Bot-Invocable SDKs for Legacy Web Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational interfaces are incompatible with legacy HTML content, as they cannot consume or mimic the functionality of HTML pages, which are often accessed through traditional means like search engines and browser-displayed pages, lacking a mechanism to infer web pages from conversations and extract data retrieval or submission points.
Innovation Solution
A method that generates a data structure invocable by a conversational agent, involving obtaining a conversation thread, generating topic distributions, pre-fetching web content, parsing and filtering it to separate REST and non-REST content, extracting REST call signatures, and packaging context for invocation, allowing conversational agents to interact with legacy web content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conversational interfaces are used to access web content, then user interaction becomes more natural and intuitive, but legacy HTML content becomes inaccessible and incompatible
Solution Approach 1:
The patent introduces a bot as an intermediary component that sits between the conversational interface and legacy HTML content. The bot captures conversation threads, translates user intents into web navigation actions, and retrieves content from legacy HTML pages, thereby enabling compatibility without modifying the legacy content itself.
Solution Approach 2:
The system changes the parameter of content representation by converting legacy HTML content into structured data formats (JSON, XML) that can be consumed by conversational agents. This transformation allows the same content to be accessed through both traditional web interfaces and modern conversational interfaces.
2Adaptability or versatility
If traditional search engines and browser-displayed pages are used to access web content, then legacy HTML content remains accessible, but the interface lacks natural conversation capabilities
Solution Approach 1:
The patent segments the web access system into distinct functional components: a conversational interface for natural language input, a bot for intent translation and navigation, and a content retrieval module for fetching legacy HTML content. This segmentation allows each component to specialize in its strength while working together to provide both accessibility and usability.
3Ease of operation
If conversational agents directly interact with legacy HTML pages, then natural conversation is enabled, but the system cannot extract data retrieval or submission points from HTML
Solution Approach 1:
The system performs preliminary analysis of legacy HTML pages to identify and extract data retrieval and submission points before the conversational agent needs to use them. This pre-processing creates a structured map of interactive elements that the conversational agent can reference during natural conversations, eliminating the need for real-time HTML parsing.
Data Source
AI summary
A method, computer program product, and a system where a processor(s), obtains, via a conversational agent executing on a client, a conversation thread and generates topic distributions. The processors(s) identifies topics and pre-fetches web content, based on utilizing the topics as search keywords. The processor(s) parses the pre-fetched web content to identify, in the pre-fetched web content, a first content type and a second content type. The processor(s) filters the parsed pre-fetched web content, to separate the first content type from the second content type and extracts a signature of a REST call associated with the pre-fetched web content from the first type of content and tokenizes the second type of content to supply context for invoking the REST call. The processor(s) generates a package that includes signature and the context and injects the package into the client so it is invocable by the conversational agent, based on the context.