Natural language text analytics

• US 8,473,498 B2
• Filed: 08/02/2011
• Issued: 06/25/2013
• Est. Priority Date: 08/02/2011
• Status: Active Grant

• Current Assignee: Tom H.C. Anderson
• Original Assignee: Tom H.C. Anderson
• Inventors: Anderson, Tom H. C.
• Primary Examiner(s): THAI, HANH B
• Application Number:
  US13/196,426
• Publication Number:
  US 20130036126A1
• Time in Patent Office: 693 Days
• Field of Search: 707748-750, 707/754
• US Class Current: 707/748
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

A method of text analytics includes filtering a plurality of unfiltered records having unstructured data into at least a first group and a second group. The first group and said second group each include at least two records and the first group is different than the second group. The method includes determining a first proportion of occurrence for a term by comparing a first number of records having at least one occurrence of the term in the first group to a first total number of records in the first group, determining a second proportion of occurrence for the term by comparing a second number of records having at least one occurrence of the term in said second group to a second total number of records in the second group, and comparing the first proportion of occurrence to the second proportion of occurrence to yield a resultant comparison occurrence.

Claims

1. A method comprising:

using a computer having a processor, and a memory having computer instructions to cause the processor to perform steps, including;

filtering a plurality of unfiltered records having unstructured data according to at least one criterion into at least a first group and a second group, said first group and said second group each comprise at least two records, wherein said first group is different than said second group, the groups being stored in the memory;

determining a first proportion of occurrence for a term by comparing a first number of records having at least one occurrence of said term in said first group to a first total number of records in said first group;

determining a second proportion of occurrence for said term by comparing a second number of records to determine a number of occurrences of said term in said second group to a second total number of records in said second group;

determining a first standard error range according to said first proportion of occurrence of said term, a first total number of records within said first group, and a level of confidence;

determining a second standard error range according to said second proportion of occurrence of said term, a second total number of records within said second group, and said level of confidence; and

indicating, via an overlap identifier, when said first standard error range and said second error range overlap.

2. The method of claim 1, wherein said plurality of unfiltered records comprise at least 3 records, and wherein at least one record of said first group is different than at least one record of second group.

3. The method of claim 1, wherein said plurality of unfiltered records comprise at least 4 records, and wherein said at least two records of said first group are different than said at least two records of said second group.

4. The method of claim 1, further comprising

comparing said first proportion of occurrence to said second proportion of occurrence to yield a resultant comparison occurrence.

5. The method of claim 1, wherein said term comprises at least one selected from the group consisting of:

an alphanumeric character, a symbol, and any combination thereof.

6. The method of claim 1, wherein said at least one criterion is selected from the group consisting of:

a time, a gender, and an age.

7. A non-transitory storage medium comprising:

instructions that are readable by a processor and cause said processor to;

filter a plurality of unfiltered records having unstructured data according to at least one criterion into at least a first group and a second group, said first group and said second group each comprise at least two records, wherein said first group is different than said second group;

determine a first proportion of occurrence for a term by comparing a first number of records having at least one occurrence of said term in said first group to a first total number of records in said first group;

determine a second proportion of occurrence for said term by comparing a second number of records to determine a number of occurrences of said term in said second group to a second total number of records in said second group;

compare said first proportion of occurrence to said second proportion of occurrence to yield a resultant comparison occurrences;

determine a first standard error range according to said first proportion of occurrence of said term, a first total number of records within said first group, and a level of confidence;

determine a second standard error range according to said second proportion of occurrence of said term, a second total number of records within said second group, and said level of confidence; and

indicate, via an overlap identifier, when said first standard error range and said second error range overlap.

8. A method comprising:

using a computer having a processor and a memory having computer instructions to cause the processor to perform steps, including;

allocating each record of a plurality of records a numerical value according to a sentiment to yield a plurality of sentiment records;

filtering said plurality of sentiment records according to a criterion to yield filtered records;

determining a sentiment value for a term according to a number of said filtered records having said term and said numerical value, wherein said sentiment value is selected from the group consisting of;

a mean, a variance and a deviation; and

determining a proportion of occurrence of a term by comparing a number of said filtered records having at least one occurrence of said term to a total number of records in said filtered records.

9. The method of claim 8, wherein said filtering further comprises filtering said plurality of sentiment records according to one criterion selected from the group consisting of:

said numerical value, a time, a gender, and an age.

10. A non-transitory storage medium comprising:

instructions that are readable by a processor and cause said processor to;

allocate each record of a plurality of records a numerical value according to a sentiment to yield a plurality of sentiment records;

filter said plurality of sentiment records according to a criterion to yield filtered records;

determine a sentiment value for a term according to a number of said filtered records having said term and said numerical value, wherein said sentiment value is selected from the group consisting of;

a mean, a variance and a deviation; and

determining a proportion of occurrence of a term by comparing a number of said filtered records having at least one occurrence of said term to a total number of records in said filtered records.