Method and apparatus for voice recognition unit simulation

• US 9,497,304 B1
• Filed: 12/15/2014
• Issued: 11/15/2016
• Est. Priority Date: 06/07/2007
• Status: Active Grant

• Current Assignee: West Technology Group LLC (West Corporation)
• Original Assignee: West Corporation
• Inventors: Varman, Mahendra, Akhwand, Mahmood S.
• Primary Examiner(s): Gay, Sonia
• Application Number:
  US14/570,498
• Time in Patent Office: 701 Days
• Field of Search: 379/10.02
• US Class Current: 1/1
• CPC Class Codes: G06F 11/3664 Environments for testing or debugging software
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 43/50 Testing arrangements
• CPC Class Codes: H04M 1/24 Arrangements for testing
• CPC Class Codes: H04M 3/2227 Quality of service monitoring
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A call calculator and method thereof used to automate testing of a voice self service platform. The call calculator may have functional logic to calculate an estimated call load. The type of load may be least one of cyclic, peak, burst, choppy, and sustained. The call calculator may use a set of input parameters of an algorithm to calculate the estimated call load, wherein the algorithm may be based on an integral calculus model.

Claims

1. A method for estimating call load using a load simulation of a voice recognition unit, the method comprising:

determining, by a processor communicably coupled to the voice recognition unit;

a number of maximum simultaneous channels for the load simulation;

a duration of a call of expected simultaneous calls for the load simulation;

an active call handling procedure for the load simulation;

a load to timing choice for the load simulation;

a number of the expected simultaneous calls;

a minimum percentage of time that the expected simultaneous calls will be sustained;

a timing to load choice for the load simulation;

a number of the expected simultaneous calls to be placed in a batch of the expected simultaneous calls;

an inter-call duration between the expected simultaneous calls in the batch; and

a batch call duration;

using the determining as a set of input parameters to calculate, by the processor, the estimated call load.

2. The method for estimating call load according to claim 1, further comprising determining by the processor a type of the call load, wherein the type of the call load is at least one of cyclic, peak, burst, choppy, and sustained.

3. The method for estimating call load according to claim 1, wherein the calculating is based on an integral calculus model.

4. The method for estimating call load according to claim 1, wherein a drift for the call is directly proportional to the number of the expected simultaneous calls to be placed.

5. The method for estimating call load according to claim 1, wherein the active call handling procedure is one of a previous call hang-up and a previous call skip, and wherein the previous call hang-up is a decision whether to hang a previous call or not, when the previous call in a selected channel is still busy and a next call in the selected channel is ready to be generated.

6. The method for estimating call load according to claim 5, wherein the previous call skip is a decision whether to skip a parameter of times to generate the next call before a hang-up.

7. The method for estimating call load according to claim 1, wherein the load to timing choice is a decision whether to determine data points for given load details.

8. The method for estimating call load according to claim 1, wherein the timing to load is a decision whether to determine data points for call generation timing data.

9. A call calculator comprising a processor operable to execute instructions to calculate an estimated call load, using a load simulation of a voice recognition unit, based on a set of parameters, the parameters comprising:

a number of maximum simultaneous channels for a load simulation;

a duration of a call of expected simultaneous calls for the load simulation;

an active call handling procedure for the load simulation;

a load to timing choice for the load simulation;

a number of the expected simultaneous calls;

a minimum percentage of time that the expected simultaneous calls will be sustained;

a timing to load choice for the load simulation;

a number of the expected simultaneous calls to be placed in a batch of the expected simultaneous calls;

an inter-call duration between the expected simultaneous calls in the batch; and

a batch call duration;

wherein the processor calculates the estimated call load based on the set of parameters.

10. The call calculator for estimating call load according to claim 9, wherein the instructions include an algorithm based on an integral calculus model.

11. The call calculator for estimating call load according to claim 10, further comprising at least one of a memory operable to save the estimated call load and an outcome progress monitor operable to display a progress of execution of the instructions.

12. A non-transitory machine readable storage device having stored thereon a set of program instructions executable by the machine, the instructions when executed estimating call load, using a load simulation of a voice recognition unit, the instructions utilizing input parameters of:

a number of maximum simultaneous channels for the load simulation;

a duration of a call of expected simultaneous calls for the load simulation;

an active call handling procedure for the load simulation;

a load to timing choice for the load simulation;

a number of the expected simultaneous calls;

a minimum percentage of time that the expected simultaneous calls will be sustained;

a timing to load choice for the load simulation;

a number of the expected simultaneous calls to be placed in a batch of the expected simultaneous calls;

an inter-call duration between the expected simultaneous calls in the batch; and

a batch call duration.

13. The non-transitory machine readable storage device according to claim 12, comprising an input parameter of a type of the call load, wherein the type of the call load is at least one of cyclic, peak, burst, choppy, and sustained.

14. The non-transitory machine readable storage device according to claim 12, wherein the algorithm is based on an integral calculus model.

15. The non-transitory machine readable storage device according to claim 12, wherein a drift for the call is directly proportional to the number of the expected simultaneous calls to be placed.

16. The non-transitory machine readable storage device according to claim 12, wherein the active call handling procedure is one of a previous call hang-up and a previous call skip, and wherein the previous call hang-up is a decision whether to hang a previous call or not, when the previous call in a selected channel is still busy and a next call in the selected channel is ready to be generated.

17. The non-transitory machine readable storage device according to claim 16, wherein the previous call skip is a decision whether to skip a parameter of times to generate the next call before a hang-up.

18. The non-transitory machine readable storage device according to claim 12, wherein the load to timing choice is a decision whether to determine data points for given load details.

19. The non-transitory machine readable storage device according to claim 12, wherein the timing to load is a decision whether to determine data points for call generation timing data.