Calculating a maturity level of a text string

• US 10,037,321 B1
• Filed: 04/10/2017
• Issued: 07/31/2018
• Est. Priority Date: 12/01/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Bhar, Bigyan, Sohoney, Saurabh
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US15/484,002
• Time in Patent Office: 477 Days
• Field of Search: 704 1, 704 9, 704 10, 434178
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Techniques for determining a maturity level of a text string may be provided. For example, the text string may be associated with an electronic book or story, script or closed captioning of a movie or television show, or other text associated with media. The system may analyze the text string to identify actions in the text (e.g., concepts of death, degree of violence, etc.), story complexity (e.g., number of characters, linear/non-linear story flow, etc.), vocabulary (e.g., unique words, complexity of terms, etc.), and other metrics to determine the objective maturity level associated with the text string. The maturity level and/or references to electronic books associated with the particular maturity level may be provided to users and/or used in additional processing and analysis.

Claims

1. A computing device comprising:

a memory configured to store computer-executable instructions; and

a processor in communication with the memory configured to execute the computer-executable instructions to at least;

determine, by the computing device, at least a portion of a text string associated with a story;

determine, by the computing device, a linguistic element in the text string;

analyze, by the computing device, at least one action in the text string by comparing the linguistic element in the text string to a story complexity that comprises an identification of a linear or non-linear story flow; and

determine, by the computing device, a maturity level associated with the portion of the text string based on the analysis by at least;

determining a violence rating for a particular character in the portion of the text string; and

adjusting the maturity level of the portion of the text string to a greater maturity level based in part on the violence rating for the particular character in the portion of the text string.

2. The computing device of claim 1, wherein the analysis further comprises comparing the linguistic element with a data store of mature vocabulary.

3. The computing device of claim 1, wherein the story complexity comprises an identification of a number of characters and wherein determining the maturity level associated with the portion of the text string comprises:

adjusting the maturity level of the portion of the text string to a greater maturity level based in part on the identification of the number of characters.

4. The computing device of claim 1, wherein the analysis further comprises generating a character graph that represents relationships between one or more characters in the text string based at least in part upon one or more verbs and the at least one action, the one or more characters represented as nodes in the character graph.

5. The computing device of claim 1, wherein the computer-executable instructions further comprise:

receive a requested maturity level for an electronic book;

compare the requested maturity level for the electronic book with the maturity level associated with the portion of the text string;

when the requested maturity level for the electronic book is similar to the maturity level associated with the portion of the text string, identify the electronic book associated with the story; and

provide a reference for the electronic book associated with the story in response to the requested maturity level for the electronic book.

6. The computing device of claim 1, wherein analyzing the story complexity further comprises:

determining a character in the story;

determining a number of other characters that interact with the character; and

identifying a greater story complexity when the number of other characters associated with the character exceeds a character threshold.

7. The computing device of claim 6, wherein an interaction between the character and at least one of the other character involves a communication.

8. The computing device of claim 7, wherein the character and the at least one of the other character are associated with each other when a second linguistic element associated with the character appears within a threshold distance of a third linguistic element associated with at least one of the other characters in the text string.

9. The computing device of claim 1, wherein the comparison of the linguistic element to the story complexity comprises:

determining a number of unique linguistic terms in the text string; and

adjusting the maturity level when the number of unique linguistic terms in the text string exceeds a threshold.

10. One or more non-transitory computer-readable storage media collectively storing computer-executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to collectively perform operations comprising:

determining at least a portion of a text string associated with a story;

determining a linguistic element in the text string;

analyzing the linguistic element in the text string with respect to a story complexity that comprises an identification of a linear or non-linear story flow, wherein analyzing the story complexity further comprises;

determining a character in the story;

determining a number of other characters that interact with the character; and

identifying a greater story complexity when the number of other characters associated with the character exceeds a character threshold; and

determining a maturity level associated with the portion of the text string based on the analysis.

11. The one or more non-transitory computer-readable storage media of claim 10, wherein determining the maturity level associated with the portion of the text string comprises:

determining a violence rating for a particular character in the portion of the text string; and

adjusting the maturity level of the portion of the text string to a greater maturity level based in part on the violence rating for the particular character in the portion of the text string.

12. The one or more non-transitory computer-readable storage media of claim 10, wherein the violence rating is stored with a data store of mature vocabulary.

13. The one or more non-transitory computer-readable storage media of claim 10, wherein the story is associated with a motion picture and the text string is associated with a script or subtitles of the motion picture.

14. The one or more non-transitory computer-readable storage media of claim 10, wherein the story is associated with an electronic book and the text string is associated with a passage or chapter of the electronic book.

15. The one or more non-transitory computer-readable storage media of claim 10, wherein the operations further comprise:

receiving a requested maturity level for an electronic book;

comparing the requested maturity level for the electronic book with the maturity level associated with the portion of the text string;

when the requested maturity level for the electronic book is similar to the maturity level associated with the portion of the text string, identifying the electronic book associated with the story; and

providing a reference for the electronic book associated with the story in response to the requested maturity level for the electronic book.

16. A computer-implemented method comprising:

determining, by a computing device, at least a portion of a text string associated with a story;

determining, by the computing device, a linguistic element in the text string;

analyzing, by the computing device, at least one action in the text string by comparing the linguistic element in the text string to a story complexity that comprises an identification of a number of characters; and

determining, by the computing device, a maturity level associated with the portion of the text string based on the analysis, wherein a character and at least one other character are associated with each other when a second linguistic element associated with the character appears within a threshold distance of a third linguistic element associated with at least one of the other characters in the text string.

17. The computer-implemented method of claim 16, wherein analyzing the story complexity further comprises:

identifying a greater story complexity when the number of characters exceeds a character threshold.

18. The computer-implemented method of claim 16, wherein determining the maturity level associated with the portion of the text string comprises:

determining a violence rating for a particular character in the portion of the text string; and

adjusting the maturity level of the portion of the text string to a greater maturity level based in part on the violence rating for the particular character in the portion of the text string.