Web Task Automation via Script Synthesis from Browsing Histories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices with limited resources face inefficiencies in processing web tasks due to the need to download entire web pages, generating unnecessary network traffic and system workloads, especially when only specific information is required.
Innovation Solution
A system that synthesizes task actions and scripts based on user requests, web browsing histories, and activity logs to extract relevant information, using a message transport system, synthesizer, and browser automation server to execute scripts and return concise responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the user downloads entire web pages to find desired information, then the user can access all content on the web page, but the network traffic and system workload increase significantly
Solution Approach 1:
The patent extracts only the necessary information from web pages using a synthesizer that processes user commands and identifies relevant content. Instead of downloading entire pages, the system extracts specific data elements (e.g., business address, operating hours) and returns only those extracted pieces of information, thereby reducing network traffic and system workload while maintaining information completeness for the user's specific query.
Solution Approach 2:
The patent segments the web page content into distinct information elements and retrieves only the relevant segments. The synthesizer breaks down the user command into specific information requirements and fetches only those segments from the web pages, rather than downloading the complete page structure, thus resolving the contradiction between information completeness and resource consumption.
2Loss of information
If the user accesses multiple web pages to find specific information, then the user can locate dispersed information, but the time required and network overhead increase
Solution Approach 1:
The patent performs preliminary action by pre-processing web pages and extracting information elements before the user actually needs them. The system analyzes web page structures in advance and pre-identifies potential information sources, so when a user query arrives, the synthesizer can quickly retrieve only the necessary pre-processed information without requiring the user to manually navigate through multiple pages, thus reducing time and network overhead.
Solution Approach 2:
The patent introduces an intermediary system (the synthesizer and browser automation server) that mediates between the user's information needs and the web pages. This intermediary automatically processes requests, identifies relevant information across multiple pages, and retrieves only the necessary data, eliminating the need for the user to manually access multiple pages and reducing overall time and network consumption.
3Loss of information
If the mobile device displays graphic contents on the web page, then the user can view comprehensive information, but the device's limited resources and network bandwidth are consumed
Solution Approach 1:
The patent extracts only the necessary text information from web pages and returns it to the user without downloading or displaying graphic contents. The synthesizer processes the user command to identify information requirements and retrieves only textual data elements, eliminating the need to load images, videos, and other graphic resources, thus preserving device resources and network bandwidth while maintaining information accessibility.
Solution Approach 2:
The patent inverts the conventional approach by not downloading the complete web page including all graphic contents, but instead extracting and returning only the necessary information elements. This inversion of the traditional web browsing model allows the mobile device to access information without consuming resources for rendering graphics, resolving the contradiction between information accessibility and resource consumption.
Data Source
AI summary
Automated processing of web tasks provides information relevant to user tasks based on past user actions and web histories. Automating the processing of tasks includes receiving a task which may be sent from a system such as a short messaging system (SMS), an email system, or a telephone system. Command information is extracted from the task. A sequence of actions is generated to accomplish the task including a combined script. The script may be based on past user actions, logs, and web browsing histories. The sequence of actions is executed to return information relevant to the task.