Back to results
US 12,730,806 B2Granted
Searchable index
AssigneeGoogle Inc.
InventorsJeremiah Harmsen, Tushar Deepak Chandra, Marcus Fontoura
Life of this patent
Estimating the term…
Abstract
Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.
Claims19
A computer-implemented method, comprising:
- before receiving a subsequent model input that is associated with at least one or more features:
- generating, using a machine learning model, data indicating a model output for a model input that is associated with the one or more features, wherein the model output is generated by the machine learning model based at least on the one or more features, and
- storing, in a record entry of a database, data that associates the model input with the data indicating the model output generated by the machine learning model;
- receiving the subsequent model input that is associated with at least one or more features;
- and
- in response to receiving the subsequent model input:
- accessing the record entry of the database to identify the model output that was previously generated by the machine learning model as relevant to the subsequent model input, and
- providing data corresponding to the model output in response to the subsequent model input.
5 more elements
A computer-implemented method, comprising:
- before receiving a subsequent request that is associated with one or more features:
- generating, using a machine learning model, data indicating a likelihood of a user associated with the one or more features selecting a particular item of content that is associated with the one or more features, wherein the data indicating the likelihood is generated by the machine learning model based at least on the one or more features, and
- storing, in a record entry of a database for an index, data that associates the particular item of content and the one or more features with the data indicating the likelihood generated by the machine learning model;
- receiving the subsequent request;
- and
- in response to receiving the subsequent request:
- accessing the record entry of the database to identify the particular item and the data indicating the likelihood that was previously generated by the machine learning model,
- selecting, using the likelihood, the particular item of content, and
- providing data identifying the particular item of content in response to the subsequent request.
6 more elements
A server computing system, comprising:
- at least one processor;
- and
- memory storing instructions that, when executed by the at least one processor, cause the server computing system to perform operations including:
- before receiving a subsequent model input that is associated with one or more features:
- generating, using a machine learning model, data indicating a model output for a model input that is associated with the one or more features, wherein the model output is generated by the machine learning model based at least on the one or more features, and
- storing, in a record entry of a database, data that associates the model input with the data indicating the model output generated by the machine learning model;
- receiving the subsequent model input that is associated with one or more features;
- and
- in response to receiving the subsequent model input:
- accessing the record entry of the database to identify the model output that was previously generated by the machine learning model as relevant to the subsequent model input, and
- providing data corresponding to the model output in response to the subsequent model input.
8 more elements
Dependencies are inferred from the claim text.