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.
1 . A client computer for use in processing content data, the client computer being configurable to communicate with a remote server system via a network, the client computer comprising:
network communication modem hardware configurable for use in association with data communication with the remote server system via the network;
programmable system-on-chip (SOC) comprising central processing unit (CPU) core circuitry and accelerator circuitry, the accelerator circuitry comprising graphics processing unit (GPU) circuitry and neural network accelerator circuitry, the accelerator circuitry to execute artificial intelligence (AI)-related operations and/or machine learning (ML)-related operations, the AI-related operations and/or the ML-related operations to be based upon model data and the content data, the AI-related operations and/or the ML-related operations to result in generation of results data; and
input/output (I/O) device hardware to generate user output data corresponding, at least in part, to the results data;
wherein:
the content data is configurable to comprise one or more of audio data, video data, and/or text data;
the results data is configurable, based upon user input data, to comprise (1) at least one summary of the content data, and (2) user recommendation data related to the content data;
the at least one summary is selectable, based upon the user input data, from multiple possible summaries of the content data;
the multiple possible summaries are different from each other, at least in part;
the multiple possible summaries correspond, at least in part, to multiple possible manners of user presentation via the input/output (I/O) device hardware;
in event that the content data comprises the audio data and/or the video data, the at least one summary and/or the recommendation data are configurable to be generated in association with transcription data that corresponds, at least in part, to the audio data and/or the video data;
the AI-related operations and/or the ML-related operations are associated, at least in part, with determining one or more neural network-associated weights to be used in natural language processing;
the natural language processing comprises determining one or more key words and/or one or more key phrases to be comprised in the at least one summary;
the client computer is to provide to the remote server system, via the network, user-associated weight-related data; and
the user-associated weight-related data is to be combined, by the remote server system, with other user-associated weight-related data for use in association with the natural language processing.
2 . The client computer of claim 1 , wherein:
the client computer is to receive program instructions from the remote server system via the network that, when executed by the client computer, results in performance of the AI-related operations and/or the ML-related operations; and
the client computer comprises a smartphone.
3 . The client computer of claim 2 , wherein:
the generation of the results data is associated, at least in part, with text highlighting.
4 . The client computer of claim 2 , wherein:
the generation of the results data is associated with one or more of: email data, text message data, document data, and/or multimedia data.
5 . The client computer of claim 4 , wherein:
the user output data is to be associated, at least in part, with a smartphone application.
6 . The client computer of claim 4 , wherein:
the at least one summary comprises other data extracted and/or abstracted from the content data.
7 . The client computer of claim 4 , wherein:
the client computer is to output the user output data as speech.
8 . At least one non-transitory computer-readable storage medium storing instructions for being executed by a client computer, the client computer to be used in processing content data, the client computer being configurable to communicate with a remote server system via a network, the client computer comprising network communication modem hardware, a programmable system-on-chip (SOC), and input/output (I/O) device hardware, the programmable SOC comprising central processing unit (CPU) core circuitry and accelerator circuitry, the accelerator circuitry comprising graphics processing unit (GPU) circuitry and neural network accelerator circuitry, the instructions, when executed by the client computer, resulting in the client computer being configured for performance of operations comprising:
using the network communication modem hardware in association with data communication with the remote server system via the network;
executing, by the accelerator circuitry, artificial intelligence (AI)-related operations and/or machine learning (ML)-related operations, the AI-related operations and/or the ML-related operations to be based upon model data and the content data, the AI-related operations and/or the ML-related operations to result in generation of results data; and
generating, using the input/output (I/O) device hardware, user output data corresponding, at least in part, to the results data;
wherein:
the content data is configurable to comprise one or more of audio data, video data, and/or text data;
the results data is configurable, based upon user input data, to comprise (1) at least one summary of the content data, and (2) user recommendation data related to the content data;
the at least one summary is selectable, based upon the user input data, from multiple possible summaries of the content data;
the multiple possible summaries are different from each other, at least in part;
the multiple possible summaries correspond, at least in part, to multiple possible manners of user presentation via the input/output (I/O) device hardware;
in event that the content data comprises the audio data and/or the video data, the at least one summary and/or the recommendation data are configurable to be generated in association with transcription data that corresponds, at least in part, to the audio data and/or the video data;
the AI-related operations and/or the ML-related operations are associated, at least in part, with determining one or more neural network-associated weights to be used in natural language processing;
the natural language processing comprises determining one or more key words and/or one or more key phrases to be comprised in the at least one summary;
the client computer is to provide to the remote server system, via the network, user-associated weight-related data; and
the user-associated weight-related data is to be combined, by the remote server system, with other user-associated weight-related data for use in association with the natural language processing.
9 . The at least one non-transitory computer-readable storage medium of claim 8 , wherein:
the client computer is to receive the instructions, at least in part, from the remote server system via the network; and
the client computer comprises a smartphone.
10 . The at least one non-transitory computer-readable storage medium of claim 9 , wherein:
the generation of the results data is associated, at least in part, with text highlighting.
11 . The at least one non-transitory computer-readable storage medium of claim 9 , wherein:
the generation of the results data is associated with one or more of: email data, text message data, document data, and/or multimedia data.
12 . The at least one non-transitory computer-readable storage medium of claim 11 , wherein:
the user output data is to be associated, at least in part, with a smartphone application.
13 . The at least one non-transitory computer-readable storage medium of claim 11 , wherein:
the at least one summary comprises other data extracted and/or abstracted from the content data.
14 . The at least one non-transitory computer-readable storage medium of claim 11 , wherein:
the client computer is to output the user output data as speech.
15 . A method implemented, at least in part, using a client computer, the client computer to be used in processing content data, the client computer being configurable to communicate with a remote server system via a network, the client computer comprising network communication modem hardware, a programmable system-on-chip (SOC), and input/output (I/O) device hardware, the programmable SOC comprising central processing unit (CPU) core circuitry and accelerator circuitry, the accelerator circuitry comprising graphics processing unit (GPU) circuitry and neural network accelerator circuitry, the method comprising:
using the network communication modem hardware in association with data communication with the remote server system via the network;
executing, by the accelerator circuitry, artificial intelligence (AI)-related operations and/or machine learning (ML)-related operations, the AI-related operations and/or the ML-related operations to be based upon model data and the content data, the AI-related operations and/or the ML-related operations to result in generation of results data; and
generating, using the input/output (I/O) device hardware, user output data corresponding, at least in part, to the results data;
wherein:
the content data is configurable to comprise one or more of audio data, video data, and/or text data;
the results data is configurable, based upon user input data, to comprise ( 1 ) at least one summary of the content data, and ( 2 ) user recommendation data related to the content data;
the at least one summary is selectable, based upon the user input data, from multiple possible summaries of the content data;
the multiple possible summaries are different from each other, at least in part;
the multiple possible summaries correspond, at least in part, to multiple possible manners of user presentation via the input/output (I/O) device hardware;
in event that the content data comprises the audio data and/or the video data, the at least one summary and/or the recommendation data are configurable to be generated in association with transcription data that corresponds, at least in part, to the audio data and/or the video data;
the AI-related operations and/or the ML-related operations are associated, at least in part, with determining one or more neural network-associated weights to be used in natural language processing;
the natural language processing comprises determining one or more key words and/or one or more key phrases to be comprised in the at least one summary;
the client computer is to provide to the remote server system, via the network, user-associated weight-related data; and
the user-associated weight-related data is to be combined, by the remote server system, with other user-associated weight-related data for use in association with the natural language processing.
16 . The method of claim 15 , wherein:
the client computer is to receive program instructions from the remote server system via the network that, when executed by the client computer, results in performance of the AI-related operations and/or the ML-related operations; and
the client computer comprises a smartphone.
17 . The method of claim 16 , wherein:
the generation of the results data is associated, at least in part, with text highlighting.
18 . The method of claim 16 , wherein:
the generation of the results data is associated with one or more of: email data, text message data, document data, and/or multimedia data.
19 . The method of claim 18 , wherein:
the user output data is to be associated, at least in part, with a smartphone application.
20 . The method of claim 18 , wherein:
the at least one summary comprises other data extracted and/or abstracted from the content data.
21 . The method of claim 18 , wherein:
the client computer is to output the user output data as speech.
22 . A server system configurable to communicate with a client computer via a network, the client computer to be used in processing content data, the client computer comprising programmable system-on-chip (SOC) and input/output (I/O) device hardware, the programmable SOC comprising central processing unit (CPU) core circuitry and accelerator circuitry, the accelerator circuitry comprising graphics processing unit (GPU) circuitry and neural network accelerator circuitry, the accelerator circuitry to execute artificial intelligence (AI)-related operations and/or machine learning (ML)-related operations, the server system comprising:
processor circuitry; and
computer-readable storage to store instructions that are to be executed by the processor circuitry, the instructions, when executed by the processor circuitry, resulting in performance of operations comprising:
transmitting, via the network, program instructions to the client computer that are to be executed by the client computer, the program instructions, when executed by the client computer, resulting in performance of the AI-related operations and/or the ML-related operations, the AI-related operations and/or the ML-related operations to be based upon model data and the content data, the AI-related operations and/or the ML-related operations to result in generation of results data, the I/O device hardware to generate user output data corresponding, at least in part, to the results data;
wherein:
the content data is configurable to comprise one or more of audio data, video data, and/or text data;
the results data is configurable, based upon user input data, to comprise (1) at least one summary of the content data, and (2) user recommendation data related to the content data;
the at least one summary is selectable, based upon the user input data, from multiple possible summaries of the content data;
the multiple possible summaries are different from each other, at least in part;
the multiple possible summaries correspond, at least in part, to multiple possible manners of user presentation via the input/output (I/O) device hardware;
in event that the content data comprises the audio data and/or the video data, the at least one summary and/or the recommendation data are configurable to be generated in association with transcription data that corresponds, at least in part, to the audio data and/or the video data;
the AI-related operations and/or the ML-related operations are associated, at least in part, with determining one or more neural network-associated weights to be used in natural language processing;
the natural language processing comprises determining one or more key words and/or one or more key phrases to be comprised in the at least one summary;
the server system is to receive from the client computer, via the network, user- associated weight-related data; and
the user-associated weight-related data is to be combined, by the server system, with other user-associated weight-related data for use in association with the natural language processing.
23 . The server system of claim 22 , wherein:
the client computer comprises a smartphone.
24 . The server system of claim 23 , wherein:
the generation of the results data is associated, at least in part, with text highlighting.
25 . The server system of claim 23 , wherein:
the generation of the results data is associated with one or more of: email data, text message data, document data, and/or multimedia data.
26 . The server system of claim 25 , wherein:
the user output data is to be associated, at least in part, with a smartphone application.
27 . The server system of claim 25 , wherein:
the at least one summary comprises other data extracted and/or abstracted from the content data.
28 . The server system of claim 25 , wherein:
the client computer is to output the user output data as speech.