Gain adjustment component for computer network routing infrastructure

Patent metadata

Field	Value
Publication number	US-11379540-B2
Application number	US-201916669269-A
Country	US
Kind code	B2
Filing date	Oct 30, 2019
Priority date	Feb 1, 2017
Publication date	Jul 5, 2022
Grant date	Jul 5, 2022

Abstract

Systems and methods of a gain adjustment component for content selection infrastructure are provided. The system can receive a selection of multiple topics identified by a semantic analysis technique, and identify one or more keywords. The system can determine relevance scores between each of the keywords and the multiple topics. The system can generate an aggregated relevance score for each keyword based on the relevance score for the keyword and each of the multiple topics. The system can determine a threshold based on a metric associated with the multiple topics. The system can determine to input or exclude each of the one or more keywords based on a comparison of the corresponding aggregated relevance score with the threshold.

First claim

What is claimed is:

1. A gain adjustment system for content selection infrastructure, comprising:
a data processing system including a gain adjustment component and a content selector component executed by at least one processor, the data processing system configured to:
receive, via an interface, an indication of a seed keyword;
extract, based on the seed keyword, via a semantic analysis engine accessing a data repository including a plurality of keywords and a plurality of topics, at least one topic;
receive a selection of a plurality of topics generated by the semantic analysis engine, the plurality of topics including the topic extracted based on the seed keyword;
determine a first relevance score between a candidate keyword and a first selected topic, and a second relevance score between the candidate keyword and a second selected topic;
determine a candidate aggregated score based on the first relevance score and the second relevance score;
identify a threshold based on a metric corresponding to the plurality of topics;
input, responsive to the candidate aggregated score exceeding the threshold, the candidate keyword into a content selection process executed by the content selection infrastructure; and
select, via the candidate keyword of a content selection process executed by the content selection infrastructure, in response to a request received from a client computing device, a content item to provide for display on the client computing device.

2. The system of claim 1 , wherein the data processing system is further configured to:
receive, via an interface, an indication of the plurality of topics.

3. The system of claim 1 , wherein the data processing system is further configured to:
receive, via an interface, an indication of the plurality of keywords.

4. The system of claim 1 , wherein the data processing system is further configured to:
retrieve, from a database in memory, the first relevance score and the second relevance score; and
combine the first relevance score with the second relevance score to generate the candidate aggregated score.

5. The system of claim 1 , wherein the data processing system is further to:
combine the first relevance score with the second relevance score based on an additive technique; and
generate the candidate aggregated score based on the first relevance score combined with the second relevance score based on the additive technique.

6. The system of claim 1 , wherein the data processing system is further to:
combine the first relevance score with the second relevance score based on a multiplicative technique; and
generate the candidate aggregated score based on the first relevance score combined with the second relevance score based on the multiplicative technique.

7. The system of claim 1 , wherein the data processing system is further configured to:
generate a first weighted relevance score based on the first relevance score and a first weight assigned to the first selected topic;
generate a second weighted relevance score based on the second relevance score and a second weight assigned to the second selected topic;
combine the first weighted relevance score with the second weighted relevance score based on a multiplicative technique; and
generate the candidate aggregated score based on the first weighted relevance score combined with the second weighted relevance score based on the multiplicative technique.

8. The system of claim 1 , wherein the data processing system is further configured to:
combine the first relevance score with the second relevance score based on a bucketing technique; and
generate the candidate aggregated score based on the first relevance score combined with the second relevance score based on the bucketing technique.

9. The system of claim 1 , wherein the data processing system is further configured to:
bucketize the first relevance score to generate a first bucketed relevance score;
bucketize the second relevance score to generate a second bucketed relevance score;
combine the first bucketed relevance score with the second bucketed relevance score based on an additive technique; and
generate the candidate aggregated score based on the first bucketed relevance score combined with the second bucketed relevance score based on the additive technique.

10. The system of claim 1 , comprising the data processing system to:
bucketize the first relevance score to generate a first bucketed relevance score;
bucketize the second relevance score to generate a second bucketed relevance score;
combine the first bucketed relevance score with the second bucketed relevance score based on a multiplicative technique; and
generate the candidate aggregated score based on the first bucketed relevance score combined with the second bucketed relevance score based on the multiplicative technique.

11. The system of claim 1 , comprising the data processing system to:
set the threshold based on a number of the plurality of topics.

12. The system of claim 1 , comprising the data processing system to:
set the threshold based on a weight of each of the plurality of topics.

13. A method of adjusting gain in content selection infrastructure, comprising:
receiving, by a data processing system including a gain adjustment component and a content selector component executed by at least one processor, via an interface, an indication of a seed keyword;
extracting, by a semantic analysis engine accessing a data repository including a plurality of keywords and a plurality of topics, based on the seed keyword, at least one topic;
receiving, by the data processing system, a selection of a plurality of topics generated by the semantics analysis engine, the plurality of topics including the topic extracted based on the seed keyword;
determining, by the data processing system, a first relevance score between a candidate keyword and a first selected topic, and a second relevance score between the candidate keyword and a second selected topic;
determining, by the data processing system, a candidate aggregated score based on the first relevance score and the second relevance score;
identifying, by the data processing system, a threshold based on a metric corresponding to the plurality of topics;
inputting, by the data processing system responsive to the candidate aggregated score exceeding the threshold, the candidate keyword into a content selection process executed by the content selection infrastructure; and
selecting by the data processing system, via the candidate first keyword of the content selection process executed by the content selection infrastructure, in response to a request received from a client computing device, a content item to provide for display on the client computing device.

14. The method of claim 13 , comprising:
receiving, by the data processing system via an interface, an indication of the plurality of topics.

15. The method of claim 13 , comprising
receiving, by the data processing system via an interface, an indication of the plurality of keywords.

16. The method of claim 13 , comprising:
retrieving, by the data processing system from a database in memory, the first relevance score and the second relevance score; and
combining, by the data processing system, the first relevance score with the second relevance score to generate the candidate aggregated score.

17. The method of claim 13 , comprising:
combining, by the data processing system, the first relevance score with the second relevance score based on an additive technique; and
generating, by th

Assignees

• Google Llc

Inventors

• James Gavin
• Lewis Justin

Classifications

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title

• G06F16/355 Primary

  Creation or modification of classes or clusters · CPC title

• G06F16/313

  Selection or weighting of terms for indexing · CPC title

• G06F16/35

  Clustering; Classification · CPC title

• G06F7/24

  Sorting, i.e. extracting data from one or more carriers, rearranging the data in numerical or other ordered sequence, and rerecording the sorted data on the original carrier or on a different carrier or set of carriers {sorting methods in general}(G06F7/36 takes precedence) · CPC title