Gain adjustment component for computer network routing infrastructure
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.
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 to:
receive, via a front end interface, an indication of a seed keyword;
extract from the seed keyword, via a semantic analysis engine accessing a data repository pre-populated with 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 from the seed keyword;
determine a first relevance score between a first keyword and a first selected topic, a second relevance score between the first keyword and a second selected topic, a third relevance score between a second keyword and the first selected topic, and a fourth relevance score between the second keyword and the second selected topic;
determine a first aggregated score based on the first relevance score and the second relevance score, and a second aggregated score based on the third relevance score and the fourth relevance score;
identify a threshold based on a metric corresponding to the plurality of topics;
input, responsive to the first aggregated score exceeding the threshold, the first keyword into a content selection process executed by the content selection infrastructure;
exclude, responsive to the second aggregated score less than the threshold, the second keyword from the content selection process executed by the content selection infrastructure; and
select, via the first 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 , comprising the data processing system to:
receive, via a front end interface, an indication of the plurality of topics.
3. The system of claim 1 , comprising the data processing system 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 first aggregated score.
4. The system of claim 1 , comprising the data processing system to:
combine the first relevance score with the second relevance score based on an additive technique; and
generate the first aggregated score based on the first relevance score combined with the second relevance score based on the additive technique.
5. The system of claim 1 , comprising the data processing system to:
combine the first relevance score with the second relevance score based on a multiplicative technique; and
generate the first aggregated score based on the first relevance score combined with the second relevance score based on the multiplicative technique.
6. The system of claim 1 , comprising the data processing system 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 first aggregated score based on the first weighted relevance score combined with the second weighted relevance score based on the multiplicative technique.
7. The system of claim 1 , comprising the data processing system to:
combine the first relevance score with the second relevance score based on a bucketing technique; and
generate the first aggregated score based on the first relevance score combined with the second relevance score based on the bucketing technique.
8. 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 an additive technique; and
generate the first aggregated score based on the first bucketed relevance score combined with the second bucketed relevance score based on the additive technique.
9. 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 first aggregated score based on the first bucketed relevance score combined with the second bucketed relevance score based on the multiplicative technique.
10. The system of claim 1 , comprising the data processing system to:
set the threshold based on a number of the plurality of topics.
11. 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.
12. A method of adjusting gain in content selection infrastructure, comprising:
receiving by the data processing system via a front end interface, an indication of a seed keyword;
extracting by a semantic analysis engine accessing a data repository pre-populated with a plurality of keywords and a plurality of topics, from the seed keyword, at least one topic;
receiving, by a data processing system including a gain adjustment component and a content selector component executed by at least one processor, a selection of a plurality of topics generated by a semantic analysis engine, the plurality of topics including the extracted topic;
determining, by the data processing system, a first relevance score between a first keyword and the first selected topic;
determining, by the data processing system, a second relevance score between the first keyword and the second selected topic;
determining, by the data processing system, a third relevance score between a second keyword and the first selected topic;
determining, by the data processing system, a fourth relevance score between the second keyword and the second selected topic;
determining, by the data processing system, a first aggregated score based on the first relevance score and the second relevance score;
determining, by the data processing system, a second aggregated score based on the third relevance score and the fourth 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 first aggregated score exceeding the threshold, the first keyword into a content selection process executed by the content selection infrastructure;
excluding, by the data processing system, responsive to the second aggregated score less than the threshold, the second keyword from the content selection process executed by the content selection infrastructure; and
selecting by the data processing system, via the 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.
13. The method of claim 12 , comprising:
receiving, by the data processing system via a front end interface, an indication of the plurality of topics.
14. 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 first aggregated score.
15. 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 the data processing system, the first aggregated score based on the first relevance score combined with the second relevance score based on the additive technique.
16. The method of claim 13 , comprising:
combining, by the data processing system, the first relevance score with the second relevance score based on a multiplicative technique; and
generating, by the data processing system, the first aggregated score based on the first relevance score combined with the second relevance score based on the multiplicative technique.
17. The method of claim 13 , comprising
generating, by the data processing system, a first weighted relevance score based on the first relevance score and a first weight assigned to the first selected topic;
generating, by the data processing system, a second weighted relevance score based on the second relevance score and a second weight assigned to the second selected topic;
combining, by the data processing system, the first weighted relevance score with the second weighted relevance score based on a multiplicative technique; and
generating, by the data processing system, the first aggregated score based on the first weighted relevance score combined with the second weighted relevance score based on the multiplicative technique.
18. The method of claim 13 , comprising:
combining, by the data processing system, the first relevance score with the second relevance score based on a bucketing technique; and
generating, by the data processing system, the first aggregated score based on the first relevance score combined with the second relevance score based on the bucketing technique.