CONTENT SUMMARIZATION AND/OR RECOMMENDATION APPARATUS AND METHOD
Embodiments are provided for summarization and recommendation of content. In disclosed embodiments, a summarization engine scores constituent parts of content, and generates a plurality of summaries from a plurality of points of view for the content based at least in part on the scores of constituent parts. The summaries may be formed with constituent parts extracted from the contents. A recommendation engine provides recommendations to a user based on rankings of the summaries generated by the summarization engine. Other embodiments may be described and/or claimed.
21 . At least one non-transitory computer readable storage medium comprising a set of instructions which, when executed, cause a computing apparatus to:
conduct an analysis, using natural language processing, of raw text from a user, the analysis to:
identify at least one main concept; and
identify at least one named entity; and
identify an opinion based on the analysis;
wherein one or more of the at least one main concept, the at least one named entity or the opinion are provided to the user.
22 . The at least one non-transitory computer readable storage medium of claim 21 , wherein the analysis is to identify key phrases contained in the text, wherein at least one key phrase includes a noun.
23 . The at least one non-transitory computer readable storage medium of claim 22 , wherein the analysis is to ignore non-essential words contained in the text.
24 . The at least one non-transitory computer readable storage medium of claim 23 , wherein the analysis is to determine a relative importance of the identified key phrases by measuring a frequency of occurrence of the identified key phrases, and wherein the at least one main concept is identified based on the determined relative importance.
25 . The at least one non-transitory computer readable storage medium of claim 21 , wherein the instructions, when executed, cause the computing apparatus to provide one or more links to further information relating to the text.
26 . The at least one non-transitory computer readable storage medium of claim 21 , wherein the computing apparatus comprises a trained machine learning model.
27 . The at least one non-transitory computer readable storage medium of claim 26 , wherein the trained machine learning model is a neural network.
28 . A computing system comprising:
a processor; and
a memory coupled to the processor, the memory including a set of executable program instructions which, when executed by the processor, cause the computing system to:
conduct an analysis, using natural language processing, of raw text from a user, the analysis to:
identify at least one main concept; and
identify at least one named entity; and
identify an opinion based on the analysis;
wherein one or more of the at least one main concept, the at least one named entity or the opinion are provided to the user.
29 . The computing system of claim 28 , wherein the analysis is to identify key phrases contained in the text, wherein at least one key phrase includes a noun.
30 . The computing system of claim 29 , wherein the analysis is to ignore non-essential words contained in the text.
31 . The computing system of claim 30 , wherein the analysis is to determine a relative importance of the identified key phrases by measuring a frequency of occurrence of the identified key phrases, and wherein the at least one main concept is identified based on the determined relative importance.
32 . The computing system of claim 28 , wherein the instructions, when executed, cause the computing system to provide one or more links to further information relating to the text.
33 . The computing system of claim 28 , wherein the computing apparatus comprises a trained machine learning model.
34 . The computing system of claim 33 , wherein the trained machine learning model is a neural network.
35 . The computing system of claim 28 , wherein the processor comprises a hardware accelerator.
36 . A method comprising:
conducting an analysis, using natural language processing, of raw text from a user, the analysis including:
identifying at least one main concept; and
identifying at least one named entity; and
identifying an opinion based on the analysis;
wherein one or more of the at least one main concept, the at least one named entity or the opinion are provided to the user.
37 . The method of claim 36 , wherein the analysis is to identify key phrases contained in the text, wherein at least one key phrase includes a noun.
38 . The method of claim 37 , wherein the analysis is to ignore non-essential words contained in the text.
39 . The method of claim 38 , wherein the analysis is to determine a relative importance of the identified key phrases by measuring a frequency of occurrence of the identified key phrases, and wherein the at least one main concept is identified based on the determined relative importance.
40 . The method of claim 36 , further comprising providing one or more links to further information relating to the text.
41 . The method of claim 36 , wherein the analysis is conducted using a trained machine learning model.
42 . The method of claim 41 , wherein the trained machine learning model is a neural network.