SYSTEMS AND METHODS FOR AUTHORING AND MODIFYING PRESENTATION CONVERSATION FILES FOR MULTIMODAL INTERACTIVE COMPUTING DEVICES / ARTIFICIAL COMPANSIONS
Systems and methods for authoring and modifying presentation conversation files are disclosed. Exemplary implementations may: receive, at a renderer module, voice files, visual effect files, facial expression files, and/or mobility files; analyze, by the language processor module, the voice files, the visual effect files, the facial expression files, and/or mobility files follow guidelines of a multimodal authoring system; generate, by the renderer module, one or more presentation conversation files based at least in part on the received voice files, visual effect files, facial expression files, and/or mobility files; test, at an automatic testing system, the one or more presentation conversation files to verify correct operation of a computing device that receives the one or more presentation conversation files as an input; and identify, by a multimodal review module, changes to be made to the voice input files, the visual effect files, the facial expression files, and/or the mobility files.
1 . A method of authoring and modifying presentation conversation files, comprising:
accessing computer-readable instructions from one or more memory devices for execution by one or more processors of the computing device;
executing the computer-readable instructions accessed from the one or more memory devices by the one or more processors of the computing device; and
wherein executing the computer-readable instructions further comprising:
receiving, at a renderer module of the computing device, voice files, visual effect files, facial expression files and/or mobility files, wherein the voice files cause a robot computing device providing the voice files to make sounds and the mobility files cause parts of the robot computing device providing the mobility files to move;
analyzing, by the language processor module of the computing device, the voice files, the visual effect files, the facial expression files and/or mobility files follow guidelines of a multimodal authoring system;
generating, by the renderer module, one or more presentation conversation files based at least in part on the received voice files, visual effect files, facial expression files and/or mobility files;
testing, at an automatic testing system, the one or more presentation conversation files to verify correct operation with respect to a robot computing device that receives the one or more presentation conversation files as an input and that the automatic testing system is simulating; and
testing, at the automatic testing system, the one or more presentation conversation files on different device configuration files to simulate testing on different robot computing devices.
2 . The method of claim 1 , wherein executing the computer-readable instructions further comprising:
identifying, by a multimodal review module, changes to be made to the voice input files, the visual effect files, the facial expression files and/or the mobility files;
communicating, to the editor module of the computing device, the changes to be made to the voice files, the visual effect files, the facial expression files and/or the mobility files; and
generating revised voice files, revised visual effect files, revised facial expression files and/or revised mobility files based at least in part on the identified changes.
3 . The method of claim 2 , wherein executing the computer-readable instructions further comprising: communicating revised voice files, revised visual effect files, revised facial expression files and/or revised mobility files to the language processor module to verify these files follows the guidelines of the multimodal authoring system.
4 . The method of claim 3 , wherein executing the computer-readable instructions further comprising: wherein if the revised voice files, the revised visual effect files, the revised facial expression files and/or the revised mobility files follow the guidelines of the multimodal authoring system, communicating the revised voice files, revised visual effect files, revised facial expression files and/or revised mobility files to the renderer module to generate a new presentation conversation file.
5 . The method of claim 1 , wherein the voice files are generated utilizing one or more microphones and speech recognition software.
6 . The method of claim 1 , wherein the visual effect files are generated utilizing one or more imaging devices, one or more microphones or special effect software.
7 . The method of claim 1 , wherein the facial expression files are generated utilizing one or more imaging devices, one or more microphones or graphical animation software.
8 . The method of claim 1 , wherein the mobility files are generated utilizing one or more imaging devices, one or more microphones and mobility command generation software.
9 . The method of claim 1 , wherein the multimodal authoring system includes autocompletion software, the autocompletion software authoring the voice files, the visual effect files, the facial expression files or the mobility files.
10 . The method of claim 9 , wherein the autocompletion software generates phrase hints to assist in generating the voice input files.
11 . The method of claim 1 , wherein the multimodal authoring system provides suggestions for generation of the voice files, the visual effect files, the facial expression files and/or the mobility files based on a current context.
12 . The method of claim 1 , wherein the language processor module provides suggestions for generation of the voice files, the visual effect files, the facial expression files or the mobility files based on a robot computing device's characteristics, which include a companion's personality characteristics.
13 . (canceled)
14 . The method of claim 12 , wherein the robot computing device's characteristics include atypical vocabulary.
15 . The method of claim 12 , wherein the robot computing device's characteristics include target user group characteristics.
16 . The method of claim 12 , wherein the robot computing device's characteristics include target user group's needs, goals and/or abilities.
17 . The method of claim 2 , wherein the revised voice files, the revised visual effect files, the revised visual effect files and/or the revised mobility files are based on the multimodal authoring system's analyzing similar content based on characteristics of the similar content.
18 . The method of claim 17 , wherein the characteristics of the similar content comprise sentiment of the similar content, affect of the similar content and context of the similar content.
19 . The method of claim 1 , wherein executing the computer-readable instructions further comprising learning synonymous pathways to the generated presentation conversation files and generating synonymous presentation conversation files that are acceptable to the multimodal authoring system.
20 . The method of claim 1 , wherein executing the computer-readable instructions further comprising receiving performance analysis statistics from other robot computing devices that have implemented the one or more presentation conversation files; and
generating one or more modified presentation conversation files based on the received performance analysis statistics; and further testing the modified presentation conversation file.
21 . The method of claim 1 , wherein the robot computing device comprises a computing device, a chatbot, a voice recognition computing device, or an artificial intelligence computing device.