Media file recommendations for a search engine
A method for recommending results to a user from a search query is provided. The method includes receiving, in a search engine, a search query for a media file from a user, identifying a style preference of the user associated with a one or more media file attributes, based on a user-related search history, selecting, from a database, a one or more media files based on the search query and the style preference of the user, determining a style preference score for the one or more media files based on the media file attributes, and recommending to the user a top ranked media file based on the style preference score. A system including a memory storing instructions and one or more processors to execute the instructions to cause the system to perform the above method is also provided.
1. A method for training a model for recommending media files for a user of a search engine based on a query, comprising:
retrieving a new media file selected by the user;
retrieving the model stored in a training database associated with the search engine, wherein the model has not been trained using the new media file;
determining a style preference score for the new media file based on the model; and
when the style preference score is lower than a pre-selected value:
identifying a new attribute in the new media file that is not included in the model,
updating a first coefficient in the model based on a value of the new attribute,
scoring multiple media files in a user-related search history of the user with the model to form a ranked list based on the updated first coefficient, and
updating a second coefficient in the model when the new media file is not at a top position of the ranked list, relative to the multiple media files in the user-related search history; and
storing the updated model in the training database;
receiving a search query provided by the user to the search engine;
recommending a top-ranked media file matching the search query based on the updated model.
2. The method for training a model as in claim 1 , wherein the retrieving of the new media file selected by the user comprises verifying that a respective search query associated with the new media file is different from one or more search queries in the user-related search history.
3. The method for training a model as in claim 1 , wherein the retrieving of the new media file comprises retrieving the new media file selected by the user after a pre-determined period of time has passed relative to a most recent media file in the user-related search history.
4. The method for training a model as in claim 1 , further comprising, when the style preference score is higher than the pre-selected value, increasing a cutoff to selected older files in the user-related search history.
5. The method for training a model as in claim 1 , wherein the identifying of the new attribute in the new media file comprises identifying a salient feature in the new media file.