Candidate matching using algorithmic analysis of candidate-authored narrative information

• US 7,813,917 B2
• Filed: 06/22/2005
• Issued: 10/12/2010
• Est. Priority Date: 06/22/2004
• Status: Active Grant

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Hoshiko LLC (Raoul Management LLC)
• Inventors: Shuster, Gary Stephen
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US11/159,484
• Publication Number:
  US 20060080084A1
• Time in Patent Office: 1,938 Days
• Field of Search: 704/9, 705/1, 705/5, 706/45, 706/54
• US Class Current: 704/9
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06Q 10/00 Administration; Management

Abstract

A method and system for candidate matching, such as used in match-making services, assesses narrative responses to measure candidate qualities. A candidate database includes self-assessment data and narrative data. Narrative data concerning a defined topic is analyzed to determine candidate qualities separate from topical information. Candidate qualities thus determined are included in candidate profiles and used to identify desirable candidates.

Claims

1. A method, comprising:

initiating transmission of a request for a personally-authored narrative relating to a defined topic to a computing device;

receiving narrative information generated by a user from the computing device in response to the request;

storing the narrative information in a computer readable medium;

receiving self-assessment data describing at least one personal quality claimed by the user from the computing device;

storing the self-assessment data in a computer readable medium;

determining quality ratings for respective personal qualities claimed by the user based on comparisons of the respective claimed personal qualities to corresponding respective probable personal qualities that are determined based on the narrative information generated by the user; and

storing the quality ratings with data identifying the user in a candidate database,

wherein at least some of the method is performed by a suitably configured computing system comprising one or more computing devices.

2. The method of claim 1, further comprising ranking information describing the user relative to information describing one or more other users based on one or more of the quality ratings.

3. The method of claim 1, wherein a first probable personal quality comprises a probable educational level of the user and a corresponding first claimed personal quality comprises a claimed educational level of the user.

4. The method of claim 1, wherein a first probable personal quality comprises a probable personal age of the user and a corresponding first claimed personal quality comprises a claimed personal age of the user.

5. The method of claim 1, wherein a first probable personal quality comprises a probable personal gender of the user and a corresponding first claimed personal quality comprises a claimed personal gender of the user.

6. The method of claim 1, wherein the defined topic is randomly selected from a plurality of defined topics.

7. The method of claim 1, wherein the narrative information comprises audio data, and the method further comprises converting the audio data to textual data.

8. The method of claim 1, further comprising receiving a query for selecting candidates from the candidate database possessing a particular personal quality.

9. The method of claim 8, further comprising initiating transmission of query results comprising a quality rating associated with the particular personal quality.

10. The method of claim 8, further comprising initiating transmission of query results comprising a list of candidates ranked according to associated quality ratings for the particular personal quality each indicating whether the particular personal quality is accurately claimed by each respective candidate.

11. The method of claim 8, further comprising initiating transmission of query results comprising a list of candidates selected on the basis of associated quality ratings for the particular personal quality each indicating whether the particular personal quality is accurately claimed by each respective candidate.

12. A computing system for candidate matching, comprising:

a computer readable memory;

a network interface; and

one or more modules configured for execution on a processor in order to cause the computing system to

receive narrative information generated by a user;

receive self-assessment data describing a self-reported attribute of the user;

determine a metric based on the narrative information, wherein the metric indicates a probable attribute of the user;

determine a quality rating for the self-reported attribute indicative of a likelihood that the self-reported attribute is accurate based on a comparison of the metric and the self-reported attribute; and

store the quality rating associated with the attribute of the user in a candidate database.

13. The system of claim 12, wherein the processor is further configured to execute one or more modules in order to cause the computing system to rank information describing the user relative to information describing other users based on the metric.

14. The system of claim 12, wherein the processor is further configured to execute one or more modules in order to cause the computing system to

randomly select a topic for the narrative information from a plurality of defined topics;

and

initiate transmission of the topic to a computing device associated with the user.

15. The system of claim 12, wherein the self-reported attribute is a personal age and the probable attribute is a probable personal age of the user.

16. The system of claim 12, wherein the at least one self-reported attribute is a personal gender and the probable attribute is a probable personal gender of the user.

17. The system of claim 12, wherein the self-reported attribute is an educational level and the probable attribute is a probable education level of the user.

18. The system of claim 12, wherein the narrative information comprises audio data, and wherein the processor is further configured to execute one or more modules in order to cause the computing system to convert the audio data to textual data.

19. The system of claim 12, wherein the processor is further configured to execute one or more modules in order to cause the computing system to receive a query for selecting candidates possessing the self-reported attribute from the candidate database.

20. The system of claim 19, wherein the processor is further configured to execute one or more modules in order to cause the computing system to initiate transmission of query results in response to receiving the query, the query results comprising the quality rating.

21. The system of claim 19, wherein the processor is further configured to execute one or more modules in order to cause the computing system to initiate transmission of query results in response to receiving the query, the query results comprising a list of candidates ranked according to associated quality ratings of the respective candidates.

22. The system of claim 19, wherein the processor is further configured to execute one or more modules in order to cause the computing system to initiate transmission of query results in response to receiving the query, the query results comprising a list of candidates selected on the basis of associated quality ratings of the respective candidates.

23. A non-transitory computer readable medium having computer-executable instructions stored thereon, the computer-executable instructions readable by a computing system comprising one or more computing devices, wherein the computer-executable instructions are executable on the computing system in order to cause the computing system to perform operations comprising:

receiving narrative information generated by a user;

generating a first metric based on the narrative information;

receiving a first self-reported attribute from the user; and

generating a first quality indicator indicative of a likelihood that the first self-reported attribute is accurate based on a comparison of the first metric to the first self-reported attribute.

24. The non-transitory computer readable medium of claim 23, wherein the operations further comprise:

generating a second metric based on the narrative information;

receiving a second self-reported attribute from the user; and

generating a second quality indicator indicative of a likelihood of the second self-reported attributed being accurate based on a comparison of the second metric to the second self-reported attribute.

25. The non-transitory computer readable medium of claim 23, wherein the first metric comprises an indication of a probability that the user has a specific attribute.

26. The non-transitory computer readable medium of claim 25, wherein the first metric comprises a level-of-confidence indicator.