# US 2019/0236216 A1 · Automatic generation of variations of search criteria for use in a predictive search engine

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

- Number: US 2019/0236216 A1
- Document ID: US20190236216A1
- Status: Published application
- Kind: A1
- Application number: 15/881,483
- Filed: 2018-01-26
- Published: 2019-08-01
- Earliest claimed: 2018-01-26
- Assignees: MapQuest, Inc.
- Applicants: MapQuest, Inc.
- Inventors: Andrew BATTA; Jonathan Harahush; Chad Kearney; Carolyn Vlach
- Web page: https://patentgrep.com/patent/US20190236216A1

## CPC

- G06F 16/90328: {using search space presentation or visualization, e.g. category or range presentation and selection}
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A device can obtain location information that includes a set of location name values associated with a set of locations. The device can identify, using a natural language processing model, a set of proper noun values associated with the set of location name values. The device can generate a set of search criteria variant terms for the set of proper noun values. The set of search criteria variant terms can each include one or more characters associated with an alias of a particular proper noun value. The device can receive, from a user device, partial search criteria relating to an alias of a destination location. The device can process the partial search criteria using the set of search criteria variant terms to identify a set of candidate search terms. The device can provide the set of candidate search terms to the user device.

## Claims

### Claim 1

A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
obtain location information associated with a set of locations,
the location information including a set of location name values for the set of locations;
identify, using a natural language processing model, a set of proper noun values associated with the set of location name values;
generate a set of search criteria variant terms for the set of proper noun values,
the set of search criteria variant terms each including one or more characters associated with an alias of a particular proper noun value of the set of proper noun values;
receive, from a user device, partial search criteria relating to an alias of a destination location;
process the partial search criteria using the set of search criteria variant terms to identify a set of candidate search terms; and
provide the set of candidate search terms for display on an interface of the user device.

### Claim 2 (depends on 1)

The device of claim 1, where the one or more processors, when generating the set of search criteria variant terms, are to:
determine a particular alias for a proper noun value of the set of proper noun values, and
generate one or more search criteria variant terms, of the set of search criteria variant terms, for the particular alias for the proper noun value,
the one or more search criteria variant terms including at least one of:
one or more variations of a first name,
one or more variations of a last name,
one or more variations of a middle name or initial, or
one or more variations of a nickname that is different than the first name, the last name, and/or the middle name or initial.

### Claim 3 (depends on 1)

The device of claim 1, where the one or more processors, when generating the set of search criteria variant terms, are to:
generate, for one or more proper noun values, of the set of proper noun values, a configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the configurable template to identify a group of proper noun values that share a common type of alias, and
generate the one or more search criteria variant terms using the configurable template.

### Claim 4 (depends on 1)

The device of claim 1, where the one or more processors, when generating the set of search criteria variant terms, are to:
generate, for one or more proper noun values, of the set of proper noun values, a configurable template that includes a language-specific naming convention that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms, and
generate the one or more search criteria variant terms using the configurable template.

### Claim 5 (depends on 1)

The device of claim 1, where the one or more processors, when generating the set of search criteria variant terms, are to:
generate, for one or more proper noun values, of the set of proper noun values, a first configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the first configurable template to identify a group of proper noun values that share a common type of alias,
generate, for the one or more proper noun values, of the set of proper noun values, a second configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the second configurable template to identify a geographic area associated with the one or more proper noun values, and
generate the one or more search criteria variant terms using the first configurable template and the second configurable template.

### Claim 6 (depends on 1)

The device of claim 1, where the one or more processors, when identifying the set of proper noun values, are to:
provide, using an application programming interface (API), the location information as input to the natural language processing model,
the natural language processing model being supported by a server device,
the server device to use the natural language processing model to identify the set of proper noun values, and
the server device to provide the set of proper noun values to the device.

### Claim 7 (depends on 1)

The device of claim 1, where the one or more processors, when processing the partial search criteria, are to:
use the partial search criteria to query a data structure that stores the set of search criteria variant terms, and
receive the set of candidate search terms as a result of the query.

### Claim 8

A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
obtain location information associated with a set of locations,
the location information including a set of location name values for the set of locations;
identify, using a natural language processing model, a set of proper noun values associated with the set of location name values;
generate a set of search criteria variant terms for the set of proper noun values,
the set of search criteria variant terms each including one or more characters associated with an alias of a particular proper noun value of the set of proper noun values;
receive, from a user device, partial search criteria relating to an alias of a destination location;
process the partial search criteria using the set of search criteria variant terms to identify a set of candidate search terms; and
provide the set of candidate search terms for display on an interface of the user device.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium of claim 8, where the one or more instructions, that cause the one or more processors generate the set of search criteria variant terms, cause the one or more processors to:
determine a particular alias for a proper noun value, of the set of proper noun values, by analyzing historical search information,
the historical search information including a threshold number of searches that searched for the particular alias, and
generate one or more search criteria variant terms, of the set of search criteria variant terms, for the particular alias for the proper noun value.

### Claim 10 (depends on 8)

The non-transitory computer-readable medium of claim 8, where the one or more instructions, that cause the one or more processors to generate the set of search criteria variant terms, cause the one or more processors to:
generate, for one or more proper noun values, of the set of proper noun values, a configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
where the one or more processors generate the configurable template by analyzing historical search information to identify a group of proper noun values that share a common type of alias, and
generate the one or more search criteria variant terms using the configurable template.

### Claim 11 (depends on 8)

The non-transitory computer-readable medium of claim 8, where the one or more instructions, that cause the one or more processors to generate the set of search criteria variant terms, cause the one or more processors to:
generate, for one or more proper noun values, of the set of proper noun values, a configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the configurable template to identify a geographic area associated with the one or more proper noun values, and
generate the one or more search criteria variant terms using the configurable template.

### Claim 12 (depends on 8)

The non-transitory computer-readable medium of claim 8, where the one or more instructions, that cause the one or more processors to identify the set of proper noun values, cause the one or more processors to:
train the natural language processing model on historical location information, and
provide the location information as input to the natural language processing model to cause the natural language processing model identify the set of proper noun values,
where the natural language processing model uses a named-entity recognition (NER) technique to process the location information.

### Claim 13 (depends on 8)

The non-transitory computer-readable medium of claim 8, where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receiving feedback information associated with a set of requests for navigational directions,
the feedback information indicating which candidate search terms were selected during each request, of the set of requests for navigational directions, and
modify one or more search criteria variant terms based on the feedback information.

### Claim 14

A method, comprising:
obtaining, by a device, location information associated with a set of locations,
the location information including a set of location name values for the set of locations;
identifying, by the device and by using a natural language processing model, a set of proper noun values associated with the set of location name values;
generating, by the device, a set of search criteria variant terms for the set of proper noun values,
the set of search criteria variant terms each including one or more characters associated with an alias of a particular proper noun value of the set of proper noun values;
receiving, by the device and from a user device, partial search criteria relating to an alias of a destination location;
processing, by the device, the partial search criteria using the set of search criteria variant terms to identify a set of candidate search terms; and
providing, by the device, the set of candidate search terms for display on an interface of the user device.

### Claim 15 (depends on 14)

The method of claim 14, where generating the set of search criteria variant terms comprises:
generating one or more search criteria variant terms, of the set of search criteria variant terms, for a particular alias for a proper noun value, of the set of proper noun values,
the one or more search criteria variant terms including at least one of:
one or more variations of a first name,
one or more variations of a last name,
one or more variations of a middle name or initial, or
one or more variations of a nickname that is different than the first name, the last name, and/or the middle name or initial.

### Claim 16 (depends on 14)

The method of claim 14, where generating the set of search criteria variant terms comprises:
generating, for one or more proper noun values, of the set of proper noun values, a configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the configurable template to identify a group of proper noun values that share a common type of alias, and
generating the one or more search criteria variant terms using the configurable template.

### Claim 17 (depends on 14)

The method of claim 14, where generating the set of search criteria variant terms comprises:
generating, for one or more proper noun values, of the set of proper noun values, a configurable template that includes a language-specific naming convention that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms, and
generating the one or more search criteria variant terms using the configurable template.

### Claim 18 (depends on 14)

The method of claim 14, where generating the set of search criteria variant terms comprises:
generating, for one or more proper noun values, of the set of proper noun values, a first configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the first configurable template to identify a group of proper noun values that share a common type of alias,
generating, for the one or more proper noun values, of the set of proper noun values, a second configurable template that is to be used to generate one or more search criteria variant terms, of the set of search criteria variant terms,
the second configurable template to identify a geographic area associated with the one or more proper noun values, and
generating the one or more search criteria variant terms using the first configurable template and the second configurable template.

### Claim 19 (depends on 14)

The method of claim 14, where identifying the set of proper noun values comprises:
training the natural language processing model on historical location information, and
providing the location information as input to the natural language processing model to cause the natural language processing model identify the set of proper noun values.

### Claim 20 (depends on 14)

The method of claim 14, further comprising:
receiving feedback information associated with a set of requests for navigational directions,
the feedback information indicating which candidate search terms were selected during each request, of the set of requests for navigational directions, and
modifying one or more search criteria variant terms based on the feedback information.
