Management and optimization of search term clustering based on performance data

Patent metadata

Field	Value
Publication number	US-11928137-B2
Application number	US-202318099642-A
Country	US
Kind code	B2
Filing date	Jan 20, 2023
Priority date	Oct 29, 2020
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

A system and method to generate and manage clusters of search terms. The system and method generate a cluster including a set of search terms. A size of the cluster is compared to a cluster size threshold level to determine that the cluster comprises a valid-sized cluster. A noise rate of the cluster is compared to a noise rate threshold level to determine that the noise rate is less than the noise rate threshold level, wherein the noise rate relates to a distance of the cluster from a set of other clusters. Performance data associated with the cluster is generated based on a comparison with one or more cluster performance metric thresholds. A user interface is generated to display information associated with the cluster comprising the performance data. Input is received via the user interface comprising an adjustment of the one or more cluster performance metrics thresholds.

First claim

What is claimed is:

1. A method comprising:
generating, by a processing device, a cluster comprising a set of search terms;
comparing a size of the cluster to a cluster size threshold level to determine that the cluster comprises a valid-sized cluster;
comparing a noise rate of the cluster to a noise rate threshold level to determine that the noise rate is less than the noise rate threshold level, wherein the noise rate relates to a distance of the cluster from a set of other clusters;
collecting data associated with a plurality of search queries relating to the cluster;
generating first performance data associated with the cluster based on a comparison of the data with a search quality threshold level and a search volume threshold level, wherein the search quality threshold level relates to one of a search result rate or a click through rate associated with the cluster;
generating a user interface to display first information associated with the cluster comprising the first performance data in view of the search quality threshold level and the search volume threshold level;
receiving input via the user interface, wherein the input comprises an adjustment of the one or more of the search quality threshold level or the search volume threshold level to establish one or more adjusted threshold levels;
generating second performance data associated with the cluster based on a comparison of the data with the one or more adjusted threshold levels; and
causing an updated display, via the user interface, of the second performance data.

2. The method of claim 1 , further comprising collecting the set of search terms associated with the plurality of search queries.

3. The method of claim 1 , further comprising generating, by a neural network executed by the processing device, a set of embedding vectors, wherein each embedding vector represents a unique numerical representation of a search term of the set of search terms.

4. The method of claim 1 , wherein the search volume threshold level relates to a number of sessions relating to the cluster.

5. The method of claim 1 , wherein the search volume threshold level relates to a number of searches relating to the cluster.

6. The method of claim 1 , further comprising assigning an identifier to the cluster, wherein the identifier comprises a search term of the cluster, and wherein the search term that has one or more of a highest number of user sessions associated with the search term as compared to other search terms in the cluster, the search term has a smallest number of characters as compared to other search terms in the cluster, or the search term is included in each of the search terms of the cluster.

7. A system comprising:
a memory to store instructions; and
a processing device, operatively coupled to the memory, to execute the instructions to perform operations comprising:
generating a cluster comprising a set of search terms;
comparing a size of the cluster to a cluster size threshold level to determine that the cluster comprises a valid-sized cluster;
comparing a noise rate of the cluster to a noise rate threshold level to determine that the noise rate is less than the noise rate threshold level, wherein the noise rate relates to a distance of the cluster from a set of other clusters;
collecting data associated with a plurality of search queries relating to the cluster;
generating first performance data associated with the cluster based on a comparison of the data with a search quality threshold level and a search volume threshold level, wherein the search quality threshold level relates to one of a search result rate or a click through rate associated with the cluster;
generating a user interface to display first information associated with the cluster comprising the first performance data in view of the search quality threshold level and the search volume threshold level;
receiving input via the user interface, wherein the input comprises an adjustment of the one or more of the search quality threshold level or the search volume threshold level to establish one or more adjusted threshold levels;
generating second performance data associated with the cluster based on a comparison of the data with the one or more adjusted threshold levels; and
causing an updated display, via the user interface, of the second performance data.

8. The system of claim 7 , the operations further comprising collecting the set of search terms associated with the plurality of search queries.

9. The system of claim 7 , the operations further comprising generating, by a neural network executed by the processing device, a set of embedding vectors, wherein each embedding vector represents a unique numerical representation of a search term of the set of search terms.

10. The system of claim 7 , wherein the search volume threshold level relates to a number of sessions relating to the cluster.

11. The system of claim 7 , wherein the search volume threshold level relates to one of a number of searches relating to the cluster.

12. The system of claim 7 , the operations further comprising assigning an identifier to the cluster, wherein the identifier comprises a search term of the cluster, and wherein the search term that has one or more of a highest number of user sessions associated with the search term as compared to other search terms in the cluster, the search term has a smallest number of characters as compared to other search terms in the cluster, or the search term is included in each of the search terms of the cluster.

13. A non-transitory computer readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
generating a cluster comprising a set of search terms;
comparing a size of the cluster to a cluster size threshold level to determine that the cluster comprises a valid-sized cluster;
comparing a noise rate of the cluster to a noise rate threshold level to determine that the noise rate is less than the noise rate threshold level, wherein the noise rate relates to a distance of the cluster from a set of other clusters;
collecting data associated with a plurality of search queries relating to the cluster;
generating first performance data associated with the cluster based on a comparison of the data with a search quality threshold level and a search volume threshold level, wherein the search quality threshold level relates to one of a search result rate or a click through rate associated with the cluster;
generating a user interface to display first information associated with the cluster comprising the first performance data in view of the search quality threshold level and the search volume threshold level;
receiving input via the user interface, wherein the input comprises an adjustment of the one or more of the search quality threshold level or the search volume threshold level to establish one or more adjusted threshold levels;
generating second performance data associated with the cluster based on a comparison of the data with the one or more adjusted threshold levels; and
causing an updated display, via the user interface, of the second performance data.

14. The non-transitory computer readable storage medium of claim 13 , the operations further comprising collecting the set of search terms associated with the plurality of search queries.

15. The non-transitory computer readable storage medium of claim 13 , the operations further comprising generating, by a neural network executed by the processing device, a set of embedding vectors, wherein each embedding vector rep

Assignees

• Yext Inc

Inventors

• Misiewicz Michael
• Peralta Michael
• Shaw Maxwell

Classifications

• G06F16/358

  Browsing; Visualisation therefor · CPC title

• G06F16/906 Primary

  Clustering; Classification · CPC title

• G06F16/287 Primary

  Visualization; Browsing · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06N20/00

  Machine learning · CPC title