Back to results
US 11,706,357 B2Granted
Multifunction peripheral natural language chatbot
AssigneeToshiba Tec Kabushiki Kaisha
InventorsHung Tran, Halley Bradt
Life of this patent
Estimating the term…
Abstract
A system and method for natural language communication between a user and a multifunction peripheral incorporates a chatbot. The chatbot response to verbal user commands or inquiries with corresponding device reports or operation. The chatbot operates in conjunction monitored multifunction peripheral states and document processing jobs, and tenders a verbal reply accordingly, supplying information to inform the user of additional matters related to the inquiry and of likely usefulness to the user.
Claims18
A document processing system comprising:
- a microphone configured to receive digitized human speech comprising an inquiry from a user related to a current state of the document processing system;
- a memory storing text responses associatively with one or more requests;
- the memory further storing a list of identified users, wherein each identified user in the list is associated with historical request information corresponding to prior requests;
- a hardware monitor configured to monitor device states of a multifunction peripheral;
- the memory further storing text strings corresponding to each of a plurality of multifunction peripheral device states;
- a document processing engine including a scanner and a printer;
- a processor and associated memory, the processor configured for speech-to-text conversion of the digitized human speech received via the microphone to form inquiry text;
- the processor further configured to determine an identity of the user in accordance with the digitized human speech received from the user;
- the processor further configured to determine two or more text responses corresponding the inquiry text and one or more text strings corresponding to device states monitored by the hardware monitor and historical request information associated with the identified user;
- the processor further configured to generate a ranking of each determined text response, the ranking being determined by one or more of a confidence level relative to the received inquiry, availability of a response to a particular interpretation of the received query, a satisfaction level associated with previous responses to a similar inquiry, and a timing associated with previous responses;
- and
- the processor further configured to output verbal responses from a speaker in accordance with the two or more determined text responses, their associated ranking and the one or more text strings.
9 more elements
A method comprising:
- generating, via a processor from voice input received from a user into a microphone, digitized human speech comprising an inquiry related to a current state of a document processing system;
- storing, in a memory, text responses associatively with one or more requests;
- storing, in the memory, a list of identified users wherein each identified user in the list is associated with historical request information corresponding to prior requests;
- monitoring device states of a multifunction peripheral;
- storing, in the memory, text strings corresponding to each of a plurality of multifunction peripheral device states;
- a document processing engine including a scanner and a printer;
- converting, via the processor, the digitized human speech received via the microphone to text to form inquiry text;
- determining an identity of the user in accordance with the digitized human speech received from the user;
- determining one two or more text responses corresponding to the inquiry text and one or more text strings corresponding to device states monitored by a hardware monitor and historical request information associated with the identified user;
- the processor further configured to generate a ranking of each determined text response, the ranking being determined by one or more of a confidence level relative to the received inquiry, availability of a response to a particular interpretation of the received query, a satisfaction level associated with previous responses to a similar inquiry, and a timing associated with previous responses;
- outputting, via a speaker, verbal responses from the speaker in accordance with the two or more determined text responses and the one or more text strings;
- and scanning or printing a document associated with the voice input.
9 more elements
A method comprising:
- receiving a document processing job from an associated user;
- generating inquiry text from digitized speech corresponding to an inquiry received into a microphone from the associated user;
- analyzing, via a processor, generated inquiry text to identify one or more words or phrases;
- analyzing, via the processor, generated inquiry text to identify the associated user;
- receiving state data corresponding to a current state of a multifunction peripheral into memory;
- receiving, from the memory, two or more text strings corresponding to the one or more identified words and phrases and the state data;
- receiving, from the memory, historical request information associated with the identified user;
- generating a ranking of each received text string, the ranking being determined by one or more of a confidence level relative to the received inquiry, availability of a response to a particular interpretation of the received query, a satisfaction level associated with previous responses to a similar inquiry, and a timing associated with previous responses;
- generating speech output from a speaker corresponding the two or more text strings in accordance with its associated ranking;
- generating instruction text from the digitized speech received in the microphone from the associated user responsive to generated speech output;
- analyzing generated instruction text;
- and
- performing a document processing operation on the document processing job in accordance with analyzed instruction text.
10 more elements
Dependencies are inferred from the claim text.