Call handoff initiation in hybrid networks

• US 9,510,251 B2
• Filed: 12/31/2013
• Issued: 11/29/2016
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Sidhu, Gursharan S, Kuehnel, Thomas, Salapaka, Rao, Soni, Vishal, Chandra, Ranveer, Jafry, Mansoor, Desai, Anish, Astavans, Ruchir, Khan, Humayun, Miller, John Mark
• Primary Examiner(s): Bhattacharya, Sam
• Application Number:
  US14/144,668
• Publication Number:
  US 20150189556A1
• Time in Patent Office: 1,064 Days
• Field of Search: 455436-442
• US Class Current: 1/1
• CPC Class Codes: H04B 17/318 Received signal strength
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42
• CPC Class Codes: H04M 7/122 where the PSTN/ISDN access is used as an access to networks other than PSTN/ISDN access arrangements to networks other than PSTN/ISDN H04M7/0066; access arrangements to public data networks H04L12/2856
• CPC Class Codes: H04W 36/008375 based on historical data
• CPC Class Codes: H04W 36/1446 wherein at least one of the networks is unlicensed
• CPC Class Codes: H04W 40/26 for hybrid routing by combining proactive and reactive routing

Abstract

A continual learning process is applied to a class of risk estimate-based algorithms and associated risk thresholds used for deciding when to initiate a handoff between different types of network connections that are available to a mobile device having telephony functionality. The process is implemented as a virtuous loop providing ongoing tuning and adjustment to improve call handoff algorithms and risk thresholds so that handoffs can be performed with the goals of minimizing dropped calls and unacceptable degradation in call quality as well as avoiding premature handoffs. Device characteristics, environmental context, connection measurements, and outcomes of call handoff decisions are crowd-sourced from a population of mobile devices into a cloud-based handoff decision enabling service. The service evaluates potentially usable handoff decision algorithms and risk thresholds against archived crowd-sourced data to determine how they would have performed in real world situations and delivers improved algorithms and risk thresholds to the mobile devices.

Claims

1. A method for improving decision making for handoff of calls between different connection types, the calls carried on a hybrid network comprising loosely coupled network portions, the network portions including at least a mobile operator network and a VoIP (Voice over Internet Protocol) network, the method comprising the steps of:

implementing a virtuous learning loop between a handoff decision enabling service and each of a plurality of mobile devices, the virtuous learning loop being configured to provide feedback from the mobile devices to the handoff decision enabling service;

receiving crowd-sourced data from the mobile devices, the crowd-sourced data comprising outcomes for past attempts at handoffs for calls and parameters associated with each handoff outcome, the parameters including at least one of environmental context of a mobile device in which a handoff was attempted or measured characteristics of network connections available to the mobile device prior to the attempted handoff;

evaluating a call handoff algorithm to determine the call handoff algorithm'"'"'s performance under conditions described by the crowd-sourced data;

evaluating a risk threshold to determine the risk threshold'"'"'s performance under conditions described by the crowd-sourced data; and

delivering the handoff algorithm or risk threshold to the mobile devices over the virtuous learning loop.

2. The method of claim 1 further including a step of operating the handoff decision enabling service as a part of the VoIP network.

3. The method of claim 2 further including a step of aggregating crowd-sourced data from the plurality of mobile devices in which the crowd-sourced data is collected on a mobile device over a pre-determined time interval that begins at a start time prior to a handoff attempt and ends at an end time after the handoff attempt.

4. The method of claim 1 in which the hybrid network further includes a PSTN (Public Switched Telephone Network) portion.

5. The method of claim 1 in which a handoff outcome includes one of successful handoff, dropped call, perceptible interruption, or premature handoff.

6. The method of claim 1 further including a step of utilizing a variety of types of information in the crowd-sourced data, the crowd-sourced data types including one of mobile device characteristics, connection measurements, call-related measurements, or environmental context data.

7. The method of claim 6 in which the connection measurements comprise measurements of Wi-Fi connection characteristics or measurements of cellular connection characteristics.

8. The method of claim 6 in which the call-related measurements comprise measurements of media stack parameters or measurements of transport stack parameters.

9. The method of claim 1 further including a step of optimizing the handoff algorithm or risk threshold to a given environmental context for a mobile device, the environmental context including one of a time of day or day of week in which a handoff is being attempted, a location of the mobile device at which the handoff is being attempted, or a type of network connection to which a call is being handed off.

10. A mobile device, comprising:

at least one processor; and

memory operatively coupled to the processor and storing computer-readable instructions that, when executed by the at least one processor, implement call handoff initiation components that perform a method comprising the steps of;

measuring characteristics of each of multiple connections to a hybrid network having loosely coupled network portions including a mobile operator network, and a VoIP (Voice over Internet Protocol) network, each of the multiple connections being of a different type,

collecting data describing an environmental context in which a call handoff between the multiple connections is attempted,

sending measured connection characteristics and environmental context data to a handoff decision enabling service as a part of data crowd-sourced from a population of mobile devices having access to the hybrid network to make calls;

receiving a handoff decision algorithm or a risk threshold from the handoff decision enabling service, the handoff decision algorithm and risk threshold being generated in view of the crowd-sourced data, and

running the received handoff decision algorithm or applying the received risk threshold when attempting a call handoff.

11. The mobile device of claim 10 in which the method further includes a step of sending characteristics of the mobile device to the handoff decision enabling service, the characteristics including at least one of mobile device type, mobile device model, or operating system instantiated on the mobile device.

12. The mobile device of claim 10 in which the received handoff decision algorithm is optimized to a particular environmental context and the handoff decision algorithm is run or the risk threshold applied when the particular environmental context is applicable.

13. The mobile device of claim 10 in which the handoff decision enabling service is cloud-based.

14. The mobile device of claim 10 in which the handoff decision enabling service is implemented at least in part in the VoIP network portion.