# US 2025/0094503 A1 · Automatically restructuring search campaigns

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0094503 A1
- Document ID: US20250094503A1
- Status: Published application
- Kind: A1
- Application number: 18/573,376
- Filed: 2023-04-17
- Published: 2025-03-20
- Earliest claimed: 2023-01-23
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Vineet Verma
- Web page: https://patentgrep.com/patent/US20250094503A1

## CPC

- G06F 16/953: Querying, e.g. by the use of web search engines
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/2468: {Fuzzy queries}
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 16/906: Clustering; Classification
- G06F 16/955: using information identifiers, e.g. uniform resource locators [URL]
- G06Q 30/0277: {Online advertisement}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

To automatically map keywords to landing pages, a system obtaining a dataset including an initial set of groups of content items, each of the groups mapped to a respective landing page in an initial set of landing pages, and each of the content items associated with one or more keywords in an initial keyword vocabulary; generates a reduced dataset based on the obtained dataset, which includes (i) generating a reduced set of landing pages based on the initial set of landing pages using parameters of links associated with the respective landing pages, (ii) clustering the keywords to determine a set of themes associated with the dataset, and (iii) generating a reduced set of groups, including identifying overlaps in themes included in the set of themes, between the groups. The system further uses the generated data structure to map a received search term to one or more of the content items.

## Claims

### Claim 1

A method of automatically mapping keywords to landing pages, the method comprising:
obtaining, by processing hardware, a dataset including an initial set of groups of content items, each of the groups mapped to a respective landing page in an initial set of landing pages, and each of the content items associated with one or more keywords in an initial keyword vocabulary;
generating, by the processing hardware, a reduced dataset based on the obtained dataset, the generating including:
generating a reduced set of landing pages based on the initial set of landing pages using parameters of links associated with the respective landing pages,
clustering the keywords to determine a set of themes associated with the dataset, and
generating a reduced set of groups, including identifying overlaps in themes included in the set of themes, between the groups; and
using the reduced dataset to map a received search term to one or more of the content items.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the reduced set of landing pages includes determining that a first landing page and a second landing page correspond to a common resource based on one or more path parameters of the first landing page and the second landing page.

### Claim 3 (depends on 1)

The method of claim 1, wherein generating the reduced set of landing pages includes determining that a first landing page and a second landing page correspond to a common resource based on one or more query parameters of the first landing page and the second landing page.

### Claim 4 (depends on 1)

The method of claim 1, wherein clustering the keywords includes applying Word2Vec vectorization.

### Claim 5 (depends on 1)

The method of claim 1, wherein clustering the keywords includes calculating a silhouette score.

### Claim 6 (depends on 1)

The method of claim 1, wherein clustering the keywords includes applying an unsupervised clustering technique.

### Claim 7 (depends on 1)

The method of claim 1, wherein clustering the keywords includes applying TF-IDF vectorization to identify out-of-vocabulary (OOV) words.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
generating a reduced keyword vocabulary prior to the clustering of the keywords.

### Claim 9 (depends on 8)

The method of claim 8, wherein generating the reduced keyword vocabulary includes applying fuzzy matching to reduce a number of the keywords in the initial keyword vocabulary.

### Claim 10 (depends on 9)

The method of claim 9, wherein the applying of the fuzzy matching includes:
evaluating a cosine similarity between the keywords to build a priority queue.

### Claim 11 (depends on 9)

The method of claim 9, wherein the applying of the fuzzy matching includes:
constructing an N×N matrix for storing matching values.

### Claim 12 (depends on 11)

The method of claim 11, wherein the generating of the reduced keyword vocabulary includes:
constructing disconnected graphs based on the matrix, each disconnected graph including a plurality of nodes corresponding to respective similar keywords that form a keyword cluster.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
identifying a central node in each of the disconnected graph; and
reducing the keyword cluster to a keyword associated with the central node.

### Claim 14

A system comprising:
one or more processors; and
a computer-readable medium storing instructions that, when executed by the one or more processors, cause the system to:
obtain a dataset including an initial set of groups of content items, each of the groups mapped to a respective landing page in an initial set of landing pages, and each of the content items associated with one or more keywords in an initial keyword vocabulary;
generate a reduced dataset based on the obtained dataset, the generating including:
generating a reduced set of landing pages based on the initial set of landing pages using parameters of links associated with the respective landing pages,
clustering the keywords to determine a set of themes associated with the dataset, and
generating a reduced set of groups, including identifying overlaps in themes included in the set of themes, between the groups; and
use the reduced dataset to map a received search term to one or more of the content items.

### Claim 15 (depends on 14)

The system of claim 14, wherein generating the reduced set of landing pages includes determining that a first landing page and a second landing page correspond to a common resource based on one or more path parameters of the first landing page and the second landing page.

### Claim 16 (depends on 14)

The system of claim 14, wherein generating the reduced set of landing pages includes determining that a first landing page and a second landing page correspond to a common resource based on one or more query parameters of the first landing page and the second landing page.

### Claim 17 (depends on 14)

The system of claim 14, wherein clustering the keywords includes applying Word2Vec vectorization.

### Claim 18 (depends on 14)

The system of claim 14, wherein clustering the keywords includes calculating a silhouette score.

### Claim 19 (depends on 14)

The system of claim 14, wherein clustering the keywords includes applying an unsupervised clustering technique.

### Claim 20 (depends on 14)

The system of claim 14, wherein clustering the keywords includes applying TF-IDF vectorization to identify out-of-vocabulary (OOV) words.