System and method for providing context recommendations

1 . A computer-implemented method for generating one or more content recommendation, the method comprising:

opening a content recommendation session for a selected user, wherein, as part of the session, a content recommendation procedure for generating one or more recommendation candidates based on a seed content item or seed content item identifier is available, wherein the content recommendation procedure is an item based procedure configured to receive, as an input, a seed content item or seed content item identifier and output one or more recommendations corresponding to content items available via a content distribution system;

receiving, from a user device, a content recommendation request representing one or more desired content attributes;

generating a dummy content item having metadata representing the one or more desired content attributes, wherein the dummy content item does not correspond to an available content item, wherein generating the dummy content item comprises creating an instance of a content item object and assigning said metadata representing the one or more desired content attributes to the content item object;

performing the content recommendation procedure thereby to generate one or more content recommendation candidates for the desired content attributes;

wherein the performing of the content recommendation procedure comprises providing the generated dummy content item or an identifier for the dummy content item as the seed content item or seed content item identifier to the item based procedure.

2 . The method of claim 1 , wherein performing the content recommendation procedure comprises:

obtaining metadata associated with the dummy content item or a corresponding dummy content item identifier; and

identifying related content comprising content associated with one or more of the same or similar metadata.

3 . The method of claim 1 , wherein the content attributes comprise any property, parameter and/or characteristic capable of distinguishing one or more content items.

4 . The method of claim 1 , wherein the content attributes comprise at least one of: Actor; Audience; Award; Category; Character; Character Type; Concept Source; Director; Format; Franchise; Host; Milieu; Mood; Producer; Person; Subcategory; Scenario; Setting; Sports Competition; Studio; Style; Subject; Team; Theme; Time Period; Writer.

5 . The method of claim 1 , wherein the generated dummy content item comprises a transitory content item, optionally, wherein the method comprises deleting the dummy content item from storage after completion of the content recommendation procedure.

6 . The method of claim 1 , wherein the content attributes and their associated weighting are represented mathematically as a feature vector and wherein generating the dummy content item comprises assigning values to the feature vector so that the feature vector represents the desired attributes.

7 . The method of claim 6 , wherein performing the recommendation procedure comprises determining a set of closest feature vectors to the feature vector wherein the recommendation candidates correspond to the determined set of nearest feature vectors.

8 . The method of claim 1 , wherein the method comprises receiving user input and wherein the content attributes are generated based on keywords derived from user input.

9 . The method of claim 1 , wherein the method comprises processing an audio input sample to extract content attributes and/or attribute weightings for the request.

10 . The method of claim 1 , wherein the method comprises receiving user input performing a comparison between at least some of the received user input and a stored list of attributes to determine the content attributes and/or attribute weightings.

11 . The method of claim 1 , wherein the method further comprises performing one or more selection and/or filtering and/or ranking procedures on the one or more content recommendation candidates based on obtained user data.

12 . The method of claim 1 further comprising:

using the seed content item identifier to generate a plurality of non-personalised content item recommendations; and

sorting, filtering and/or ranking the plurality of non-personalised content item recommendations using user data.

13 . The method of claim 12 , wherein the sorting, filtering and/or ranking of the plurality of non-personalised content item recommendations comprises using content metadata or more other items of user data to identify one or more of the non-personalised content item recommendations that represent a closest match with the user data.

14 . The method of claim 12 further comprising presenting the one or more personalised content item recommendation candidates to the user in order from closest match to least closest match.

15 . The method of claim 12 wherein identifying the closest match comprises comparing metadata associated with the non-personalised content item recommendations with metadata associated or represented by the user data.

16 . The method of claim 1 wherein using the dummy content item and/or identifier to generate a plurality of non-personalised content item recommendations comprises:

obtaining metadata associated with the dummy content item identified by the dummy content item identifier; and identifying related content comprising content associated with one or more of the same or similar metadata.

17 . A system comprising processing circuitry configured to:

open a content recommendation session for a selected user, wherein, as part of the session, a content recommendation procedure for generating one or more recommendation candidates based on a seed content item or seed content item identifier is available, wherein the content recommendation procedure is an item based procedure configured to receive, as an input, a seed content item or seed content item identifier and output one or more recommendations corresponding to content items available via a content distribution system;

receive, from a user input device, a content recommendation request representing one or more desired content attributes;

generating a dummy content item having metadata representing the one or more desired content attributes, wherein the dummy content item does not correspond to an available content item, wherein generating the dummy content item comprises creating an instance of a content item object and assigning said metadata representing the one or more desired content attributes to the content item object;

perform the content recommendation procedure thereby to generate one or more content recommendation candidates for the desired content attributes;

wherein the performing of the content recommendation procedure comprises providing the generated dummy content item or an identifier as the seed content item or seed content item identifier for the dummy content item to the item based procedure.

18 . A non-transitory computer-readable medium that comprises computer-readable instructions that are executable to:

open a content recommendation session for a selected user, wherein, as part of the session, a content recommendation procedure for generating one or more recommendation candidates based on a seed content item or seed content item identifier is available, wherein the content recommendation procedure is an item based procedure configured to receive, as an input, a seed content item or seed content item identifier and output one or more recommendations corresponding to content items available via a content distribution system;

receive, from a user device, a content recommendation request representing one or more desired content attributes;

generate a dummy content item having metadata representing the one or more desired content attributes, wherein the dummy content item does not correspond to an available content item, wherein generating the dummy content item comprises creating an instance of a content item object and assigning said metadata representing the one or more desired content attributes to the content item object;

perform the content recommendation procedure thereby to generate one or more content recommendation candidates for the desired content attributes;

wherein the performing of the content recommendation procedure comprises providing the generated dummy content item or an identifier as the seed content item or seed content item identifier for the dummy content item to the item based procedure.