Back to results
US 11,455,510 B2Granted
Virtual-life-based human-machine interaction methods, apparatuses, and electronic devices
AssigneeAlipay (Hangzhou) Information Technology Co., Ltd.
InventorJinhui Sun
Life of this patent
Estimating the term…
Abstract
Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtual-life-based human-machine interaction. One of the method includes obtaining cognitive data for a target user in response to a human-machine interaction from the target user by performing perception analysis on the target user. Target response content is identified based on the cognitive data and sent to the target user. A virtual interactive animation that comprises a virtual life image is dynamically generated based on the cognitive data and the target response content, where the virtual life image has an animation effect that matches the human-machine interaction performed by the target user.
Claims15
A computer-implemented method, comprising:
- in response to a human-machine interaction from a target user, obtaining cognitive data for the target user by performing perception analysis on the target user;
- identifying target response content based on the cognitive data;
- sending the target response content to the target user;
- generating a basic virtual interactive animation based on the target response content, wherein generating the basic virtual interactive animation based on the target response content comprises:
- obtaining a first response feature of the target response content by performing feature extraction on the target response content based on at least one feature dimension predetermined for the target user;
- and
- obtaining the basic virtual interactive animation by inputting the first response feature of the target response content to a predetermined basic virtual image generation model, wherein the predetermined basic virtual image generation model is obtained by training a basic animation effect of a virtual life image marked by sample response content and based on a second response feature in the sample response content, wherein the second response feature in the sample response content has a same feature dimension as the first response feature extracted from the target response content;
- generating an additional virtual interactive animation based on the cognitive data, wherein the cognitive data comprises a first emotional indicator that indicates an emotion of the target user, wherein generating the additional virtual interactive animation comprises:
- determining a second emotional indicator based on the first emotional indicator, wherein the second emotional indicator indicates a responsive emotion to the emotion of the target user that is indicated by the first emotional indicator;
- and
- generating the additional virtual interactive animation based on the second emotional indicator;
- and
- dynamically generating, based on the basic virtual interactive animation and the additional virtual interactive animation, a virtual interactive animation that comprises a virtual life image, wherein the virtual life image has an animation effect that matches the human-machine interaction performed by the target user.
10 more elements
A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
- in response to a human-machine interaction from a target user, obtaining cognitive data for the target user by performing perception analysis on the target user;
- identifying target response content based on the cognitive data;
- sending the target response content to the target user;
- generating a basic virtual interactive animation based on the target response content, wherein generating the basic virtual interactive animation based on the target response content comprises:
- obtaining a first response feature of the target response content by performing feature extraction on the target response content based on at least one feature dimension predetermined for the target user;
- and
- obtaining the basic virtual interactive animation by inputting the first response feature of the target response content to a predetermined basic virtual image generation model, wherein the predetermined basic virtual image generation model is obtained by training a basic animation effect of a virtual life image marked by sample response content and based on a second response feature in the sample response content, wherein the second response feature in the sample response content has a same feature dimension as the first response feature extracted from the target response content;
- generating an additional virtual interactive animation based on the cognitive data, wherein the cognitive data comprises a first emotional indicator that indicates an emotion of the target user, wherein generating the additional virtual interactive animation comprises:
- determining a second emotional indicator based on the first emotional indicator, wherein the second emotional indicator indicates a responsive emotion to the emotion of the target user that is indicated by the first emotional indicator;
- and
- generating the additional virtual interactive animation based on the second emotional indicator;
- and
- dynamically generating, based on the basic virtual interactive animation and the additional virtual interactive animation, a virtual interactive animation that comprises a virtual life image, wherein the virtual life image has an animation effect that matches the human-machine interaction performed by the target user.
10 more elements
A computer-implemented system, comprising:
- one or more computers;
- and
- one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
- in response to a human-machine interaction from a target user, obtaining cognitive data for the target user by performing perception analysis on the target user;
- identifying target response content based on the cognitive data;
- sending the target response content to the target user;
- generating a basic virtual interactive animation based on the target response content, wherein generating the basic virtual interactive animation based on the target response content comprises:
- obtaining a first response feature of the target response content by performing feature extraction on the target response content based on at least one feature dimension predetermined for the target user;
- and
- obtaining the basic virtual interactive animation by inputting the first response feature of the target response content to a predetermined basic virtual image generation model, wherein the predetermined basic virtual image generation model is obtained by training a basic animation effect of a virtual life image marked by sample response content and based on a second response feature in the sample response content, wherein the second response feature in the sample response content has a same feature dimension as the first response feature extracted from the target response content;
- generating an additional virtual interactive animation based on the cognitive data, wherein the cognitive data comprises a first emotional indicator that indicates an emotion of the target user, wherein generating the additional virtual interactive animation comprises:
- determining a second emotional indicator based on the first emotional indicator, wherein the second emotional indicator indicates a responsive emotion to the emotion of the target user that is indicated by the first emotional indicator;
- and
- generating the additional virtual interactive animation based on the second emotional indicator;
- and
- dynamically generating, based on the basic virtual interactive animation and the additional virtual interactive animation, a virtual interactive animation that comprises a virtual life image, wherein the virtual life image has an animation effect that matches the human-machine interaction performed by the target user.
13 more elements
Dependencies are inferred from the claim text.