Dynamic event processing

Patent metadata

Field	Value
Publication number	US-2018358006-A1
Application number	US-201715620365-A
Country	US
Kind code	A1
Filing date	Jun 12, 2017
Priority date	Jun 12, 2017
Publication date	Dec 13, 2018
Grant date	—

Abstract

Methods, systems, and computer program products for dispatching an incoming event are described. A scoring stack is accessed, the scoring stack comprising an identity of one or more tasks, each task corresponding to one or more scorable functions. A scorable tree is generated based on the one or more scorable functions corresponding to the one or more tasks of the scoring stack and the incoming event is processed using the scorable tree to generate one or more scores. One or more actions identified in the scorable tree are performed based on the one or more scores.

First claim

What is claimed is:

1 . A method for dispatching an incoming event, comprising:
obtaining the incoming event from a user device, the incoming event being a component of a natural language conversation; accessing a scoring stack using at least one hardware processor, the scoring stack comprising an identity of one or more tasks related to the natural language conversation, each task corresponding to one or more scorable functions; generating, using the least one hardware processor, a scorable tree based on the one or more scorable functions corresponding to the one or more tasks of the scoring stack, the scorable tree configured to evaluate a meaning of the incoming event; processing, using the least one hardware processor, the incoming event using the scorable tree to generate one or more scores; and performing, using the least one hardware processor, one or more actions related to the natural language conversation identified in the scorable tree based on the one or more scores.

2 . The method of claim 1 , wherein the performing the one or more actions is based on event information forwarded to one or more child nodes of the scorable tree, the event information comprising one or more entities associated with the incoming event.

3 . The method of claim 1 , wherein the incoming event is an internal or external event.

4 . The method of claim 1 , further comprising determining a final score at a root node of the scorable tree based on an intermediate scoring event from one or more child nodes of the root node.

5 . The method of claim 4 , wherein the final score comprises a confidence level that ranges from zero to one.

6 . The method of claim 1 , further comprising parsing the incoming event to identify one or more entities.

7 . The method of claim 1 , further comprising deactivating the scoring stack and initializing a second scoring stack to process a divergence from a conversational track of the natural language conversation.

8 . The method of claim 1 , further comprising evaluating a global scorable function based on an assigned status of the global scorable function, the status designating the corresponding global scorable as active or inactive.

9 . The method of claim 1 , further comprising defining a group of global scoreable functions and assigning a priority to the group, the priority used to determine an order of evaluation of the global scorable functions.

10 . The method of claim 1 , further comprising resetting the scoring stack based on an evaluation of a global scorable function.

11 . The method of claim 1 , further comprising appending a stack interruption element to the scoring stack and resuming processing of an element of the scoring stack after processing the stack interruption element.

12 . The method of claim 1 , further comprising updating the scoring stack with an identity of one or more scorable functions that are within scope.

13 . The method of claim 1 , further comprising emptying the scoring stack in response to receiving an indication of a match from one of the scorable functions.

14 . The method of claim 1 , further comprising removing one or more of the one or more tasks from the scoring stack in response to receiving an indication of a match from one of the scorable functions.

15 . An apparatus comprising:
one or more hardware processors; memory to store instructions that, when executed by the one or more hardware processors perform operations comprising: obtaining the incoming event from a user device, the incoming event being a component of a natural language conversation: accessing a scoring stack using at least one hardware processor, the scoring stack comprising an identity of one or more tasks related to the natural language conversation, each task corresponding to one or more scorable functions; generating, using the least one hardware processor, a scorable tree based on the one or more scorable functions corresponding to the one or more tasks of the scoring stack, the scorable tree configured to evaluate a meaning of the incoming event; processing, using the least one hardware processor, the incoming event using the scorable tree to generate one or more scores; and performing, using the least one hardware processor, one or more actions related to the natural language conversation identified in the scorable tree based on the one or more scores.

16 . The apparatus of claim 15 , wherein the performing the one or more actions is based on event information forwarded to one or more child nodes of the scorable tree, the event information comprising one or more entities associated with the incoming event.

17 . The apparatus of claim 15 , the operations further comprising determining a final score at a root node of the scorable tree based on an intermediate scoring event from one or more child nodes of the root node.

18 . The apparatus of claim 15 , the operations further comprising evaluating a global scorable function based on an assigned status of the global scorable function, the status designating the corresponding global scorable as active or inactive.

19 . The apparatus of claim 15 , the operations further comprising deactivating the scoring stack and initializing a second scoring stack to process a divergence from a conversational track of the natural language conversation.

20 . A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform operations comprising:
obtaining the incoming event from a user device, the incoming event being a component of a natural language conversation; accessing a scoring stack using at least one hardware processor, the scoring stack comprising an identity of one or more tasks related to the natural language conversation, each task corresponding to one or more scorable functions; generating, using the least one hardware processor, a scorable tree based on the one or more scorable functions corresponding to the one or more tasks of the scoring stack, the scorable tree configured to evaluate a meaning of the incoming event; processing, using the least one hardware processor, the incoming event using the scorable tree to generate one or more scores; and performing, using the least one hardware processor, one or more actions related to the natural language conversation identified in the scorable tree based on the one or more scores.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Mcconnell Christopher C
• Portnoy William L
• Ickman Steven W
• Shayandeh Shahin
• Taylor John Anthony

Classifications

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• G06F40/295

  Named entity recognition · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F16/3329

  Natural language query formulation · CPC title