Determining popular and trending content characteristics

• US 10,445,753 B1
• Filed: 01/24/2018
• Issued: 10/15/2019
• Est. Priority Date: 08/30/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Taylor, Brett R., Killian, David A., Hill, Peter F., Vaswani, Ameet N., Sham, Ivan King Yu, Atreya, Ranganath, Young, Samuel J.
• Primary Examiner(s): Chea, Philip J
• Assistant Examiner(s): Ahmed, Mohammed
• Application Number:
  US15/879,348
• Time in Patent Office: Days
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

Features are disclosed for analyzing requests for network accessible content, including but not limited to web pages, to determine which topics and other characteristics are popular or are gaining in popularity (“trending”). Content items or sources may be profiled to determine characteristics that two or more content items or sources may have in common. Content requests from multiple client devices may be tracked and analyzed to determine the trending or popular characteristics. Data feeds or reports regarding the summarized content requests may be generated and distributed to content servers and other entities. The data feeds may be used to tailor content, such as by highlighting or featuring content associated with the most-requested content characteristics, or utilizing demographic data to tailor content for different users.

Claims

1. A computer-implemented process, comprising:

assigning individual topics of a plurality of topics to each of a plurality of content items, including content items of different respective content sites, based at least partly on keyword analyses of the content items, wherein each topic is represented by a respective tag;

generating trend data for the topics based on requests from client devices for the content items, the client devices distributed across a plurality of geographic regions, wherein generating the trend data comprises maintaining, for a topic and for each of a plurality of periods of time, a count value representing a count of requests made during the respective period of time for content items to which the topic is assigned, and using the count values to measure a rate of change in popularity of the topic;

wherein generating the trend data further comprises maintaining at least first and second count values for the topic, the first count value corresponding to a first geographic region and representing a count of requests made by client devices in the first geographic region, the second count value corresponding to a second geographic region and representing a count of requests made by client devices in the second geographic region, and using the first and second count values to determine geographic-region-specific rates of change in popularity of the topic;

said process performed by execution of program code by one or more processors.

2. The process of claim 1, further comprising maintaining a mapping table that maps addresses of the content items to the tags, and using the mapping table to determine tags associated with particular requests from the client devices for the content items.

3. The process of claim 1, further comprising processing the requests from the client devices for the content items by retrieving the content items from the content sites and providing the content items to the client devices.

4. The process of claim 3, wherein the process is performed by an intermediary computer system that operates as an intermediary between the client devices and the content sites.

5. The process of claim 1, wherein generating the trend data comprises using device characteristic data associated with the client devices to generate, for the topic, multiple count values that each correspond to a different respective type of client device.

6. The process of claim 1, wherein generating the trend data comprises using demographic data associated with the client devices to generate, for the topic, multiple count values that each correspond to a different demographic category.

7. A system capable of identifying geographic region-specific content request trends, the system comprising a processor and a memory, and being programmed with executable instructions to implement a process that comprises:

monitoring requests from client devices in a plurality of geographic regions for content items hosted by content sites;

determining topics associated with the requests based at least in part on keyword analyses of the requested content items, wherein each topic is represented by a respective tag;

generating count values for each of a plurality of the topics based on (1) the requests for the content items and (2) the determined topics associated with the requests, each count value corresponding to a respective topic and representing a measure of how often content items associated with the respective topic are requested, wherein generating the count values comprises maintaining at least first and second count values for a topic, the first count value corresponding to a first geographic region and representing a count of requests made by client devices in the first geographic region, the second count value corresponding to a second geographic region and representing a count of requests made by client devices in the second geographic region; and

generating, based on the count values, topic trend data reflecting topics associated with an increasing volume of content requests, wherein generating the topic trend data comprises using the count values to determine geographic-region-specific rates of change in popularity of particular topics.

8. The system of claim 7, wherein the process further comprises using demographic data associated with the client devices to determine demographic specific topical trends associated with the content requests.

9. The system of claim 7, wherein the process further comprises using device characteristic data associated with the client devices to determine topical trends associated with each of a plurality of client device types.

10. The system of claim 7, wherein the system is further programmed to transmit the topic trend data as a data feed.

11. The system of claim 7, wherein the system is further programmed to provide the topic trend data to a content provider in response to a request from the content provider.

12. A system comprising one or more computing devices, the system programmed via executable program instructions to implement a process that comprises:

receiving requests made by client devices for content pages hosted by content servers, the client devices distributed across a plurality of geographic regions;

retrieving the requested content pages from the content servers;

determining, based on an analysis of content of the retrieved content pages, topics associated with the retrieved content pages, wherein each topic is represented by a respective tag; and

generating topic trend data based at least partly on a volume of the received requests for content pages and the determined topics associated with the retrieved content pages, said topic trend data indicating trends associated with particular topics;

wherein generating the topic trend data comprises maintaining, for at least a first topic, topic-specific count values representing a measure of how often content pages associated with the first topic are requested over respective periods of time, and using the topic-specific count values to determine a rate of change in popularity of the first topic;

wherein generating the topic-specific count values comprises maintaining at least first and second count values for a topic, the first count value corresponding to a first geographic region and representing a count of requests made by client devices in the first geographic region, the second count value corresponding to a second geographic region and representing a count of requests made by client devices in the second geographic region;

wherein generating the topic trend data comprises using the count values to determine geographic-region-specific rates of change in popularity of particular topics.

13. The system of claim 12, wherein the system is programmed to provide said topic trend data as a data feed.

14. The system of claim 12, wherein generating the topic trend data comprises using device data regarding the client devices associated with particular page requests to determine device-type-specific topical trends.

15. The system of claim 12, wherein generating the topic trend data comprises using demographic data associated with at least some of the client devices to determine demographic-category-specific topical trends.

16. The system of claim 12, wherein the process further comprises generating a mapping table that maps URLs to topics based on the analysis of the retrieved pages, and wherein generating the topic trend data comprises using the mapping table to look up topics associated with specific URLs.

17. The system of claim 12, wherein generating the topic trend data comprises determining, for the first topic, a rate of change in requests for content pages corresponding to the first topic.

18. The system of claim 12, wherein determining the topics associated with the retrieved content pages comprises assigning a textual tag to each of a plurality of retrieved content pages based on keyword analyses of the retrieved content pages, the textual tag representing a particular topic.

19. The system of claim 12, wherein the system is programmed to retrieve the requested content pages from the content servers on behalf of the requesting client devices, and to deliver representations of the requested content pages to the client devices.

20. The system of claim 12, wherein the system includes a page rendering component that partially or fully renders a requested page retrieved from a content server before delivering the requested page to a requesting client device.