System and method for visually searching and debugging conversational agents of electronic devices

US10754885B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10754885-B2
Application numberUS-201916249691-A
CountryUS
Kind codeB2
Filing dateJan 16, 2019
Priority dateNov 27, 2017
Publication dateAug 25, 2020
Grant dateAug 25, 2020

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Embodiments of the inventive system and methods are directed to a computer program that employs a drag-and-drop user interface for debugging dialogue states, tracking dialogue context, understanding dialogue utterances, and managing dialogue sessions of a conversational agent. Each dialogue element is defined in a “node” that can be dragged and dropped into a canvas of the user interface. A debugging window allows a user to visually debug and/or search the code associated with each dialogue element as well as execute each dialogue element of the conversational agent in sequence at a pace that is suitable to the user.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method for debugging a conversational agent of an electronic device, the method comprising: providing a canvas and a debugging window side by side in a graphical user interface (GUI) to allow a user to debug a conversational agent, the conversational agent comprising a router node and one or more sequences of nodes that can be invoked by the router node, wherein each sequence of nodes represents a dialog processing flow mapped to a corresponding intent and zero or more entities, wherein each node is represented by a graphical representation in a canvas of the GUI, wherein each graphical representation is linked to code for the corresponding node in the debugging window; analyzing one or more of the nodes in the canvas based on input received from the user, wherein the debugging window includes a break point graphical representation, which can be dragged and dropped onto a selected one of the nodes displayed in the canvas to set a break point at the selected node; during executing code associated with the conversational agent, suspending executing code associated with the selected node in response to the break point set at the selected node; displaying a search function that enables a global search for one or more characters in the debugging window; responsive to finding the one or more matches to the characters in a text representation of one or more nodes in the debugging window, highlighting the one or more matching characters in the debugging window and highlighting the one or more nodes in the canvas that contain the one or more matching characters; receiving a modification to the text representation that contain the one or more matching characters in the debugging window; and responsive to the modifying the text representation in the debugging window, synchronizing, by the debugging window, the modification between the one or more nodes in the canvas and the debugging window. 2. The method of claim 1 , wherein the breakpoint graphical representation is associated with a break point function for allowing the user to generate a break point anywhere on the sequence of nodes within the canvas, wherein the break point pauses execution of a subsequent node in the sequence. 3. The method of claim 2 , wherein the debugging window further comprises: a continue graphical representation representing a continue function for allowing the user to automatically execute each node in the sequence until the break point is reached; and a step graphical representation representing a step function for allowing the user to execute a current node, and pause prior to execution of a next node in the sequence. 4. The method of claim 1 , wherein the debugging window comprises a stop graphical representation representing a stop function for allowing the user to stop execution of a current node and return to a first node of the sequence. 5. The method of claim 1 , further comprising displaying a search function for allowing the user to search for the one or more characters within a text representation each node in the debugging window. 6. The method of claim 5 , wherein the search function allows a user to search for the characters within a specific field of each node's text representation. 7. The method of claim 1 , wherein synchronizing the modification between the one or more nodes in the canvas and the debugging window further includes changing the one or more nodes and one or more corresponding text representations in the debugging window simultaneously. 8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising: providing a canvas and a debugging window side by side in a graphical user interface (GUI) to allow a user to debug a conversational agent, the conversational agent comprising a router node and one or more sequences of nodes that can be invoked by the router node, wherein each sequence of nodes represents a dialog processing flow mapped to a corresponding intent and zero or more entities, wherein each node is represented by a graphical representation in a canvas of the GUI, wherein each graphical representation is linked to code for the corresponding node in the debugging window; analyzing one or more of the nodes in the canvas based on input received from the user, wherein the debugging window includes a break point graphical representation, which can be dragged and dropped onto a selected one of the nodes displayed in the canvas to set a break point at the selected node; during executing code associated with the conversational agent, suspending executing code associated with the selected node in response to the break point set at the selected node; displaying a search function that enables a global search for one or more characters in the debugging window; responsive to finding the one or more matches to the characters in a text representation of one or more nodes in the debugging window, highlighting the one or more matching characters in the debugging window and highlighting the one or more nodes in the canvas that contain the one or more matching characters; receiving a modification to the text representation that contain the one or more matching characters in the debugging window; and responsive to the modifying the text representation in the debugging window, synchronizing, by the debugging window, the modification between the one or more nodes in the canvas and the debugging window. 9. The machine-readable medium of claim 8 , wherein the breakpoint graphical representation is associated with a break point function for allowing the user to generate a break point anywhere on the sequence of nodes within the canvas, wherein the break point pauses execution of a subsequent node in the sequence. 10. The machine-readable medium of claim 9 , wherein the debugging window comprises: a continue graphical representation representing a continue function for allowing the user to automatically execute each node in the sequence until the break point is reached; and a step graphical representation representing a step function for allowing the user to execute a current node, and pause prior to execution of a next node in the sequence. 11. The machine-readable medium of claim 8 , wherein the debugging window comprises a stop graphical representation representing a stop function for allowing the user to stop execution of a current node and return to a first node of the sequence. 12. The machine-readable medium of claim 8 , wherein the operations further comprise displaying a search function for allowing the user to search for the one or more characters within a text representation each node in the debugging window. 13. The machine-readable medium of claim 12 , wherein the search function allows a user to search for the characters within a specific field of each node's text representation. 14. The machine-readable medium of claim 8 , wherein synchronizing the modification between the one or more nodes in the canvas and the debugging window further includes changing the one or more nodes and one or more corresponding text representations in the debugging window simultaneously. 15. A data processing system, comprising: a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations comprising: providing a canvas and a debugging window side by side in a graphical user interface (GUI) to allow a user to debug a conversational agent, the conversational agent

Assignees

Inventors

Classifications

  • Environments for analysis, debugging or testing of software · CPC title

  • Presentation of query results · CPC title

  • G06F16/34Primary

    Browsing; Visualisation therefor (browsing or visualisation for clustering or classification G06F16/358) · CPC title

  • by tracing the execution of the program · CPC title

  • Debugging of software · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10754885B2 cover?
Embodiments of the inventive system and methods are directed to a computer program that employs a drag-and-drop user interface for debugging dialogue states, tracking dialogue context, understanding dialogue utterances, and managing dialogue sessions of a conversational agent. Each dialogue element is defined in a “node” that can be dragged and dropped into a canvas of the user interface. A deb…
Who is the assignee on this patent?
Baidu Usa Llc
What technology area does this patent fall under?
Primary CPC classification G06F16/34. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Aug 25 2020 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 12 related publications on this page (citations in our corpus or others sharing the same primary CPC).