Animated presentation creator

• US 10,482,159 B2
• Filed: 11/02/2017
• Issued: 11/19/2019
• Est. Priority Date: 11/02/2017
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Bainer, Nicolas, Falasca, Dario Alejando, Gimenez Molinelli, Federico Tomas, Nappe, Nicolas O., Rius, Gaston Alejo, Tcherechansky, Nicolas, Tomaselli, Facundo J.
• Primary Examiner(s): Abebe, Daniel
• Application Number:
  US15/801,388
• Publication Number:
  US 20190129920A1
• Time in Patent Office: 747 Days
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8543 using a description language, e.g. Multimedia and Hypermedia information coding Expert Group [MHEG], eXtensible Markup Language [XML] information retrieval of semistructured data, the underlying structure being taken into account, e.g. mark-up language structure data G06F16/80

Abstract

Aspects create a multimedia presentation wherein processors are configured to calculate a time it would take to narrate a plurality of words in a document at a specified speech speed in response to determining that the time it would take to narrate the plurality of words in the document at the specified speech speed exceeds a specified maximum time, generate a long summary of the document as a subset of the plurality of words, generate audio content for a first portion of the plurality of words of the long summary by applying a text-to-speech processing mechanism to the portion of the long summary at the desired speech speed, and create a multimedia slide of a multimedia presentation by adding the generated audio content to a presentation of text from a remainder portion of the plurality of words of the long summary.

Claims

1. A computer-implemented method for creating a presentation based on a text document, comprising executing on a computer processor:

calculating a time it would take to narrate a plurality of words in a document at a specified speech speed;

in response to determining that the calculated time it would take to narrate the plurality of words in the document at the specified speech speed exceeds a specified maximum time, generating a long summary of the document as a subset of the plurality of words that comprises highest relevant information identified by applying natural language processing to the document, and that requires a time to narrate at the specified speech speed that is less than the specified maximum time;

calculating a long summary ratio by dividing the specified maximum time by the calculated time it would take to narrate the number of words in the document at the desired speech speed;

selecting a first portion of the plurality of words of the long summary to comprise an amount of text content that is the calculated long summary ratio percentage of text content defined by the plurality of words in the document;

generating audio content for the first portion of the plurality of words of the long summary by applying a text-to-speech processing mechanism to the portion of the long summary at the desired speech speed; and

creating a multimedia slide of a multimedia presentation by adding the generated audio content to a presentation of text from a remainder portion of the plurality of words of the long summary.

2. The method of claim 1, further comprising:

integrating computer-readable program code into a computer system comprising a processor, a computer readable memory in circuit communication with the processor, and a computer readable storage medium in circuit communication with the processor; and

wherein the processor executes program code instructions stored on the computer-readable storage medium via the computer readable memory and thereby performs the calculating the time it would take to narrate the plurality of words in a document at the specified speech speed, generating the long summary of the document in response to determining that the time it would take to narrate the plurality of words in the document at the specified speech speed exceeds the specified maximum time, the calculating the long summary ratio, the selecting the first portion of the plurality of words of the long summary, the generating the audio content for the first portion of the plurality of words of the long summary, and the creating the multimedia slide of the multimedia presentation.

3. The method of claim 2, wherein the computer-readable program code is provided as a service in a cloud environment.

4. The method of claim 1, wherein the natural language processing generates relevance scores for text content of the document, the method further comprising:

generating the long summary by selecting text content having relevance scores above a long summary threshold.

5. The method of claim 4, further comprising:

calculating a short summary ratio as a fractional amount of the long summary ratio;

generating a short summary by applying the natural language processing to select a second portion of the document comprising a short summary ratio amount of the plurality of words of the document that have the highest relevance scores;

matching a first sentence of the short summary to a first sentence of the long summary;

matching a second sentence of the short summary to a second sentence of the long summary;

designating the first portion of the plurality of words of the long summary as words of the long summary located between the first sentence and the second sentence;

generating the audio content by applying the text-to-speech processing mechanism to the first portion; and

creating the multimedia slide by adding the first sentence of the short summary and the audio content to the multimedia slide.

6. The method of claim 5, further comprising,

generating the short summary by selecting scored text having relevance scores above a short summary threshold.

7. The method of claim 4, further comprising:

selecting the short summary ratio to be half the long summary ratio.

8. The method of claim 5, further comprising:

using the natural language processing to score the text content of the document based on the location of phrases within the document.

9. A system comprising:

a processor;

a computer readable memory in circuit communication with the processor; and

a computer readable storage medium in circuit communication with the processor;

wherein the processor executes program instructions stored on the computer-readable storage medium via the computer readable memory and thereby;

calculates a time it would take to narrate a plurality of words in a document at a specified speech speed;

in response to determining that the calculated time it would take to narrate the plurality of words in the document at the specified speech speed exceeds a specified maximum time, generates a long summary of the document as a subset of the plurality of words that comprises highest relevant information identified by applying natural language processing to the document, and that requires a time to narrate at the specified speech speed that is less than the specified maximum time;

calculates a long summary ratio by dividing the specified maximum time by the calculated time it would take to narrate the number of words in the document at the desired speech speed;

selects a first portion of the plurality of words of the long summary to comprise an amount of text content that is the calculated long summary ratio percentage of text content defined by the plurality of words in the document;

generates audio content for the first portion of the plurality of words of the long summary by applying a text-to-speech processing mechanism to the portion of the long summary at the desired speech speed; and

creates a multimedia slide of a multimedia presentation by adding the generated audio content to a presentation of text from a remainder portion of the plurality of words of the long summary.

10. The system of claim 9, wherein the natural language processing generates relevance scores for text content of the document and wherein the processor executes the program instructions stored on the computer-readable storage medium via the computer readable memory and thereby:

generates the long summary by selecting text content having relevance scores above a long summary threshold.

11. The system of claim 10, wherein the processor executes the program instructions stored on the computer-readable storage medium via the computer readable memory and thereby:

calculates a short summary ratio as a fractional amount of the long summary ratio;

generates a short summary by applying the natural language processing to select a second portion of the document comprising a short summary ratio amount of the plurality of words of the document that have the highest relevance scores;

matches a first sentence of the short summary to a first sentence of the long summary;

matches a second sentence of the short summary to a second sentence of the long summary;

designates the first portion of the plurality of words of the long summary as words of the long summary located between the first sentence and the second sentence;

generates the audio content by applying the text-to-speech processing mechanism to the first portion; and

creates the multimedia slide by adding the first sentence of the short summary and the audio content to the multimedia slide.

12. The system of claim 11, wherein the processor executes the program instructions stored on the computer-readable storage medium via the computer readable memory and thereby:

generates the short summary by selecting scored text having relevance scores above a short summary threshold.

13. The system of claim 11, wherein the processor executes the program instructions stored on the computer-readable storage medium via the computer readable memory and thereby:

uses the natural language processing to score the text content of the document based on the location of phrases within the document.

14. A computer program product for scheduling an event, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the computer readable program code comprising instructions for execution by a processor that cause the processor to;

calculate a time it would take to narrate a plurality of words in a document at a specified speech speed;

in response to determining that the calculated time it would take to narrate the plurality of words in the document at the specified speech speed exceeds a specified maximum time, generate a long summary of the document as a subset of the plurality of words that comprises the highest relevant information identified by applying natural language processing to the document, and that requires a time to narrate at the specified speech speed that is less than the specified maximum time;

calculate a long summary ratio by dividing the specified maximum time by the calculated time it would take to narrate the number of words in the document at the desired speech speed;

select a first portion of the plurality of words of the long summary to comprise an amount of text content that is the calculated long summary ratio percentage of text content defined by the plurality of words in the document;

generate audio content for the first portion of the plurality of words of the long summary by applying a text-to-speech processing mechanism to the portion of the long summary at the desired speech speed; and

create a multimedia slide of a multimedia presentation by adding the generated audio content to a presentation of text from a remainder portion of the plurality of words of the long summary.

15. The computer program product of claim 14, wherein the natural language processing generates relevance scores for text content of the document and wherein the computer readable program code instructions for execution by the processor further cause the processor to:

generate the long summary by selecting text content having relevance scores above a long summary threshold.

16. The computer program product of claim 15, wherein the computer readable program code instructions for execution by the processor further cause the processor to:

calculate a short summary ratio as a fractional amount of the long summary ratio;

generate a short summary by applying the natural language processing to select a second portion of the document comprising a short summary ratio amount of the plurality of words of the document that have the highest relevance scores;

match a first sentence of the short summary to a first sentence of the long summary;

match a second sentence of the short summary to a second sentence of the long summary;

designate the first portion of the plurality of words of the long summary as words of the long summary located between the first sentence and the second sentence;

generate the audio content by applying the text-to-speech processing mechanism to the first portion; and

create the multimedia slide by adding the first sentence of the short summary and the audio content to the multimedia slide.

17. The computer program product of claim 16, wherein the computer readable program code instructions for execution by the processor further cause the processor to:

generate the short summary by selecting scored text having relevance scores above a short summary threshold.