# US 2019/0171943 A1 · Automatic generation of human-understandable geospatial descriptors

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

- Number: US 2019/0171943 A1
- Document ID: US20190171943A1
- Status: Published application
- Kind: A1
- Application number: 15/829,965
- Filed: 2017-12-03
- Published: 2019-06-06
- Earliest claimed: 2017-12-03
- Assignees: Lyft, Inc.
- Applicants: Lyft, Inc.
- Inventors: YUANYUAN PAO; JAMES MURPHY; ASIF HAQUE; RAMESH SARUKKAI
- Web page: https://patentgrep.com/patent/US20190171943A1

## CPC

- G06N 5/02: Knowledge representation; Symbolic representation
- G06F 16/29: Geographical information databases
- G06F 16/338: Presentation of query results
- G06N 20/00: Machine learning
- G06Q 50/40: Business processes related to the transportation industry (shipping G06Q10/083)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

A disclosed method may include receiving geographic coordinates of a location at which two parties are to rendezvous, generating a human-understandable geospatial descriptor for the request location, and sending the descriptor to respective devices of the two parties for presentation to the two parties. Generating the human-understandable geospatial descriptor may include identifying a human-visible feature in the vicinity of the request location that is labeled within available map data, selecting, based on a descriptor generation model, a reference expression relative to the identified feature, and applying a grammar-based constructor to the label and the selected reference expression to form the human-understandable geospatial descriptor. The model may be tuned using machine learning. The two parties may include a ride requestor and a ride provider in a ridesharing service. The identified feature may be a point of interest, landmark, street name, intersection, marker, or structure.

## Claims

### Claim 1

A method comprising, by a computing system:
receiving location data including a request location;
generating a human-understandable geospatial descriptor for the request location, the generating including:
identifying a human-visible feature in the vicinity of the request location, the identified feature being associated with a label;
selecting, based on a descriptor generation model, a reference expression relative to the identified feature; and
applying a grammar-based constructor to the label associated with the identified feature and the selected reference expression to form the human-understandable geospatial descriptor; and
sending a representation of the human-understandable geospatial descriptor to a device for presentation by the device.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
obtaining, from encoded map data including a plurality of labels stored in association with location data for respective points of interest, landmarks, street names, intersections, markers, or structures:
a label for the request location; or
the label associated with the identified feature; and
sending a representation of the obtained label to the device for presentation by the device.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
creating the descriptor generation model; and
tuning the descriptor generation model based on machine learning.

### Claim 4 (depends on 3)

The method of claim 3, wherein creating the descriptor generation model comprises:
creating a data set including labels associated with location data, each label representing a point of interest, a landmark, a street name, an intersection, a marker, or a structure; and
seeding the descriptor generation model with the data set.

### Claim 5 (depends on 3)

The method of claim 3, wherein creating the descriptor generation model comprises:
creating a data set including labels associated with location data, each label representing a visible characteristic of a point of interest, a landmark, a street name, an intersection, a marker, or a structure extracted from an image including the point of interest, landmark, street name, intersection, marker, or structure; and
seeding the descriptor generation model with the data set.

### Claim 6 (depends on 3)

The method of claim 3, wherein:
the request location is where two parties are to rendezvous;
the two parties comprise a first user of an application executing on the device and a second user of the application executing on a second device, the application being configured to facilitate rendezvous between multiple parties;
creating the descriptor generation model comprises:
collecting free-form text included in communications exchanged between parties when using the application to facilitate rendezvous, the free-form text including text exchanged between the parties within short message service texts, text exchanged between the parties within multimedia messaging service texts, text exchanged between the parties within the application, or text obtained from transcripts of calls made between the parties on mobile phones;
identifying, within the free-form text, reference expressions associated with human-visible features at respective locations; and
seeding the descriptor generation model with the identified reference expressions and data usable to identify the respective locations, and
the machine learning includes determining a respective importance of each of the plurality of reference expressions in facilitating rendezvous between multiple parties.

### Claim 7 (depends on 6)

The method of claim 6, wherein the selected reference expression is derived from a reference expression identified within the free-form text and associated with a human-visible feature at a location other than the request location.

### Claim 8 (depends on 6)

The method of claim 6, wherein the identified reference expressions include a plurality of reference expressions descriptive of a relative position with respect to a point of interest, landmark, street name, intersection, marker, or structure.

### Claim 9 (depends on 6)

The method of claim 6, wherein identifying the reference expressions within the free-form text comprises applying natural language processing to the free-form text to extract expressions descriptive of points of interest, landmarks, street names, intersections, markers, or structures at a plurality of locations and to filter out expressions descriptive of variable environmental conditions, user-specific identifying information, or conversation unrelated to facilitating rendezvous between multiple parties.

### Claim 10 (depends on 1)

The method of claim 1, wherein:
the request location is where two parties are to rendezvous;
the two parties comprise a ride requestor and a ride provider who are users of a ridesharing application executing on their respective devices; and
identifying the human-visible feature in the vicinity of the request location and selecting the reference expression relative to the identified feature are dependent on a path between the ride requestor and the request location or a path between the ride provider and the request location.

### Claim 11

A system comprising: one or more processors and one or more computer-readable non-transitory storage media coupled to one or more of the processors, the one or more computer-readable non-transitory storage media comprising instructions operable when executed by one or more of the processors to cause the system to perform operations comprising:
receiving location data including a request location;
generating a human-understandable geospatial descriptor for the request location, the generating including:
identifying a human-visible feature in the vicinity of the request location, the identified feature being associated with a label;
selecting, based on a descriptor generation model, a reference expression relative to the identified feature; and
applying a grammar-based constructor to the label associated with the identified feature and the selected reference expression to form the human-understandable geospatial descriptor; and
sending a representation of the human-understandable geospatial descriptor to a device for presentation by the device.

### Claim 12 (depends on 11)

The system of claim 11, wherein the processors are further operable when executing the instructions to perform operations comprising:
creating the descriptor generation model, including:
creating a data set including labels associated with location data, each label representing:
a point of interest, a landmark, a street name, an intersection, a marker, or a structure; or
a visible characteristic of a point of interest, a landmark, a street name, an intersection, a marker, or a structure extracted from an image including the point of interest, landmark, street name, intersection, marker, or structure; and
seeding the descriptor generation model with the data set; and
tuning the descriptor generation model based on machine learning.

### Claim 13 (depends on 12)

The system of claim 12, wherein:
the request location is where two parties are to rendezvous;
the two parties comprise a first user of an application executing on the device and a second user of the application executing on a second device, the application being configured to facilitate rendezvous between multiple parties;
creating the descriptor generation model comprises:
collecting free-form text included in communications exchanged between parties when using the application to facilitate rendezvous, the free-form text including text exchanged between the parties within short message service texts, text exchanged between the parties within multimedia messaging service texts, text exchanged between the parties within the application, or text obtained from transcripts of calls made between the parties on mobile phones;
identifying, within the free-form text, reference expressions associated with human-visible features at respective locations; and
seeding the descriptor generation model with the identified reference expressions and data usable to identify the respective locations; and
the machine learning includes determining a respective importance of each of the plurality of reference expressions in facilitating rendezvous between multiple parties.

### Claim 14 (depends on 13)

The system of claim 13, wherein the selected reference expression is derived from a reference expression identified within the free-form text and associated with a human-visible feature at a location other than the request location.

### Claim 15 (depends on 13)

The system of claim 13, wherein identifying the reference expressions within the free-form text comprises applying natural language processing to the free-form text to extract expressions descriptive of points of interest, landmarks, street names, intersections, markers, or structures at a plurality of locations and to filter out expressions descriptive of variable environmental conditions, user-specific identifying information, or conversation unrelated to facilitating rendezvous between multiple parties.

### Claim 16

One or more computer-readable non-transitory storage media embodying software that is operable when executed to cause one or more processors to perform operations comprising:
receiving location data including a request location;
generating a human-understandable geospatial descriptor for the request location, the generating including:
identifying a human-visible feature in the vicinity of the request location, the identified feature being associated with a label;
selecting, based on a descriptor generation model, a reference expression relative to the identified feature; and
applying a grammar-based constructor to the label associated with the identified feature and the selected reference expression to form the human-understandable geospatial descriptor; and
sending a representation of the human-understandable geospatial descriptor to a device for presentation by the device.

### Claim 17 (depends on 16)

The media of claim 16, wherein the software is further operable when executed to cause the one or more processors to perform operations comprising:
creating the descriptor generation model, including:
creating a data set including labels associated with location data, each label representing:
a point of interest, a landmark, a street name, an intersection, a marker, or a structure; or
a visible characteristic of a point of interest, a landmark, a street name, an intersection, a marker, or a structure extracted from an image including the point of interest, landmark, street name, intersection, marker, or structure; and
seeding the descriptor generation model with the data set; and
tuning the descriptor generation model based on machine learning.

### Claim 18 (depends on 17)

The media of claim 17, wherein
the request location is where two parties are to rendezvous;
the two parties comprise a first user of an application executing on the device and a second user of the application executing on a second device, the application being configured to facilitate rendezvous between multiple parties;
creating the descriptor generation model comprises:
collecting free-form text included in communications exchanged between parties when using the application to facilitate rendezvous, the free-form text including text exchanged between the parties within short message service texts, text exchanged between the parties within multimedia messaging service texts, text exchanged between the parties within the application, or text obtained from transcripts of calls made between the parties on mobile phones;
identifying, within the free-form text, reference expressions associated with human-visible features at respective locations; and
seeding the descriptor generation model with the identified reference expressions and data usable to identify the respective locations; and
the machine learning includes determining a respective importance of each of the plurality of reference expressions in facilitating rendezvous between multiple parties.

### Claim 19 (depends on 18)

The media of claim 18, wherein the selected reference expression is derived from a reference expression identified within the free-form text and associated with a human-visible feature at a location other than the request location.

### Claim 20 (depends on 18)

The media of claim 18, wherein identifying the reference expressions within the free-form text comprises applying natural language processing to the free-form text to extract expressions descriptive of points of interest, landmarks, street names, intersections, markers, or structures at a plurality of locations and to filter out expressions descriptive of variable environmental conditions, user-specific identifying information, or conversation unrelated to facilitating rendezvous between multiple parties.
