Recommender system and method for generating implicit ratings based on user interactions with handheld devices

• US 6,947,922 B1
• Filed: 06/16/2000
• Issued: 09/20/2005
• Est. Priority Date: 06/16/2000
• Status: Expired due to Term

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Glance, Natalie S.
• Primary Examiner(s): Kindred, Alford
• Assistant Examiner(s): NGUYEN, CAM LINH T
• Application Number:
  US09/596,070
• Time in Patent Office: 1,922 Days
• Field of Search: 705/26, 1 2/7, 701/201, 707/100, 707/1, 707/3, 707/26
• US Class Current: 1/1
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/637 Administration of user profiles, e.g. generation, initialization, adaptation or distribution
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A recommender system employs implicit ratings generated from monitoring user interaction with an item, such as while listening to a music track on a MP3 player or reading an electronic book. A method for generating item recommendations includes: providing an item to a device having an application for engaging a repetitive activity with the provided item, wherein the repetitive activity occurs primarily during standalone operation of the device; generating a history of user interaction with the provided item, wherein user interaction includes engaging in the repetitive activity with the provided item; transforming the history of user interactions into an implicit rating of the provided item; and using the implicit rating of the provided item to generate recommendations of other items.

Claims

1. A method for generating recommendations, comprising:

providing an item of a particular type to a handheld de having an application for engaging in a repetitive activity with items of the particular type, wherein the repetitive activity comprises displaying or playing items of the particular type to a user;

generating a history of user interaction with the provided item, wherein a user interaction comprises an instance of a user causing the application to display or play the provided item to the user and duration of the display or play, wherein each user interaction occurs during standalone operation of the handheld device disconnected from a network;

wherein the history of user interactions is transformed into recency and frequency of interaction data pertaining to the provided item;

uploading the history of user interactions to a network recommender;

transforming the history into an implicit rating of the provided item, wherein the history of user interactions with the provided item may be used to create more accurate statistical profiles the rating comprising predicted ratings for a user for a plurality of items not rated by the user, having measure of confidence in the prediction and a rationale for the prediction;

using the implicit rating of the provided item to generate recommendations of other items of the particular type; and

wherein an implicit rating is generated in accordance with the relationship;

rating(item)=number of interactions (item) since datetime(item acquired)/number of total interactions (item) since datetime(item acquired).

2. A method for generating recommendations, comprising

providing an item of a particular type to a handheld device having an application for engaging in a repetitive activity with items of the particular type, wherein the repetitive activity comprises displaying or playing items of the particular type to a user;

generating a history of user interaction with the provided item, wherein a user interaction comprises an instance of a user causing the application to display or play the provided item to the user and duration of the display or play, wherein each user interaction occurs during standalone operation of the handheld device disconnected from a network;

wherein the history of user interactions is transformed into data pertaining to normalized time spent interacting with the provided item;

uploading the history of user interactions to a network recommender;

transforming the history into an implicit rating of the provided item, wherein the history of user interactions with the provided item may be used to create more accurate statistical profiles the rating comprising predicted ratings for a user for a plurality of items not rated by the user, having a measure of confidence in the prediction and a rationale for the prediction;

using the implicit rating of the provided item to generate recommendations of other items of the particular type; and

wherein an implicit rating is generated in accordance with the relationship;

rating(item)=total interaction time(item)/size(item).

3. A method for generating recommendations, comprising:

providing an item of a particular type to a handheld device having an application for engaging in a repetitive activity with items of the particular type, wherein the repetitive activity comprises displaying or playing items of the particular type to a user;

generating a history of user interaction with the provided item, wherein a user interaction comprises an instance of a user causing the application to display or play the provided item to the user and duration of the display or play, wherein each user interaction occurs during standalone operation of the handheld device disconnected from a network;

wherein the history of user interactions is transformed into data pertaining to normalized time spent interacting with the provided item;

uploading the history of user interactions to a network recommender;

transforming the history into an implicit rating of the provided item, wherein the history of user interactions with the provided item may be used to create more accurate statistical profiles the rating comprising predicted ratings for a user for a plurality of items not rated by the user, having a measure of confidence in the prediction and a rationale for the prediction;

using the implicit rating of the provided item to generate recommendations of other items of the particular type; and

wherein an implicit rating is generated in accordance with the relationship;

rating(item)=[total interaction time(item)/size(item)*exp(−

damping coefficient]*(date−

time acquired).