Theme detection for object-recognition-based notifications
US-12183330-B2 · Dec 31, 2024 · US
US10369699B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10369699-B2 |
| Application number | US-201515300724-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 17, 2015 |
| Priority date | Apr 17, 2014 |
| Publication date | Aug 6, 2019 |
| Grant date | Aug 6, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method of handling a software application on a robot comprising a plurality of installed software application, a software application being associated with a predefined semantic description, the method comprises the steps of extracting one or more patterns from an audio dialog with a human user; an audio dialog comprising sentences and a pattern comprising predefined sentences; comparing one or more patterns with the semantic descriptions of the software applications; selecting a software application based on the performed comparisons; and executing the selected software application. Described developments comprise software application execution rules, predefined or dynamically defined execution rules, the audio listing of the installed applications depending on environmental parameters, the optional use of complimentary display means and the installation of a missing application. Associated systems are described.
Opening claim text (preview).
The invention claimed is: 1. A method of handling a software application on a humanoid robot, said robot comprising a plurality of installed software applications, a software application being associated with a predefined semantic description, the method comprising the steps of: extracting one or more patterns from an audio dialog with a human user, an audio dialog comprising sentences and a pattern comprising predefined sentences; comparing said one or more patterns with the semantic descriptions of said software applications, the semantic descriptions comprising one or more pre-fabricated dialogs associated with a software application, said pre-fabricated dialogs comprising variations describing the software application; selecting a software application based on the performed comparisons; executing the selected software application, wherein at least one installed software application is associated with one or more execution rules and the step of selecting a software application comprises verifying said one or more rules; the humanoid robot does not comprise a graphical user interface, the dialog comprises a request by the user of the robot to pronounce a list of installed software applications, and the list to be pronounced by the robot is dependent on parameters associated with the perceived environment of the robot. 2. The method of claim 1 , wherein said one or more rules are predefined or are dynamically defined. 3. The method of claim 1 , wherein said one or more rules are locally retrievable on the robot or are remotely accessible via a network connection. 4. The method of claim 1 , wherein the audio dialog comprises a response by the user to a question raised by the robot. 5. The method of claim 4 , wherein the question is raised by the robot to disambiguate a sentence of the dialog or a pattern extracted from said dialog. 6. The method of claim 1 , wherein the parameters are selected from the group comprising the age of a user, the gender of a user, the height of a user, the number of users in the vicinity of the robot, the mood of a user, the presence or the absence of a smile of a user, the ambient audio level, the current date, the current time, the current location and combinations thereof. 7. The method of claim 1 , wherein the step of selecting a software application further comprises associating an execution probability value to each installed software application depending on said comparisons. 8. The method of claim 1 , further comprising receiving the confirmation of the user before executing the selected software application. 9. The method of claim 1 , further comprising displaying one or more representations associated with one or more of the installed software applications during the dialog with the user. 10. The method of claim 1 , further comprising identifying a missing application in the robot, retrieving and installing said missing software application in the robot during the dialog with the user. 11. A non-transitory computer readable medium comprising instructions that when executed by a suitable computer device cause the computer device to automatically perform the steps of the method according to claim 1 . 12. A system comprising means adapted to carry out the steps of the method according to claim 1 .
Execution procedure of a spoken command · CPC title
Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title
Program controls (total factory control, i.e. centrally controlling a plurality of machines, G05B19/418) · CPC title
Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title
Feature extraction for speech recognition; Selection of recognition unit · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.