Cognitive browse operation
A method, system and computer readable medium for performing a cognitive browse operation comprising: receiving training data, the training data comprising information based upon user interaction with cognitive attributes; performing a machine learning operation on the training data; generating a cognitive profile based upon the information generated by performing the machine learning operation; and, performing a cognitive browse operation on a corpus of content based upon the cognitive profile, the cognitive browse operation returning cognitive browse results specific to the cognitive profile of the user.
1. A computer-implementable method for performing a cognitive browse operation comprising:
receiving training data, the training data comprising information based upon user interaction with cognitive attributes, the training data comprising a corpus of content;
curating the corpus of content to generate a curated corpus of content, the curated corpus of content comprising a product-by-feature matrix and a product-by-user-interaction matrix, each row of the product-by-feature matrix representing a particular product and each column of the product-by-feature matrix representing a particular feature, each row of the product-by-user-interaction matrix representing a particular user and each column of the product-by-user-interaction matrix representing a particular product associated with the particular user interaction;
performing a machine learning operation on the training data, the machine learning operation using the curated corpus of content;
performing a cognitive learning operation via a cognitive inference and learning system using the training data, the cognitive learning operation including the machine learning operation, the machine learning operation generating a cognitive learning result;
generating a cognitive profile based upon the cognitive learning result generated by performing the machine learning operation; and,
performing a cognitive browse operation on a corpus of content based upon the cognitive profile, the cognitive browse operation returning cognitive browse results specific to the cognitive profile of the user; and wherein
the machine learning operation comprises a hierarchical topic model operation, the hierarchical topic model operation generating a hierarchical topic model via a domain topic abstraction algorithm, the hierarchical topic model representing a hierarchical abstraction of topics, the hierarchical topic model operation processing the corpus of content to identify a set of domain topics, the hierarchical topic model operation abstracting the set of domain topics into the hierarchical topic model, domain topics having a higher degree of abstraction being hierarchically abstracted into upper levels of the hierarchical topic model and domain topics having a lesser degree of abstraction being hierarchically abstracted into lower levels of abstraction, each of the set of domain topics having an associated attribute, each of the set of domain topics being abstracted into the hierarchical topic model according to the associated attribute.
2. The method of claim 1 , wherein:
the results specific to the user are further refined based upon terms used when performing the cognitive browse operation.
3. The method of claim 2 , wherein:
a second user having a second cognitive profile and performing a search using the terms used when performing the cognitive browse operation would return cognitive browse results specific to the second cognitive profile.
4. The method of claim 1 , wherein:
the machine learning operation comprises a ranked insight model operation, the ranked insight operation comprising a factor-needs operation.
5. The method of claim 1 , wherein:
the hierarchical topic model operation comprises a domain topic abstraction operation and a hierarchical topic navigation operation, the domain topic abstraction operation resulting in a hierarchical abstraction of domain topics, the hierarchical topic navigation operation assisting a user to hierarchically navigate a particular hierarchical topic model.
6. The method of claim 1 , wherein:
the cognitive profile is continuously updated based upon at least one of a plurality of feedback information sources, the feedback information sources comprising information based upon feedback from interactions between the user and the cognitive insight and learning system, information from a query submitted by the user to the cognitive insight and learning system, information from external input data, information from a user navigating a hierarchical topic model and information received from a training system.
7. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
receiving training data, the training data comprising information based upon user interaction with cognitive attributes, the training data comprising a corpus of content;
curating the corpus of content to generate a curated corpus of content, the curated corpus of content comprising a product-by-feature matrix and a product-by-user-interaction matrix, each row of the product-by-feature matrix representing a particular product and each column of the product-by-feature matrix representing a particular feature, each row of the product-by-user-interaction matrix representing a particular user and each column of the product-by-user-interaction matrix representing a particular product associated with the particular user interaction;
performing a machine learning operation on the training data, the machine learning operation using the curated corpus of content;
performing a cognitive learning operation via a cognitive inference and learning system using the training data, the cognitive learning operation including the machine learning operation, the machine learning operation generating a cognitive learning result;
generating a cognitive profile based upon the cognitive learning result generated by performing the machine learning operation; and,
performing a cognitive browse operation on a corpus of content based upon the cognitive profile, the cognitive browse operation returning cognitive browse results specific to the cognitive profile of the user; and wherein
the machine learning operation comprises a hierarchical topic model operation, the hierarchical topic model operation generating a hierarchical topic model via a domain topic abstraction algorithm, the hierarchical topic model representing a hierarchical abstraction of topics, the hierarchical topic model operation processing the corpus of content to identify a set of domain topics, the hierarchical topic model operation abstracting the set of domain topics into the hierarchical topic model, domain topics having a higher degree of abstraction being hierarchically abstracted into upper levels of the hierarchical topic model and domain topics having a lesser degree of abstraction being hierarchically abstracted into lower levels of abstraction, each of the set of domain topics having an associated attribute, each of the set of domain topics being abstracted into the hierarchical topic model according to the associated attribute.
8. The system of claim 7 , wherein:
the results specific to the user are further refined based upon terms used when performing the cognitive browse operation.
9. The system of claim 8 , wherein:
a second user having a second cognitive profile and performing a search using the terms used when performing the cognitive browse operation would return cognitive browse results specific to the second cognitive profile.
10. The system of claim 7 , wherein:
the plurality of machine learning operation comprise a ranked insight model operation, the ranked insight operation comprising a factor-needs operation.
11. The system of claim 7 , wherein:
the hierarchical topic model operation comprises a domain topic abstraction operation and a hierarchical topic navigation operation, the domain topic abstraction operation resulting in a hierarchical abstraction of domain topics, the hierarchical topic navigation operation assisting a user to hierarchically navigate a particular hierarchical topic model.
12. The system of claim 7 , wherein:
the cognitive profile is continuously updated based upon at least one of a plurality of feedback information sources, the feedback information sources comprising information based upon feedback from interactions between the user and the cognitive insight and learning system, information from a query submitted by the user to the cognitive insight and learning system, information from external input data, information from a user navigating a hierarchical topic model and information received from a training system.
13. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
receiving training data, the training data comprising information based upon user interaction with cognitive attributes, the training data comprising a corpus of content;
curating the corpus of content to generate a curated corpus of content, the curated corpus of content comprising a product-by-feature matrix and a product-by-user-interaction matrix, each row of the product-by-feature matrix representing a particular product and each column of the product-by-feature matrix representing a particular feature, each row of the product-by-user-interaction matrix representing a particular user and each column of the product-by-user-interaction matrix representing a particular product associated with the particular user interaction;
performing a machine learning operation on the training data, the machine learning operation using the curated corpus of content;
performing a cognitive learning operation via a cognitive inference and learning system using the training data, the cognitive learning operation including the machine learning operation, the machine learning operation generating a cognitive learning result;
generating a cognitive profile based upon the cognitive learning result generated by performing the machine learning operation; and,
performing a cognitive browse operation on a corpus of content based upon the cognitive profile, the cognitive browse operation returning cognitive browse results specific to the cognitive profile of the user; and wherein
the machine learning operation comprises a hierarchical topic model operation, the hierarchical topic model operation generating a hierarchical topic model via a domain topic abstraction algorithm, the hierarchical topic model representing a hierarchical abstraction of topics, the hierarchical topic model operation processing the corpus of content to identify a set of domain topics, the hierarchical topic model operation abstracting the set of domain topics into the hierarchical topic model, domain topics having a higher degree of abstraction being hierarchically abstracted into upper levels of the hierarchical topic model and domain topics having a lesser degree of abstraction being hierarchically abstracted into lower levels of abstraction, each of the set of domain topics having an associated attribute, each of the set of domain topics being abstracted into the hierarchical topic model according to the associated attribute.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the results specific to the user are further refined based upon terms used when performing the cognitive browse operation.
15. The non-transitory, computer-readable storage medium of claim 14 , wherein:
a second user having a second cognitive profile and performing a search using the terms used when performing the cognitive browse operation would return cognitive browse results specific to the second cognitive profile.
16. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the plurality of machine learning operation comprise a ranked insight model operation, the ranked insight operation comprising a factor-needs operation.
17. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the hierarchical topic model operation comprises a domain topic abstraction operation and a hierarchical topic navigation operation, the domain topic abstraction operation resulting in a hierarchical abstraction of domain topics, the hierarchical topic navigation operation assisting a user to hierarchically navigate a particular hierarchical topic model.
18. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the cognitive profile is continuously updated based upon at least one of a plurality of feedback information sources, the feedback information sources comprising information based upon feedback from interactions between the user and the cognitive insight and learning system, information from a query submitted by the user to the cognitive insight and learning system, information from external input data, information from a user navigating a hierarchical topic model and information received from a training system.
19. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are deployable to a client system from a server system at a remote location.
20. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.