Utilizing a query response to automate a task associated with a webpage
AssigneeTiny Fish Inc.
InventorsShuhao Zhang, Qi Zhai, Daniel Lawrence Schafer, Pavlo Dudka, Mingyang Li, Urvish Dipakkumar Thakker
Life of this patent
Estimating the term…
Abstract
A query and processed webpage content are received. A prompt for a large language model based on the received query and the received processed webpage content is generated. A query response is received from the large language model that is generated in response to providing the prompt to the large language model. Inference patterns are generated based on the query response. The inference patterns are stored in an inference patterns store. The query response is provided.
Claims20
A method, comprising:
- determining that the previously generated script is nonfunctional based on a change associated with at least one of one or more web elements;
- processing updated webpage content associated with a webpage to identify a plurality of updated web elements associated with the webpage;
- providing one or more variables and the updated webpage content to a machine learning model;
- receiving, from the machine learning model, an updated query response that maps the one or more variables to a subset of the plurality of updated web elements;
- and
- updating the previously generated script based on the updated query response to automate the task associated with the webpage.
A system, comprising:
- a processor configured to:
- determine that the previously generated script is nonfunctional based on a change associated with at least one of one or more web elements;
- process updated webpage content associated with a webpage to identify a plurality of updated web elements associated with the webpage;
- provide one or more variables and the updated webpage content to a machine learning model;
- receive, from the machine learning model, an updated query response that maps the one or more variables to a subset of the plurality of updated web elements;
- and
- update the previously generated script based on the updated query response to automate the task associated with the webpage;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- determining that the previously generated script is nonfunctional based on a change associated with at least one of one or more web elements;
- processing updated webpage content associated with a webpage to identify a plurality of updated web elements associated with the webpage;
- providing one or more variables and the updated webpage content to a machine learning model;
- receiving, from the machine learning model, an updated query response that maps the one or more variables to a subset of the plurality of updated web elements;
- and
- updating the previously generated script based on the updated query response to automate the task associated with the webpage.
Dependencies are inferred from the claim text.