# US 2019/0095807 A1 · Image-based popularity prediction

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

- Number: US 2019/0095807 A1
- Document ID: US20190095807A1
- Status: Published application
- Kind: A1
- Application number: 16/200,881
- Filed: 2018-11-27
- Published: 2019-03-28
- Earliest claimed: 2011-05-24
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Anjan Goswami; Sung Hwan Chung
- Web page: https://patentgrep.com/patent/US20190095807A1

## CPC

- G06F 16/583: using metadata automatically derived from the content
- G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor
- G06F 16/24: Querying
- G06F 16/242: Query formulation
- G06F 16/24578: {using ranking}
- G06F 16/2462: {Approximate or statistical queries}
- G06F 16/2465: {Query processing support for facilitating data mining operations in structured databases}
- G06F 16/2471: {Distributed queries}
- G06F 16/248: Presentation of query results
- G06F 16/332: Query formulation
- G06F 16/338: Presentation of query results
- G06F 16/345: {Summarisation for human users}
- G06F 16/5838: {using colour}
- G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information}
- G06F 16/587: using geographical or spatial information, e.g. location
- G06F 16/951: Indexing; Web crawling techniques
- G06F 17/00: Digital computing or data processing equipment or methods, specially adapted for specific functions (information retrieval, database structures or file system structures therefor G06F16/00)
- G06F 18/2115: by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06N 5/048: Fuzzy inferencing
- G06N 20/00: Machine learning
- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G06V 10/10: Image acquisition (document image scanning and transmission H04N1/00; control of digital cameras H04N23/60)
- G06V 10/40: Extraction of image or video features
- G06V 10/507: {Summing image-intensity values; Histogram projection analysis}
- G06V 10/75: Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V 10/771: Feature selection, e.g. selecting representative features from a multi-dimensional feature space
- G06V 20/695: {Preprocessing, e.g. image segmentation}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A machine may be configured to access an image of an item described by a description of the item. The machine may determine an image quality score of the image based on an analysis of the image. A request for search results that pertain to the description may be received by the machine, and the machine may present a search result that references the item's image, based on its image quality score. Also, the machine may access images of items and descriptions of items and generate a set of most frequent text tokens included in the item descriptions. The machine may identify an image feature exhibited by an item's image and determine that a text token from the corresponding item description matches one of the most frequent text tokens. A data structure may be generated by the machine to correlate the identified image feature with the text token.

## Claims

### Claim 1

A system comprising:
one or more processors;
memory; and
one or more programs stored in the memory, the one or more programs comprising instructions that cause the one or more processors to perform operations comprising:
receiving a search query that includes a text token from a client system;
identifying a plurality of results based on the search query, the plurality of search results including a first search result that comprises an item image that comprises an image feature;
accessing a visual repository that includes a mapping of the text token to a vector of the image feature; and
ranking the first search result among the plurality of search results based on the vector of the image feature.

### Claim 2 (depends on 1)

The system of claim 1, wherein the instructions cause the system to perform operations further comprising:
storing historical click data for the first search result, the historical click data indicating a number of requests to access the first search result; and
wherein the ranking the first search result among the plurality of search results is based on the vector of the image feature and the historical click data.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions cause the system to perform operations further comprising:
segmenting the item image into a foreground and a background; and
identifying the image feature in the foreground of the item image in response to the segmenting the item image.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions cause the system to perform operations further comprising:
causing display of a presentation of the plurality of search results at the client system, the presentation of the plurality of search results comprising a display of the first search result that includes the item image at a position among the plurality of search results, the position based on the ranking.

### Claim 5 (depends on 1)

The system of claim 1, wherein the plurality of results comprise listing titles that include the text token of the search query.

### Claim 6 (depends on 1)

The system of claim 1, wherein the instructions cause the system to perform operations further comprising:
receiving a plurality of annotated images, the annotated images comprising a set of image features and text tokens that correspond to each of the image features of the annotated image; and
mapping the set of image features to the text tokens within the visual repository.

### Claim 7 (depends on 6)

The system of claim 6, wherein the receiving the plurality of annotated images includes:
receiving a plurality of item listings, the plurality of item listings comprising item images and item titles, the item titles including the text tokens; and
mapping the text tokens from the item titles to the item images of the item listings.

### Claim 8

A method comprising:
receiving a search query that includes a text token from a client system;
identifying a plurality of results based on the search query, the plurality of search results including a first search result that comprises an item image that comprises an image feature;
accessing a visual repository that includes a mapping of the text token to a vector of the image feature; and
ranking the first search result among the plurality of search results based on the vector of the image feature.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
storing historical click data for the first search result, the historical click data indicating a number of requests to access the first search result; and
wherein the ranking the first search result among the plurality of search results is based on the vector of the image feature and the historical click data.

### Claim 10 (depends on 8)

The method of claim 8, further comprising:
segmenting the item image into a foreground and a background; and
identifying the image feature in the foreground of the item image in response to the segmenting the item image.

### Claim 11 (depends on 8)

The method of claim 8, further comprising:
causing display of a presentation of the plurality of search results at the client system, the presentation of the plurality of search results comprising a display of the first search result that includes the item image at a position among the plurality of search results, the position based on the ranking.

### Claim 12 (depends on 8)

The method of claim 8, wherein the plurality of results comprise listing titles that include the text token of the search query.

### Claim 13 (depends on 8)

The method of claim 8, further comprising:
receiving a plurality of annotated images, the annotated images comprising a set of image features and text tokens that correspond to each of the image features of the annotated image; and
mapping the set of image features to the text tokens within the visual repository.

### Claim 14 (depends on 13)

The method of claim 13, wherein the receiving the plurality of annotated images includes:
receiving a plurality of item listings, the plurality of item listings comprising item images and item titles, the item titles including the text tokens; and
mapping the text tokens from the item titles to the item images of the item listings.

### Claim 15

A non-transitory machine readable storage medium storing instructions, that when executed by one or more processors, causes the one or more processors to perform operations comprising:
receiving a search query that includes a text token from a client system;
identifying a plurality of results based on the search query, the plurality of search results including a first search result that comprises an item image that comprises an image feature;
accessing a visual repository that includes a mapping of the text token to a vector of the image feature; and
ranking the first search result among the plurality of search results based on the vector of the image feature.

### Claim 16 (depends on 15)

The non-transitory machine readable storage medium of claim 15, wherein the instructions cause the machine to perform operations further comprising:
storing historical click data for the first search result, the historical click data. indicating a number of requests to access the first search result; and
wherein the ranking the first search result among the plurality of search results is based on the vector of the image feature and the historical click data.

### Claim 17 (depends on 15)

The non-transitory machine readable storage medium of claim 15, wherein the instructions cause the machine to perform operations further comprising:
segmenting e item image into a foreground and a background; and
identifying the image feature in the foreground of the item image in response to the segmenting the item image.

### Claim 18 (depends on 15)

The non-transitory machine readable storage medium of claim 15, wherein the instructions cause the machine to perform operations further comprising:
causing display of a presentation of the plurality of search results at the client system, the presentation of the plurality of search results comprising a display of the first search result that includes the item image at a position among the plurality of search results, the position based on the ranking.

### Claim 19 (depends on 15)

The non-transitory machine readable storage medium of claim 15, wherein the plurality of results comprise listing titles that include the text token of the search query.

### Claim 20 (depends on 15)

The non-transitory machine readable storage medium of claim 15, wherein the instructions cause the machine to perform operations further comprising:
receiving a plurality of annotated images, the annotated images comprising a set of image features and text tokens that correspond to each of the image features of the annotated image; and
mapping the set of image features to the text tokens within the visual repository.
