the application code used to create the application.
2. 2 . The method of claim 1 wherein the one or more ingested documents are available in multiple formats, including, PDF, text files, spreadsheets, emails, messages, JSON, and so on.
3. 3 . The method of claim 1 wherein the API bundles include a plurality of APIs packaged in a structured manner to collect the data from the local or cloud storage and help in ingestion.
4. 4 . The method of claim 1 wherein the analysis of the ingested documents further comprises: utilizing NLP techniques to identify and extract key terms, and entities, including names, places, dates, and relationships within the ingested documents; performing semantic analysis to understand the content and context of the ingested documents; and providing a metadata tag to each analyzed document based on the content, context, and semantic analysis.
5. 5 . The method of claim 1 further comprises: utilizing machine learning algorithms to convert the analyzed document's textual contents into vector embeddings that include numerical format; encoding relationships between words, entities, and sections of the documents, allowing easy retrieval of information from the documents; and chunking the embedded vector data content into smaller, coherent chunks based on semantic analysis, such as sections, paragraphs, or topics, to facilitate more granular processing and retrieval.
6. 6 . The method of claim 1 wherein the prioritization of the one or more classified documents is done based on source reliability, content importance, or freshness of the information.
7. 7 . The method of claim 1 wherein the priority score is allocated to each document during the prioritization of the one or more classified documents.
8. 8 . The method of claim 1 wherein the documents with a priority score less than 3 are ignored or not considered for application generation.
9. 9 . The method of claim 1 wherein the priority scores are utilized during information retrieval to rank documents, ensuring that higher-priority information is retrieved first in response to user queries, thereby improving the relevance of search results.
10. 10 . The method of claim 1 further comprises: i. removing the documents with a high priority score from the list of ingested documents; ii. re-ranking the left documents by utilizing LLM tools; iii. combining the re-ranked documents with the documents with high priority scores.
11. 11 . The method of claim 1 wherein the AI engine is trained to handle specific programming languages and frameworks, allowing it to generate application code in languages such as Python, Java, JavaScript, React Code, Streamlit Code, or any user-specified programming language.
12. 12 . The method of claim 1 further comprises: a feedback mechanism that updates the generated application code by iteratively analyzing the application code and user feedback to improve the prompt generation and accuracy of the AI engine based on the user feedback.
13. 13 . A system to generate an application by utilizing a user query, and one or more ingested documents shared by the user using an online document management platform comprises: one or more processors of a computer system; and a memory, coupled to the one or more processors, that stores code and execution of the code by the one or more processors causes the computer system to perform operations comprising: automatically ingesting one or more documents to a data ingestor from multiple sources via., a plurality of API bundles to generate a vector database, wherein the multiple sources include local storage or cloud storage; analyzing the vector database to identify patterns and contextual information using an analyzer, wherein the patterns and contextual information help in generating a priority score for the ingested documents; receiving a natural language input from the user via., a chatbot, wherein the natural language input includes the user query to generate an application; generating a prompt using a prompt generator based on the analyzed patterns and contextual information to guide an AI engine to create an application code, wherein the prompt is generated by populating a prompt structure that includes a prompt template along with rules, guidelines, and examples to generate the application; transferring the generated prompt to the AI engine to: generate an application code by using a code generator that utilizes the ingested documents, prompts, and user query; and test the generated application code in an automated testing environment configured to simulate real-world application usage, identify and resolve any errors using a code tester; and presenting the generated application to the user along with the application code used to create the application on the online document management platform.
14. 14 . The system of claim 13 wherein the plurality of API bundles are configured to support data ingestion from multiple sources, including, local storage, and cloud storage, ensuring that the ingested documents are up-to-date and available in real-time for vectorization.
15. 15 . The system of claim 13 wherein the API bundles support document ingestion in a plurality of formats, including, PDF, text files, spreadsheets, emails, messages, JSON, and so on.
16. 16 . The system of claim 13 wherein the chatbot is integrated within the online document management platform.
17. 17 . The system of claim 13 wherein the code generator may generate the application simply by using the user query and the generated prompts, without utilizing the ingested documents.
18. 18 . The system of claim 13 wherein the code tester provides detailed error logs and suggestions for improving the application code, which is automatically incorporated into the final version of the application code before presenting it to the user.
19. 19 . The system of claim 13 wherein the user is provided with an interactive user interface, integrated into the online document management platform, to review the generated application code and application, request modifications, or download the application code for further customization and deployment.
20. 20 . The system of claim 13 further comprises: a feedback module that updates the generated application code by iteratively analyzing the application code and user feedback to improve the prompt generation and accuracy of the AI engine based on user feedback.

Description

CROSS-REFERENCE TO RELATED APPLICATION(S) This application claims the benefit under 35 U.S.C. § 119 (e) and 37 C.F.R. § 1.78 of U.S. Provisional Application No. 63/714,907, which is incorporated by reference in its entirety. FIELD OF THE INVENTION The present invention generally relates to the field of electronics, and more specifically to an AI (Artificial Intelligence) driven system to generate an application based on ingested documents and queries provided by the user. The user can give any query to the generated application to perform the corresponding task. BACKGROUND OF THE INVENTION Companies have faced numerous challenges in integrating Artificial Intelligence (AI) into their document management systems. Over the years, several approaches have been employed, each with its own set of limitations that hinder the seamless adoption of AI technologies. The three primary methods used have been direct integration of AI models, custom-built interfaces, and third-party solutions. However, all these approaches have struggled to meet the dynamic needs of businesses, especially as AI technology evolves rapidly. The first approach, direct integration of AI Models, involves integrating AI directly into the company's systems. This approach requires users to interact with AI models through programming interfaces, such as APIs, or specialized tools designed to connect the AI models to the existing document management systems. While this method offers the most direct control over AI capabilities, it demands a deep understanding of the AI models, their parameters, and the specific data they require. Users need to have a high level of technical expertise to manage these integrations effectively, making it a less viable option for organizations without specialized AI knowledge. Configuring and managing these models can be complex and time-consuming, requiring ongoing attention to ensure they are working as expected. The second approach is the use of custom-built interfaces in correspondence to specific AI functionalities. These interfaces are designed to meet the unique needs of an organization by allowing users to interact with AI models through a user-friendly platform. While custom-built interfaces offer some level of abstraction from the complex technicalities of AI models, they are often rigid and not easily adaptable to new or evolving AI technologies. Such systems still require a certain level of technical knowledge to operate effectively, particularly when it comes to adjusting the AI models as business requirements change. Moreover, because these interfaces are designed with a specific functionality in mind, they are often limited in their ability to adapt to new tasks or incorporate additional AI capabilities. The third approach involves third-party solutions, where companies rely on external platforms to integrate AI into their document management systems. These platforms offer a level of abstraction that simplifies the use of AI, reducing the need for deep technical knowledge. However, this convenience often comes at the cost of flexibility and customization. Third-party solutions tend to operate within the confines of the vendor's vision and update cycle, meaning that companies have limited control over the AI's behavior and development. This reliance can create a significant dependency on the vendor, which becomes problematic if the vendor's updates do not align with the company's evolving needs. Moreover, the third-party platforms are usually designed to cater to a broad audience and may not offer the specific functionalities or customizations needed for a particular business. As a result, companies are forced to adjust their workflows to fit the capabilities of the software, rather than having a solution tailored to their unique operational requirements. Overall, all these approaches share several drawbacks that make them less than ideal for companies looking to leverage AI in their document management systems. One of the most significant challenges is the requirement for deep technical knowledge. Whether it's directly integrating AI models, building custom interfaces, or managing third-party solutions, all these methods demand a certain level of expertise that many organizations may not have readily available. Additionally, integration often requires extensive customization, which increases both time and cost. For many companies, the resources needed to implement and maintain these integrations can outweigh the benefits, leading to high development and maintenance costs that are unsustainable in the long term. Less flexibility in adapting to new AI technologies or adjusting to changing business requirements further compounds these issues, as the rigid nature of existing solutions makes it difficult for organizations to remain agile and responsive in a fast-evolving technological landscape. BRIEF DESCRIPTION OF THE DRAWINGS The systems and methods described herein may be better understood, and their nume