Dynamic memory allocation using natural language processing tags

• US 10,642,890 B2
• Filed: 08/09/2018
• Issued: 05/05/2020
• Est. Priority Date: 08/09/2018
• Status: Active Grant

• Current Assignee: Bank of America Corp.
• Original Assignee: Bank of America Corp.
• Inventors: Purushothaman, Sasidhar, Kurian, Manu J., Gutman, Sean M., McCormack, James, Ramasamy, Suki, Jacobson, William P.
• Primary Examiner(s): Nguyen, Duc
• Assistant Examiner(s): Eljaiek, Alexander L
• Application Number:
  US16/059,893
• Publication Number:
  US 20200050703A1
• Time in Patent Office: 635 Days
• Field of Search: 700 94, 704236, 707737, 707738, 707776
• CPC Class Codes: G06F 16/61 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A natural language processing system that includes an artificial intelligence (AI) engine, a tagging engine, and a resource allocation engine. The AI engine is configured to receive a set of audio files and to identify concepts within the set of audio files. The AI engine is further configured to determine a usage frequency for each of the identified concepts and to generate an AI-defined tag for concepts with a usage frequency that is greater than a usage frequency threshold. The tagging engine is configured to receive an audio file and to modify metadata for the audio file to include AI-defined tags. The resource allocation engine is configured to identify a storage location from among the plurality of storage devices based on tags associated with the audio file and send the audio file to the identified storage location.

Claims

1. A natural language processing system, comprising:

a plurality of storage devices;

a network interface in signal communication with the plurality of storage devices and one or more data sources, wherein the network interface is configured to receive audio files from the one or more data sources;

a memory operable to store artificial intelligence (AI)-defined tags linked with a first set of concepts; and

a processor operably coupled to the network interface and the memory, configured to;

receive a set of audio files;

identify concepts within the set of audio files;

determine a usage frequency for each of the identified concepts, wherein the usage frequency indicates how often each of the identified concepts occurs within the set of audio files;

compare the usage frequency for each identified concept to a usage frequency threshold;

generate an AI-defined tag for each identified concept with a usage frequency that is greater than the usage frequency threshold, wherein each AI-defined tag is linked with the corresponding identified concept;

receive an audio file;

modify metadata for the audio file to include AI-defined tags linked with concepts from the first set of concepts;

identify non-verbal audio information present within the audio file;

determine a context tag based on the identified non-verbal audio information present within the audio file, wherein the determined context tag identifies a sound characteristic that is present within the audio file;

modify the metadata for the audio file to include the determined context tag;

analyze the metadata for audio file to identify tags associated with the audio file;

determine a priority level for the audio file based on the tags associated with the audio file;

determine a data access speed for the audio file based on the determined priority level associated with the audio file;

select a storage location from among the plurality of storage devices based on the determined data access speed; and

send the audio file to the identified storage location.

2. The system of claim 1, wherein:

a storage device type based at least in part on the determined priority level.

3. The system of claim 2, wherein the processor is further configured to modify the metadata for the audio file to include the determined priority level for the audio file.

4. The system of claim 1, wherein the processor is further configured to:

determine how often the audio file has been accessed within a predetermined time period;

determine an activity level for the audio file based on how often the audio file has been access within the predetermined time period, wherein the activity level is a value that decays over time; and

modify the metadata for the audio file to include the activity level for the audio file.

5. The system of claim 1, wherein:

the memory is operable to store user-defined tags linked with a second set of concepts; and

the tagging engine is further configured to;

modify the metadata for the audio file to include user-defined tags linked with concepts from the second set of concepts.

6. A natural language processing method, comprising:

receiving a set of audio files;

identifying concepts within the set of audio files;

determining a usage frequency for each of the identified concepts, wherein the usage frequency indicates how often each of the identified concepts occurs within the set of audio files;

comparing the usage frequency for each identified concept to a usage frequency threshold; and

generating an AI-defined tag for each identified concept with a usage frequency that is greater than the usage frequency threshold, wherein each AI-defined tag is linked with a concept from a first set of concepts; and

receiving an audio file;

modifying metadata for the audio file to include AI-defined tags linked with concepts from the first set of concepts;

identifying non-verbal audio information present within the audio file;

determining a context tag based on the identified non-verbal audio information present within the audio file, wherein the determined context tag identifies a sound characteristic that is present within the audio file;

modifying the metadata for the audio file to include the determined context tag;

analyzing the metadata for the audio file to identify tags associated with the audio file;

determining a priority level for the audio file based on the tags associated with the audio file;

determining a data access speed for the audio file based on the determined priority level associated with the audio file;

selecting a storage location from among the plurality of storage devices based on the determined data access speed; and

sending the audio file to the identified storage location.

7. The method of claim 6, wherein:

selecting a storage device type based at least in part on the determined priority level.

8. The method of claim 7, further comprising modifying the metadata for the audio file to include the determined priority level for the audio file.

9. The method of claim 6, further comprising:

determining how often the audio file has been accessed within a predetermined time period;

determining an activity level for the audio file based on how often the audio file has been access within the predetermined time period, wherein the activity level is a value that decays over time; and

modifying the metadata for the audio file to include the activity level for the audio file.

10. The method of claim 6, further comprising:

modifying the metadata for the audio file to include user-defined tags linked with concepts from a second set of concepts.

11. The method of claim 6, further comprising:

modifying the metadata for the audio file to include context tags linked with context identifiers, wherein a context identifier identifies non-verbal audio information.

12. A natural language processing device, comprising:

a memory operable to store artificial intelligence (AI)-defined tags linked with a first set of concepts;

a processor operably coupled to the memory, configured to;

receive a set of audio files;

identify concepts within the set of audio files;

determine a usage frequency for each of the identified concepts, wherein the usage frequency indicates how often each of the identified concepts occurs within the set of audio files;

compare the usage frequency for each identified concept to a usage frequency threshold;

generate an AI-defined tag for each identified concept with a usage frequency that is greater than the usage frequency threshold, wherein each AI-defined tag is linked with the corresponding identified concept;

receive an audio file;

modify metadata for the audio file to include AI-defined tags linked with concepts from the first set of concepts;

identify non-verbal audio information present within the audio file;

determine a context tag based on the identified non-verbal audio information present within the audio file, wherein the determined context tag identifies a sound characteristic that is present within the audio file;

modify the metadata for the audio file to include the determined context tag;

analyze the metadata for the audio file to identify tags associated with the audio file;

determine a priority level for the audio file based on the tags associated with the audio file;

determine a data access speed for the audio file based on the determined priority level associated with the audio file;

select a storage location from among a plurality of storage devices based on the determined data access speed; and

send the audio file to the identified storage location.

13. The device of claim 12, wherein:

selecting a storage device type based at least in part on the determined priority level.

14. The device of claim 13, wherein the processor is further configured to modify the metadata for the audio file to include the determined priority level for the audio file.

15. The device of claim 12, wherein the processor is further configured to:

determine how often the audio file has been accessed within a predetermined time period;

determine an activity level for the audio file based on how often the audio file has been access within the predetermined time period, wherein the activity level is a value that decays over time; and

modify the metadata for the audio file to include the activity level for the audio file.