Techniques for presenting content to a user based on the user's preferences
Techniques for presenting content to users. The techniques include: obtaining user context information including a first keyword; identifying, based on the first keyword, a first attribute and a second attribute among the plurality of attributes, the first attribute being a characteristic of the first keyword and the second attribute being another characteristic of the first keyword; obtaining, based on the user context information, at least one second-order user preference among attributes in the plurality of attributes including a preference between the first attribute and the second attribute; identifying a set of content items among the plurality of content items based on the first attribute and the second attribute; determining a ranking of content items in the set of content items based on the at least one second-order user preference; and presenting content items to the user in accordance with the ranking.
1. A computer-implemented method of refining an output of an information retrieval system based on a user context associated with a data consumer, the user context indicating user preferences of a user, wherein the information retrieval system is configured to facilitate access to information items from digital content, the information items comprising information on a plurality of items, the information including a plurality of item attributes of the plurality of items, wherein a respective item of the plurality of items is any suitable object or information about which a data consumer may express preferences, and wherein a respective information item comprises item attributes corresponding to the respective item, the method comprising:
using at least one hardware processor to perform:
deriving, by a preference engine, from the user context, at least one first-order preference, wherein the at least one first-order preference comprises, a preference among attribute values of at least one first attribute of the plurality of items;
deriving, by the preference engine at least one second-order preference associated with the user context, wherein the at least one second-order preference comprises a preference among a plurality of second attributes of the plurality of items;
encoding, by the preference engine, a preference model comprising preference attributes, wherein the preference attributes comprise the user preferences encoded as attributes based on at least a subset of the at least one first attribute of the first-order preferences and the plurality of second attributes of the second-order preferences; and
accessing, by the information retrieval system, the preference model to rank, based on the preference attributes, at least a subset of the plurality of information items associated with the plurality of item attributes to obtain a ranking of the information items in the subset.
2. The method of claim 1 , wherein the information retrieval system comprises a synthesis engine, and wherein the synthesis engine derives parameters for synthesis from the preference model.
3. The method of claim 1 , wherein the information retrieval system is implemented using one or more data structures encoding instructions for executing at least an information retrieval function.
4. The method of claim 1 , wherein the information retrieval system interfaces with one or more of a search engine, a database, and a synthesis engine.
5. The method of claim 1 , wherein the preference attributes are encoded as a knowledge representation and wherein the knowledge representation is graph-based, semantic based, or a combination thereof.
6. The method of claim 1 , wherein the processor further performs obtaining the user context by receiving from the data consumer the user context via at least one prompt.
7. The method of claim 1 , wherein the output comprises the subset of the plurality of information items and the method further comprises presenting the output in a graphical user interface in accordance with the ranking.
8. The method of claim 1 , wherein the ranking is based on a graph based model, a PageRank model, a probabilistic model, or a combination thereof.
9. The method of claim 1 , wherein the data consumer is a software application.
10. The method of claim 1 , wherein the at least one first-order preference and the at least one second-order preference are obtained passively or implicitly without interacting with the user.
11. A computer system for refining an output of an information retrieval system based on a user context associated with a data consumer, the user context indicating user preferences of a user, wherein the information retrieval system is configured to facilitate access to information items from digital content, the information items comprising information on a plurality of items, the information including a plurality of item attributes of the plurality of items, wherein a respective item of the plurality of items is any suitable object or information about which a data consumer may express preferences, and wherein a respective information item comprises item attributes corresponding to the respective item, the computer system comprising:
a preference engine configured to:
derive from the user context, at least one first-order preference, wherein the at least one first-order preference comprises, a preference among attribute values of at least one first attribute of the plurality of items;
derive at least one second-order preference associated with the user context, wherein the at least one second-order preference comprises a preference among a plurality of second attributes of the plurality of items; and
encode a preference model comprising preference attributes, wherein the preference attributes comprise the user preferences encoded as attributes based on at least a subset of the at least one first attribute of the first-order preferences and the plurality of second attributes of the second-order preferences; and
the information retrieval system configured to access the preference model to rank, based on the preference attributes, at least a subset of the plurality of information items associated with the plurality of item attributes to obtain a ranking of the information items in the subset.
12. The computer system of claim 11 , wherein the information retrieval system further comprises a synthesis engine, and wherein the synthesis engine is configured to derive parameters for synthesis from the preference model.
13. The computer system of claim 11 , wherein the information retrieval system is implemented using one or more data structures encoding instructions for executing at least an information retrieval function.
14. The computer system of claim 11 , wherein the information retrieval system is configured to interface with one or more of a search engine, a database, and a synthesis engine.
15. The computer system of claim 11 , wherein the preference attributes are encoded as a knowledge representation and wherein the knowledge representation is graph-based, semantic based, or a combination thereof.
16. A tangible, non-transitory computer readable medium having computer-executable instructions stored thereon for refining an output of an information retrieval system based on a user context associated with a data consumer, the user context indicating user preferences of a user, wherein the information retrieval system is configured to facilitate access to information items from digital content, the information items comprising information on a plurality of items, the information including a plurality of item attributes of the plurality of items, wherein a respective item of the plurality of items is any suitable object or information about which a data consumer may express preferences, and wherein a respective information item comprises item attributes corresponding to the respective item, wherein the instructions, when executed by at least one processor, cause the computer to:
derive, by a preference engine, from the user context, at least one first-order preference, wherein the at least one first-order preference comprises, a preference among attribute values of at least one first attribute of the plurality of items;
derive, by the preference engine at least one second-order preference associated with the user context, wherein the at least one second-order preference comprises a preference among a plurality of second attributes of the plurality of items;
encode, by the preference engine, a preference model comprising preference attributes, wherein the preference attributes comprise the user preferences encoded as attributes based on at least a subset of the at least one first attribute of the first-order preferences and the plurality of second attributes of the second-order preferences; and
access, by the information retrieval system, the preference model to rank, based on the preference attributes, at least a subset of the plurality of information items associated with the plurality of item attributes to obtain a ranking of the information items in the subset.
17. The computer readable medium of claim 16 , wherein the information retrieval system is implemented using one or more data structures encoding instructions for executing at least an information retrieval function.
18. The computer readable medium of claim 16 , wherein the preference attributes are encoded as a knowledge representation and wherein the knowledge representation is graph-based, semantic based, or a combination thereof.
19. The computer readable medium of claim 16 , wherein the instructions, when executed, further cause the computer to obtain the user context by receiving from the data consumer the user context via at least one prompt.
20. The computer readable medium of claim 16 , wherein the output comprises the subset of the plurality of information items and wherein the instructions, when executed, further cause the computer to present the output in a graphical user interface in accordance with the ranking.