Interpretability of deep reinforcement learning models in assistant systems
US-11715042-B1 · Aug 1, 2023 · US
Leveraging knowledge records for chatbot local search
US2023087896A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2023087896-A1 |
| Application number | US-202117483161-A |
| Country | US |
| Kind code | A1 |
| Filing date | Sep 23, 2021 |
| Priority date | Sep 23, 2021 |
| Publication date | Mar 23, 2023 |
| Grant date | — |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
At least one knowledge source for use in updating a first problem-solution data set can be selected. From data provided by the at least one knowledge source, a plurality of dialogs can be automatically generated. Existing dialogs in the first problem-solution data can be updated set using the plurality of dialogs that are generated.
First claim
Opening claim text (preview).
What is claimed is: 1 . A method, comprising: selecting at least one knowledge source for use in updating a first problem-solution data set; from data provided by the at least one knowledge source, automatically generating, using a processor, a plurality of dialogs; and updating existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated. 2 . The method of claim 1 , further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is a second intent in the existing dialogs that is the same or similar to the first intent, modifying the existing dialogs for the first intent by adding a new dialog to the existing dialogs or changing a dialog already contained in the existing dialogs. 3 . The method of claim 1 , further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is not a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set the first intent and at least one dialog for the first intent. 4 . The method of claim 1 , further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set entities for the first intent. 5 . The method of claim 1 , further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is not a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set the first intent and at least one entity for the first intent. 6 . The method of claim 1 , further comprising: generating a second problem-solution data set from intents and examples translated from the data provided by the at least one knowledge source, the second problem-solution data set comprising the intents translated from the data provided by the at least one knowledge source and the plurality of dialogs generated from the data provided by the at least one knowledge source, wherein the second problem-solution data set is used to update the existing dialogs in the first problem-solution data. 7 . The method of claim 1 , further comprising: adding to the first problem-solution data set the plurality of dialogs generated from the data provided by the at least one knowledge source as generated dialogs. 8 . A system, comprising: a processor programmed to initiate executable operations comprising: selecting at least one knowledge source for use in updating a first problem-solution data set; from data provided by the at least one knowledge source, automatically generating a plurality of dialogs; and updating existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated. 9 . The system of claim 8 , the executable operations further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is a second intent in the existing dialogs that is the same or similar to the first intent, modifying the existing dialogs for the first intent by adding a new dialog to the existing dialogs or changing a dialog already contained in the existing dialogs. 10 . The system of claim 8 , the executable operations further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is not a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set the first intent and at least one dialog for the first intent. 11 . The system of claim 8 , the executable operations further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set entities for the first intent. 12 . The system of claim 8 , the executable operations further comprising: selecting a first intent translated from the data provided by the knowledge source; and determining whether there is a second intent in the existing dialogs that is a same or similar to the first intent; wherein the updating the existing dialogs in the first problem-solution data set using the plurality of dialogs that are generated comprises: responsive to determining that there is not a second intent in the existing dialogs that is the same or similar to the first intent, adding to the first problem-solution data set the first intent and at least one entity for the first intent. 13 . The system of claim 8 , the executable operations further comprising: generating a second problem-solution data set from intents and examples translated from the data provided by the at least one knowledge source, the second problem-solution data set comprising the intents translated from the data provided by the at least one knowledge source and the plurality of dialogs generated from the data provided by the at least one knowledge source, wherein the second problem-solution data set is used to update the existing dialogs in the first problem-solution data. 14 . The system of claim 8 , the executable operations further comprising: adding to the first problem-solution data set the plurality of dialogs generated from the data provided by the at least one knowledge source as generated d
Assignees
Inventors
Classifications
Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title
Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title
- G06F40/35Primary
Discourse or dialogue representation · CPC title
- G06F16/3329Primary
Natural language query formulation · CPC title
Updates performed during online database operations; commit processing · 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 US2023087896A1 cover?
- At least one knowledge source for use in updating a first problem-solution data set can be selected. From data provided by the at least one knowledge source, a plurality of dialogs can be automatically generated. Existing dialogs in the first problem-solution data can be updated set using the plurality of dialogs that are generated.
- Who is the assignee on this patent?
- IBM
- What technology area does this patent fall under?
- Primary CPC classification G06F40/35. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Thu Mar 23 2023 00:00:00 GMT+0000 (Coordinated Universal Time) (A1). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 10 related publications on this page (citations in our corpus or others sharing the same primary CPC).