# US 2013/0159331 A1 · Systems and methods for determining related places

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

- Number: US 2013/0159331 A1
- Document ID: US20130159331A1
- Status: Published application
- Kind: A1
- Application number: 13/666,844
- Filed: 2012-11-01
- Published: 2013-06-20
- Earliest claimed: 2011-12-16
- Assignees: UrbanQ, Inc.
- Inventors: Renhui Zhang
- Web page: https://patentgrep.com/patent/US20130159331A1

## CPC

- G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor
- G06F 16/29: Geographical information databases
- G06Q 30/0261: {based on user location}
- 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

Techniques for providing location-based recommendations are described. Some embodiments provide a Location-Based Recommendation System (“LRBS”) that provides recommendations regarding physical places based on content items, such as Web pages, user reviews, directory listings, or the like, that describe or otherwise reference those places. In one embodiment, the LBRS is configured to, in response to an indication of a first place, determine one or more other places that are similar to the first place, and then provide indications of the determined places as recommendations to a user or other entity. In another embodiment, the LBRS is configured to, in response to an indication of a user, determine one or more places that may be of interest to the user, and then provide indications of the determined places as recommendations. In some embodiments, the LBRS may determine recommendations based on content vectors associated with places and/or users.

## Claims

### Claim 1

A method for determining similar places, the method comprising:
providing a location-based recommendation to a client device of a user, by electronically:
receiving an indication of a first place, the indication received from the client device;
determining a second place that is similar to the first place, based on properties of the first place and the second place that are derived from content items that describe the first place and the second place; and
providing an indication of the second place for display on the client device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the determining a second place that is similar to the first place includes: determining the second place based on a measure of similarity between a concept vector associated with the first place and a concept vector associated with the second place, the concept vectors being based on the content items that describe the first place and the second place.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
aggregating multiple content items about the first place into a single content item;
generating a term vector for the single content item; and
generating the concept vector associated with the first place by determining, for each of multiple concepts, how similar the term vector for the single content item is to a term vector associated with the concept.

### Claim 4 (depends on 1)

The method of claim 1, wherein the determining a second place that is similar to the first place includes: determining the second place based on a measure of similarity between one or more structured attributes associated with the first place and the second place, the structured attributes including one or more of name, hours of operation, category, location, description, and/or payment policy.

### Claim 5 (depends on 1)

The method of claim 1, wherein the determining a second place that is similar to the first place includes:
determining multiple places based on a measure of similarity between concept vectors associated with the first place and each of the multiple places, wherein the second place is one of the multiple places; and
ordering the multiple places based on a combination of distance between a current location of the client device of the user and locations of each of the multiple places, a measure of similarity between a concept vector associated with the first place and concept vectors associated with each of the multiple places, and a measure of similarity between structured attributes associated with the first place and structured attributes associated with the multiple places.

### Claim 6 (depends on 1)

The method of claim 1, wherein the determining a second place that is similar to the first place includes:
determining multiple places based on a measure of similarity between concept vectors associated with the first place and each of the multiple places, wherein the second place is one of the multiple places; and
ordering the multiple places based on a combination of distance between a current location of the client device of the user and locations of each of the multiple places and a measure of similarity between a concept vector associated with each of the multiple places and a user vector associated with the user.

### Claim 7 (depends on 6)

The method of claim 6, further comprising: determining a user vector for each of multiple users, each user vector based on activities of a corresponding user, the activities including searches, click-throughs, location check-ins, explicit feedback, location tracking, and/or purchase information.

### Claim 8 (depends on 6)

The method of claim 6, wherein the receiving an indication of a first place includes: adjusting entries in the user vector associated with the user in substantially real time, based on recency and/or frequency of activities performed by the user.

### Claim 9 (depends on 1)

The method of claim 1, wherein the first place and second place each operate under a corresponding brand, and wherein there exists no other place operating under the brand of the first place in a city or state in which the second place is located.

### Claim 10 (depends on 1)

The method of claim 1, wherein the providing a location-based recommendation includes: providing a location-based recommendation without reference to any social networking information associated with the user.

### Claim 11 (depends on 1)

The method of claim 1, wherein the second place is located in a different city or state than the first place.

### Claim 12 (depends on 1)

The method of claim 1, further comprising: receiving a query that specifies the first place and requests one or more places that are similar to the first place, wherein the user is located in a city that includes the first place, wherein the query further specifies a city that is remote from a current city of the user, and wherein the second place is located in the remote city.

### Claim 13 (depends on 1)

The method of claim 1, wherein the providing an indication of the second place includes: providing the indication of the second place as a cross-category recommendation, wherein the first place and the second place are in different service categories but are contextually related.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
identifying multiple places based on a corpus of content items; and
deriving properties for each of the multiple locations based on the corpus of content items.

### Claim 15 (depends on 1)

The method of claim 1, wherein the receiving an indication of a first place includes: receiving an indication of a place of business or leisure that is at least one of a restaurant, a retail establishment, a bar, a club, a venue, a cultural establishment, a recreational facility, a park, a hiking trail, a play field, and/or a location for a game.

### Claim 16 (depends on 1)

The method of claim 1, wherein the determining a second place that is similar to the first place includes: determining the second place based on content items that include online reviews, directory listings, marketing information, and/or geo-location information.

### Claim 17 (depends on 1)

The method of claim 1, wherein the providing a location-based recommendation includes:
receiving a search query that specifies the first place; and
providing an indication of the second place as part of search results determined based on the search query, the search results including multiple similar places ordered based on context vectors associated with each of the similar places.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
receiving indications of multiple places one of which is the first place, the multiple places being places that have been visited by the user and/or identified as preferred places by the user;
determining a concept vector associated with the user based on concept vectors associated with the multiple places;
determining multiple similar places based on similarity between the concept vector associated with the user and concept vectors associated with the multiple similar places; and
providing indications of the multiple similar places as personalized recommendations to the user.

### Claim 19 (depends on 18)

The method of claim 18, wherein the determining multiple similar places includes: determining the multiple places further based on a current location of the user.

### Claim 20 (depends on 18)

The method of claim 18, further comprising:
determining a feature of at least some of the multiple places that is preferred by the user; and
determining the multiple similar places further based on whether each of the multiple similar places has the determined feature.

### Claim 21 (depends on 1)

The method of claim 1, further comprising:
determining weights associated with elements of concept vectors of each of multiple places, each weight indicating a significance of a corresponding concept vector element to a determination of similarity, wherein the first place and second place are some of the multiple places; and
determining that the second place is similar to the first place based on at least some of the determined weights.

### Claim 22

A system for determining similar places, the system comprising:
a processor;
a memory; and
a module that is stored in the memory and that is configured, when executed by the processor, to:
receive an indication of a first place, the indication received from a mobile device of a user;
determine a second place that is similar to the first place, based on concept vectors associated with the first place and the second place that are derived from content items that describe the first place and the second place; and
provide an indication of the second place for display on the mobile device.

### Claim 23 (depends on 22)

The system of claim 22, wherein the memory is part of the mobile device, and the module is configured to:
transmit a request to a remote server system configured to determine similar places, the request including an indication of the first place;
receive the indication the second place from the remote server system; and
display the received indication of the second place on a display of the mobile device.

### Claim 24 (depends on 22)

The system of claim 22, wherein the memory is part of a search server, and the module is configured to:
receive a search request from the mobile device, the search request including the indication of the first place; and
transmit a search result including the indication of the second place to the mobile device.

### Claim 25

A non-transitory computer-readable medium including contents that are configured, when executed, to cause a computing system to perform a method for determining similar places, the method comprising:
providing a location-based recommendation to a client device of a user, by electronically:
receiving an indication of a first place, the indication received from the client device;
determining multiple places that is similar to the first place, based on properties of the first place and the multiple places that are derived from content items that describe the first place and the multiple places;
ordering the multiple places, based on a combination of distance between a current location of a mobile device of the user and locations of each of the multiple places, on similarity between each of the multiple places and the first place, and on similarity between each of the multiple places and the user; and
providing an indication of the ordered multiple places for display on the client device.