# US 2021/0081479 A1 · System, method, and computer program product for generation of local content corpus

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

- Number: US 2021/0081479 A1
- Document ID: US20210081479A1
- Status: Published application
- Kind: A1
- Application number: 17/033,156
- Filed: 2020-09-25
- Published: 2021-03-18
- Earliest claimed: 2011-04-11
- Assignees: Groupon, Inc.
- Applicants: Groupon, Inc.
- Inventors: Roger CASTILLO; Thomas JACK
- Web page: https://patentgrep.com/patent/US20210081479A1

## CPC

- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- G06F 16/22: Indexing; Data structures therefor; Storage structures
- G06F 16/248: Presentation of query results
- G06F 16/285: {Clustering or classification}
- G06F 16/29: Geographical information databases
- G06F 16/58: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Various methods for generating a content corpus populated with content related to a particular geographic area are provided herein. One example method comprises, for each document in an initial local content corpus, applying a first set of heuristic filters to the raw content of each document, identifying at least a second term, applying a second set of heuristic filters to the raw content of each document, the second set of heuristic filters associated with the second term, iteratively performing the identification of additional terms and application of an additional set of heuristic filters associated with the additional terms until each identifiable term is extracted, determining a level on a geographic containment hierarchy indicative of a location to which each document from the set of documents is local, and for each place in a gazette, and for each document, determining a set of place in a gazette, and for each document, determining a set of points in polygons indicative of its locality.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A computer-implemented method, comprising:
for each of a plurality geographical spaces of interest, identify a set of local content, the set of location content comprised of online resources and websites identified as locally relevant;
perform content polling, utilizing a web crawler, content polling comprising crawling links from local content, and searching by keyword, and identifying new content;
add new content to a local content corpus, the local content corpus comprising a plurality of documents, each document comprised of raw content;
for each document in the local content corpus, apply a first set of heuristic filters to the raw content of each document;
identify, based on the application of the first set of heuristic filters, at least a second term;
apply a second set of heuristic filters to the raw content of each document, the second set of heuristic filters associated with the second term; and
utilize the second term in subsequent content polling as a new keyword.

### Claim 22 (depends on 21)

The computer-implemented method according to claim 21, wherein the iterative performance of the identification of additional terms and the application of the additional set of heuristic filters associated with the additional terms is configured to generate a set of local terms referencing at least people, places, and organizations.

### Claim 23 (depends on 21)

The computer-implemented method according to claim 21, further comprising:
determining a presence of geospatial information within a particular document; and
utilizing the geospatial information in conjunction with particular term frequencies to determine to eliminate the document from the initial local content corpus.

### Claim 24 (depends on 21)

The computer-implemented method according to claim 21, further comprising:
for each place in a gazette, generating an initial set of local terms, generating the initial set of local terms comprising: accessing a document, and calculating an initial weighting for at least a portion of the initial set of local terms; and
creating the initial local content corpus utilizing the initial set of local terms, the initial local content corpus containing documents that are semantically related to each other with respect to the place, the local content corpus configured for providing the system with relevant and unranked documents.

### Claim 25 (depends on 21)

The computer-implemented method according to claim 21, further comprising:
for each place in a gazette, and for each document in the set of documents, determine a set of weightings associated with the terms in the document.

### Claim 26 (depends on 21)

The computer-implemented method according to claim 21, wherein the first set of heuristics comprises at least a topological filter with respect to the place.

### Claim 27 (depends on 21)

The computer-implemented method according to claim 21, further comprising: determine a level on a place hierarchy indicative of a location to which each document from the set of documents is local.

### Claim 28

A computer program product comprising at least one non-transitory computer readable medium storing instructions translatable by one or more server machines to perform:
for each of a plurality geographical spaces of interest, identify a set of local content, the set of location content comprised of online resources and websites identified as locally relevant;
perform content polling, utilizing a web crawler, content polling comprising crawling links from local content, and searching by keyword, and identifying new content;
add new content to a local content corpus, the local content corpus comprising a plurality of documents, each document comprised of raw content;
for each document in the local content corpus, apply a first set of heuristic filters to the raw content of each document;
identify, based on the application of the first set of heuristic filters, at least a second term;
apply a second set of heuristic filters to the raw content of each document, the second set of heuristic filters associated with the second term; and
utilize the second term in subsequent content polling as a new keyword.

### Claim 29 (depends on 28)

The computer program product according to claim 28, wherein the iterative performance of the identification of additional terms and the application of the additional set of heuristic filters associated with the additional terms is configured to generate a set of local terms referencing at least people, places, and organizations.

### Claim 30 (depends on 28)

The computer program product according to claim 28, wherein the instructions are further translatable by the one or more server machines to perform:
determining a presence of geospatial information within a particular document; and
utilizing the geospatial information in conjunction with particular term frequencies to determine to eliminate the document from the initial local content corpus.

### Claim 31 (depends on 28)

The computer program product according to claim 28, wherein the instructions are further translatable by the one or more server machines to perform:
for each place in a gazette, generating the initial set of local terms, generating the initial set of local terms comprising: accessing a document, and calculating an initial weighting for at least a portion of the initial set of local terms; and
creating an initial local content corpus utilizing the initial set of local terms, the initial local content corpus containing documents that are semantically related to each other with respect to the place, the local content corpus configured for providing the system with relevant and unranked documents.

### Claim 32 (depends on 28)

The computer program product according to claim 28, wherein the instructions are further translatable by the one or more server machines to perform:
for each place in a gazette, and for each document in the set of documents, determine a set of weightings associated with the terms in the document.

### Claim 33 (depends on 28)

The computer program product according to claim 28, wherein the first set of heuristics comprises at least a topological filter with respect to the place.

### Claim 34 (depends on 28)

The computer program product according to claim 28, wherein the instructions are further translatable by the one or more server machines to perform:
determine a level on a place hierarchy indicative of a location to which each document from the set of documents is local.

### Claim 35

A system, comprising:
one or more server machines; and
at least one non-transitory computer readable medium storing instructions translatable by the one or more server machines to perform:
for each of a plurality geographical spaces of interest, identify a set of local content, the set of location content comprised of online resources and websites identified as locally relevant;
perform content polling, utilizing a web crawler, content polling comprising crawling links from local content, and searching by keyword, and identifying new content;
add new content to a local content corpus, the local content corpus comprising a plurality of documents, each document comprised of raw content;
for each document in the local content corpus, apply a first set of heuristic filters to the raw content of each document;
identify, based on the application of the first set of heuristic filters, at least a second term;
apply a second set of heuristic filters to the raw content of each document, the second set of heuristic filters associated with the second term; and
utilize the second term in subsequent content polling as a new keyword.

### Claim 36 (depends on 35)

The system according to claim 35, wherein the iterative performance of the identification of additional terms and the application of the additional set of heuristic filters associated with the additional terms is configured to generate a set of local terms referencing at least people, places, and organizations.

### Claim 37 (depends on 35)

The system according to claim 35, wherein the instructions are further translatable by the one or more server machines to perform:
determining a presence of geospatial information within a particular document; and
utilizing the geospatial information in conjunction with particular term frequencies to determine to eliminate the document from an initial local content corpus.

### Claim 38 (depends on 35)

The system according to claim 35, wherein the instructions are further translatable by the one or more server machines to perform:
for each place in a gazette, generating the initial set of local terms, generating the initial set of local terms comprising: accessing a document, and calculating an initial weighting for at least a portion of the initial set of local terms; and
creating the initial local content corpus utilizing the initial set of local terms, the initial local content corpus containing documents that are semantically related to each other with respect to the place, the local content corpus configured for providing the system with relevant and unranked documents.

### Claim 39 (depends on 35)

The system according to claim 35, wherein the instructions are further translatable by the one or more server machines to perform:
for each place in a gazette, and for each document in the set of documents, determine a set of weightings associated with the terms in the document.

### Claim 40 (depends on 35)

The system according to claim 35, wherein the first set of heuristics comprises at least a topological filter with respect to the place.
