Distributed coordinated system and process which transforms data into useful information to help a user with resolving issues

• US 9,667,786 B1
• Filed: 10/07/2014
• Issued: 05/30/2017
• Est. Priority Date: 10/07/2014
• Status: Active Grant

• Current Assignee: IPsoft Incorporated
• Original Assignee: IPsoft Incorporated
• Inventors: Dube, Chetan
• Primary Examiner(s): Matar, Ahmad F
• Assistant Examiner(s): Pope, Kharye
• Application Number:
  US14/508,495
• Time in Patent Office: 966 Days
• Field of Search: 379265, 379266, 379 8801, 704 9, 704 2, 704257, 704275, 704 4, 704E15018
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/408 Customer-specific call routing plans
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

One embodiment relates to a computerized process for assisting a user in obtaining help from a help desk comprising a plurality of steps. One step can involve connecting the user with a computer network. Another step involves presenting the user with a plurality of questions. Another step involves analyzing a plurality of answers provided by the user by comparing said plurality of answers with a plurality of answers stored in a database. Another step involves determining using a microprocessor whether to connect a user with a live agent and connecting the user with a live agent by switching to a telephone network after determining via a predetermined score that the user needs further assistance. Ultimately, through a series of steps the system becomes more agile and intelligent thereby becoming a dynamic system which can change the process for assisting a user based upon the satisfaction of the user.

Claims

1. A computerized process implemented within a call center for assisting a user in obtaining help with issues comprising the following steps:

receiving information provided by the user in natural language, the information comprises at least three words;

determining a statement type for the information provided by the user, the statement type is one of either declarative, interrogative, or imperative;

transforming information received from the user into a first subroutine based on the statement type and a relationship model, the relationship model includes an indication of tying words in the information;

retrieving from memory a second subroutine based on whether the information is declarative, interrogative, or imperative;

for each step in the first and second subroutines, if a current step in the first subroutine matches a current step in the second subroutine, execute the current step in the first subroutine by outputting a natural language response to the user, wherein the natural language response includes at least a portion of the information provided by the user and proceed to the next step in both the first and second subroutines, otherwise i) for the current step in the first subroutine and the current step in the second subroutine that have identical meaning, merge the current step in the first subroutine and the current step in the second subroutine and replace the current step in the second subroutine with the merged step and ii) connect the user with a live agent via a telephone network or internet to establish a two way communication between the user and the live agent.

2. The process as in claim 1 further comprising the step of determining a score for efficiency in resolving a user'"'"'s issue based upon a time period and number of questions and answers necessary to resolve the issue.

3. The process as in claim 2, wherein said step of determining a score includes determining a score based upon emotional reaction of the user.

4. The process as in claim 3, further comprising the step of retaining said subroutine for resolving an issue by presenting said subroutine on a computer screen when said issue is presented by said user.

5. The process as in claim 4, further comprising the step of using said microprocessor to modify a subroutine path by recording either a different step in said path or adding additional steps in said path after connecting the user with the live agent to form a transformed subroutine.

6. The process as in claim 5, further comprising the steps of providing an index which is used by said microprocessor to determine whether the sentence is a declarative sentence, an interrogative sentence or an imperative sentence.

7. The process as in claim 5, further comprising the steps of providing a pre-set subroutine, which is used by said microprocessor to determine a best course of action in assisting a user in resolving an issue by matching said pre-set subroutine with said transformed subroutine based upon information input from said user.

8. The process as in claim 5, wherein said step of determining a sentence type comprises using a neural cognition device comprising a microprocessor to determine a type of sentence issued by the user.

9. The process as in claim 8, wherein said step of determining a type of sentence issued by the user comprises using a semantic role understanding machine to determine a type of sentence.

10. The process as in claim 8, further comprising the step of using a first order logic to answer any interrogative question presented by the user.

11. The process as in claim 8, further comprising the step of determining a known lemma of an imperative statement and then selectively invoking an invocation service based upon a type of lemma.

12. The process as in claim 8 further comprising the step of invoking a dialog management service to provide answers to users based upon the types of sentences input by the user wherein said dialog management service provides natural language statements to users.

13. The process of claim 1 wherein the natural language response also includes at least a portion of the relationship model.