Granted Patent B2

US 12,670,196 · App. 17/889,100 · Granted Jun 30, 2026

Inventor: Roman Olshansky (Plymouth, MN)

Assignee: On Time Staffing Inc.

G06F16/335G06F16/3335G06F16/387G06F16/735G06F40/279G10L15/197G10L15/26G10L25/51

Abstract

Claims (108)

1 . A method for sorting data, comprising:

a. receiving, at a non-transitory computer memory, criteria data, wherein the criteria data comprises:

i. textual criteria data and

ii. defined field criteria data, wherein the defined field criteria data comprises:

first defined field criteria data, and

second defined field criteria data;

b. receiving, at the non-transitory computer memory, candidate data, wherein the candidate data comprises:

i. textual candidate data;

ii. defined field candidate data, wherein the defined field candidate data comprises:

first defined field candidate data, and

second defined field candidate data;

iii. audio data of a response to a first prompt and a second prompt, wherein the audio data comprises:

a first portion audio data of the response to the first prompt, and

a second portion audio data of the response to the second prompt;

c. storing the candidate data in a candidate profile in a candidate database;

d. evaluating the candidate data, by a processor, wherein evaluating the candidate data comprises:

i. comparing the textual criteria data with the textual candidate data to determine a first analysis result for the candidate data;

ii. comparing the defined field criteria data with the defined field candidate data to determine a defined field analysis result for the candidate data, wherein comparing defined field criteria data with defined field candidate data comprises:

comparing the first defined field criteria data to the first defined field candidate data, and

comparing the second defined field criteria data to the second defined field candidate data;

iii. comparing the audio data to a database of successfully-selected candidates to determine an N-gram analysis result for the candidate data, wherein comparing the audio data to the database of successfully-selected candidates comprises:

creating a first textual transcript of the audio data for the first portion audio data;

removing stop words from the first textual transcript;

creating a first N-gram data set of the candidate data based on the first textual transcript with stop words removed;

comparing the first N-gram data set of the candidate data to a first N-gram data set of the successfully-selected candidates, wherein the first N-gram data set of the successfully-selected candidates is determined by responses of successfully-selected candidates to the first prompt;

creating a second textual transcript of the audio data for the second portion audio data;

removing stop words from the second textual transcript;

creating a second N-gram data set of the candidate data based on the second textual transcript with stop words removed;

comparing the second N-gram data set of the candidate data to a second N-gram data set of the successfully-selected candidates, wherein the second N-gram data set of the successfully-selected candidates is determined by responses of successfully-selected candidates to the second prompt; and

compiling the comparison of the first N-gram data set and the comparison of the second N-gram data set to determine the N-gram analysis result for the audio data;

iv. compiling the first analysis result, the direct field analysis result and the N-gram analysis result into an overall analysis result;

e. sorting the candidate data within a plurality of other candidate data using the overall analysis result.

2 . The method of claim 1 , further comprising: displaying the sorted candidate data on a user interface to the user.

3 . The method of claim 1 , further comprising sorting the candidate data into one of three groups based on the overall analysis result.

4 . The method of claim 1 , wherein the first analysis results for the candidate data further comprises a distance analysis between geographical data in the criteria data and geographical data in the textual candidate data.

5 . The method of claim 1 , wherein the candidate data further comprises video data of the candidate responding to the first prompt and the second prompt, wherein the video data is recorded simultaneously with the audio data.

6 . The method of claim 1 , wherein the second portion audio data was recorded prior to the first portion audio data.

7 . The method of claim 1 , further comprising removing low-value words from the first N-gram data set, and the second N-gram data set,

wherein after removing low-value words from the first N-gram data set and the second N-gram data set, only nouns, adjectives, verbs, and adverbs remain in the first N-gram data set and the second N-gram data set.

8 . The method of claim 1 , wherein compiling the first analysis result, the direct field analysis result, and the N-gram analysis results comprises weighting the first analysis result more than the direct field analysis result and the N-gram analysis result.

9 . The method of claim 8 , wherein compiling the first analysis result, the direct field analysis result, and the N-gram analysis results comprises weighting the direct field analysis result more than the N-gram analysis result.

10 . The method of claim 1 , wherein the candidate data comprises an initial first portion audio data and a secondary first portion audio data, wherein both the initial first portion audio data and the secondary first portion audio data are of responses to the first prompt.

11 . The method of claim 10 , further comprising selecting one of the initial first portion audio data or the secondary first portion audio data for creating the first textual transcript.

12 . The method of claim 10 , wherein comparing the first N-gram data set of the candidate data to a first N-gram data set of the successfully-selected candidates comprises:

comparing a first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidates and comparing a first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidates.

13 . The method of claim 12 , wherein compiling the comparison of the first N-gram data set and the comparison of the second N-gram data set to determine the N-gram analysis result for the audio data comprises:

determining a similarity value of the comparison of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidates and determining a similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidates.

14 . The method of claim 13 , further comprising:

maintaining the initial first portion audio data for the N-gram analysis result when the similarity value of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidate is greater than the similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidate, or

maintaining the secondary first portion audio data for the N-gram analysis result when the similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidate is greater than the similarity value of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidate; and

wherein the maintained first portion audio data is incorporated into the compilation of the first analysis result, the direct field analysis result and the N-gram analysis result into the overall analysis result.

15 . A method for sorting data, comprising:

a. receiving, at a non-transitory computer memory, criteria data;

b. receiving, at the non-transitory computer memory, candidate data, wherein the candidate data comprises audio data responding to a first prompt and a second prompt, wherein the audio data comprises:

a first portion audio data responding to the first prompt, and

a second portion audio data responding to the second prompt;

c. storing the candidate data in a candidate profile in a candidate database;

d. evaluating the candidate data, by a processor, wherein evaluating the candidate data comprises:

i. comparing the audio data to a database of successfully-selected candidates to determine an N-gram analysis result for the candidate data, wherein comparing the audio data to the database of successfully-selected candidates comprises:

creating a first textual transcript of the audio data for the first portion audio data;

removing stop words from the first textual transcript;

creating a first N-gram data set based on the first textual transcript with stop words removed;

comparing the first N-gram data set of the candidate data to a first N-gram data set of the successfully-selected candidates, wherein the first N-gram data set of the successfully-selected candidates is determined by responses of successfully-selected candidates to the first prompt;

creating a second textual transcript of the audio data for the second portion audio data;

removing stop words from the first textual transcript;

creating a second N-gram data set based on the second textual transcript with stop words removed;

comparing the second N-gram data set of the candidate data to a second N-gram data set of the successfully-selected candidates, wherein the second N-gram data set of the successfully-selected candidates is determined by responses of successfully-selected candidates to the second prompt; and

compiling the comparison of the first N-gram data set and the comparison of the second N-gram data set determine the N-gram analysis result for the audio data;

e. sorting the candidate data within a plurality of other candidate data using the N-gram analysis result.

16 . The method of claim 15 , wherein the candidate data comprises an initial first portion audio data and a secondary first portion audio data, wherein both the initial first portion audio data and the secondary first portion audio data are of responses to the first prompt.

17 . The method of claim 16 , wherein comparing the first N-gram data set of the candidate data to a first N-gram data set of the successfully-selected candidates comprises:

comparing a first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidates and comparing a first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidates.

18 . The method of claim 17 , wherein compiling the comparison of the first N-gram data set and the comparison of the second N-gram data set to determine the N-gram analysis result for the audio data comprises:

determining a similarity value of the comparison of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidates and determining a similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidates,

maintaining the initial first portion audio data for the N-gram analysis result when the similarity value of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidate is greater than the similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidate, or maintaining the secondary first portion audio data for the N-gram analysis result when the similarity value of the first N-gram data set of the secondary first portion audio data with the first N-gram data set of the successfully-selected candidate is greater than the similarity value of the first N-gram data set of the initial first portion audio data with the first N-gram data set of the successfully-selected candidate; and

wherein the maintained first portion audio data is incorporated into the compilation of the N-gram analysis result.

19 . A method of populating a successfully-selected candidate database for a first type of open opportunity, comprising:

a. receiving, at a non-transitory computer memory, criteria data from a user regarding an open opportunity of the first type;

b. receiving, at the non-transitory computer memory, first candidate data, wherein the first candidate data comprises geographical location data, and audio data of a first candidate responding to a first prompt and a second prompt, wherein the audio data comprises:

i. a first portion audio data of the first candidate responding to the first prompt, and

ii. a second portion audio data of the first candidate responding to the second prompt;

c. storing first candidate data in a first candidate profile in a candidate database;

d. receiving, by a processor, an indication that the first candidate was selected for the open opportunity;

e. saving the first candidate data in a successfully-selected candidate database for open opportunities of the first type, wherein the first candidate data comprises:

i. a first N-gram data set; wherein the first N-gram data set is created by:

creating a first textual transcript of the audio data for the first portion audio data;

removing stop words from the first textual transcript; and

forming a plurality of N-grams based on the first textual transcript with stop words removed, wherein the first N-gram data set comprises the plurality of N-grams; and

ii. a second N-gram data set; wherein the second N-gram data set is created by:

creating a second textual transcript of the audio data for the second portion audio data;

removing stop words from the second textual transcript; and

forming a plurality of N-grams based on the second textual transcript with stop words removed, wherein the first N-gram data set comprises the plurality of N-grams.

20 . The method of claim 19 , further comprising:

a. receiving, at a non-transitory computer memory, criteria data from a second user regarding a second open opportunity of the first type;

b. receiving, at the non-transitory computer memory, second candidate data, wherein the second candidate data comprises geographical location data, and audio data of a second candidate responding to the first prompt and the second prompt, wherein the audio data comprises:

i. a first portion audio data of the second candidate responding to the first prompt, and

ii. a second portion audio data of the second candidate responding to the second prompt;

c. storing second candidate data in a second candidate profile in the candidate database;

d. receiving, by the processor, an indication that the second candidate was selected for the second open opportunity;

e. saving the second candidate data in the successfully-selected candidate database for open opportunities of the first type, wherein the second candidate data comprises:

i. a first N-gram data set; wherein the first N-gram data set is created by:

creating a first textual transcript of the audio data for the first portion audio data;

removing stop words from the first textual transcript; and

forming a plurality of N-grams based on the first textual transcript with stop words removed, wherein the first N-gram data set comprises the plurality of N-grams; and

ii. a second N-gram data set; wherein the second N-gram data set is created by:

creating a second textual transcript of the audio data for the second portion audio data;

removing stop words from the second textual transcript; and

forming a plurality of N-grams based on the second textual transcript with stop words removed, wherein the first N-gram data set comprises the plurality of N-grams.

Assignments (1)

Continuity (2)

References Cited (400)