US 2023/0409577 A1 · AGGREGATING INFORMATION FROM DIFFERENT DATA FEED SERVICES

Abstract

Implementations are described herein for aggregating information responsive to a query from multiple different data feed services using machine learning. In various implementations, NLP may be performed on a natural language input comprising a query for information to generate a data feed-agnostic aggregator embedding (FAAE). A plurality of data feed services may be selected, each having its own data feed service action space that includes actions that are performable to access data via the data feed service. The FAAE may be processed based on domain-specific machine learning models corresponding to the selected data feed services. Each domain-specific machine learning model may translate between a respective data feed service action space and a data feed-agnostic semantic embedding space. Using these models, action(s) may be selected from the data feed service action spaces and performed to aggregate, from the plurality of data feed services, data that is responsive to the query.

Claims20

Dependent claims

A method implemented using one or more processors and comprising:

obtaining a natural language input comprising a query for information;
performing natural language processing (NLP) on the natural language input to generate a data feed-agnostic aggregator embedding;
selecting a plurality of data feed services, wherein each data feed service of the selected plurality of data feed services includes its own data feed service action space, wherein each data feed service action space comprises actions that are performable to access data communicated via the respective data feed service;
processing the feed-agnostic aggregator embedding based on a plurality of domain-specific machine learning models corresponding to the plurality of data feed services, wherein each domain-specific machine learning model is trained to translate between a respective data feed service action space and a data feed-agnostic semantic embedding space that includes the data feed-agnostic aggregator embedding;
based on the processing, selecting and performing one or more actions from each of the data feed service action spaces to aggregate, from the plurality of data feed services, data that is responsive to the query;
and
causing the aggregated responsive data to be presented as output.

4 more elements

A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions, cause the one or more processors to:

obtain a natural language input comprising a query for information;
perform natural language processing (NLP) on the natural language input to generate a data feed-agnostic aggregator embedding;
select a plurality of data feed services, wherein each data feed service of the selected plurality of data feed services includes its own data feed service action space, wherein each data feed service action space comprises actions that are performable to access data communicated via the respective data feed service;
process the feed-agnostic aggregator embedding based on a plurality of domain-specific machine learning models corresponding to the plurality of data feed services, wherein each domain-specific machine learning model is trained to translate between a respective data feed service action space and a data feed-agnostic semantic embedding space that includes the data feed-agnostic aggregator embedding;
select and perform one or more actions from each of the data feed service action spaces to aggregate, from the plurality of data feed services, data that is responsive to the query;
and
cause the aggregated responsive data to be presented as output.

4 more elements

Dependencies are inferred from the claim text.

Aggregating information from different data feed services

Life of this patent

Aggregating information from different data feed services

Life of this patent

Abstract

Claims20