Generating personalized videos from textual information and user preferences
View Patent ↗Systems, methods and non-transitory computer readable media for generating personalized videos from textual information are provided. An indication of a preference of a user is obtained. Further, textual information for generating a personalized video is obtained from the user. At least one characteristic of a character is selected based on the preference of the user. An artificial neural network, the textual information and the selected at least one characteristic of the character is used to generate the personalized video depicting the character with the selected at least one characteristic.
1. A computer program product for generating personalized videos from textual information, the computer program product embodied in a non-transitory computer-readable medium and including instructions that when executed by at least one processor cause the at least one processor to execute a method, the method comprising:
obtaining an indication of a preference of a user;
obtaining textual information for generating a personalized video, the textual information includes a description of an action, the action includes usage of a particular device;
selecting at least one characteristic of a character for the personalized video based on the preference of the user; and
using an artificial neural network, the textual information, and the selected at least one characteristic of the character to generate the personalized video depicting the character with the selected at least one characteristic, the generated personalized video depicts the character with the selected at least one characteristic performing the described action.
2. The computer program product of claim 1 , wherein the textual information includes a description of a location, wherein the method further comprises using the description of the location to generate a background for the character, and wherein the generated personalized video depicts the character with the selected at least one characteristic over the background.
3. The computer program product of claim 1 , wherein the method further comprises using a personalized profile associated with the user and indicative of the preference of the user to select a background, and wherein the generated personalized video depicts the character with the selected at least one characteristic over the background.
4. The computer program product of claim 1 , wherein the textual information includes a dialog between two characters, the generated personalized video depicts the character with the at least one characteristic speaking, based on the dialog, with a second character, and the method further comprises using a personalized profile associated with the user and indicative of the preference of the user and the dialog to select at least one characteristic of the second character.
5. The computer program product of claim 1 , wherein the method further comprises using a personalized profile associated with the user and indicative of the preference of the user to select an object, and wherein the generated personalized video depicts the character with the at least one characteristic interacting with the selected object.
6. The computer program product of claim 1 , wherein the method further comprises using a personalized profile associated with the user and indicative of the preference of the user to select an object, and wherein the generated personalized video depicts the character with the at least one characteristic throwing the selected object.
7. The computer program product of claim 1 , wherein the generated personalized video depicts the character behaving based on the textual information, and wherein the method further comprises:
obtaining second textual information; and
using the second textual information and the selected at least one characteristic of the character to generate a second video depicting the character behaving based on the second textual information.
8. The computer program product of claim 1 , wherein the generated personalized video depicts the character behaving based on the textual information, and wherein the method further comprises: using the textual information and a second at least one characteristic of a second character to generate a second video depicting the second character with the second at least one characteristic of the second character behaving similarly to the character with the at least one characteristic of the character in the generated personalized video.
9. The computer program product of claim 1 , wherein the textual information includes at least a text to be spoken by the character, and the generated personalized video depicts the character reading the text aloud.
10. The computer program product of claim 1 , wherein the method further comprises analyzing a text to determine a desired facial expression corresponding to a particular portion of the text, and wherein the generated personalized video depicts the character using the determined desired facial expression while saying the particular portion of the text aloud.
11. The computer program product of claim 1 , wherein the method further comprises analyzing a text to determine a desired hand gesture corresponding to a particular portion of the text, and wherein the generated personalized video depicts the character using the determined desired hand gesture while saying the particular portion of the text aloud.
12. The computer program product of claim 1 , wherein the method further comprises displaying the generated personalized video to the user.
13. The computer program product of claim 1 , wherein the method further comprises using statistical data correlating past behaviors of users with common preferences of users regarding characteristics of characters to further base the selection of the at least one characteristic of the character on past behavior of the user.
14. The computer program product of claim 13 , wherein the past behavior of the user includes an action performed by the user.
15. The computer program product of claim 13 , wherein the past behavior of the user includes a past activity corresponding to the user.
16. The computer program product of claim 13 , wherein the past behavior of the user includes past avoidance of an activity corresponding to the user.
17. The computer program product of claim 13 , wherein the past behavior of the user includes past selections made by the user.
18. The computer program product of claim 13 , wherein the past behavior of the user includes a past selection of a second character with a specific characteristic, and the selected at least one characteristic of the character includes the specific characteristic.
19. The computer program product of claim 13 , wherein the past behavior of the user includes an avoidance of characters with a specific characteristic, and wherein the specific characteristic is not included in the selected at least one characteristic of the character.
20. The computer program product of claim 1 , wherein the method further comprises using statistical data correlating demographic information with common preferences of users regarding characteristics of characters to further base the selection of the at least one characteristic of the character on a socioeconomic status of the user.
21. The computer program product of claim 1 , wherein the selection of the at least one characteristic of the character is further based on a destination of the user.
22. The computer program product of claim 1 , wherein the method further comprises using statistical data correlating cultural associations with common preferences of users regarding characteristics of characters to further base the selection of the at least one characteristic of the character on a cultural tradition of the user.
23. The computer program product of claim 1 , wherein the method further comprises using statistical data correlating emotional states with common preferences of users regarding characteristics of characters to further base the selection of the at least one characteristic of the character on an emotional state of the user.
24. The computer program product of claim 1 , wherein the method further comprises selecting a hair-style of the character based on a preferred hair-style of the user.
25. The computer program product of claim 1 , wherein the method further comprises selecting a measurement of the character based on a preferred measurements of the user.
26. The computer program product of claim 1 , wherein the method further comprises:
obtaining a personalized profile associated with the user and indicative of preferred celebrities of the user; and
using the personalized profile to select the at least one characteristic of the character.
27. The computer program product of claim 1 , wherein the method further comprises using the artificial neural network to select the at least one characteristic of the character based on the preference of the user.
28. The computer program product of claim 1 , wherein the textual information is automatically generated.
29. The computer program product of claim 1 , wherein the textual information is automatically generated from a weather forecast.
30. A system for generating personalized videos from textual information, the system comprising at least one processor configured to:
obtain an indication of a preference of a user;
obtain textual information for generating a personalized video, the textual information includes a description of an action, the action includes usage of a particular device;
select at least one characteristic of a character based on the preference of the user; and
use an artificial neural network, the textual information, and the selected at least one characteristic of the character to generate the personalized video depicting the character with the selected at least one characteristic, the generated personalized video depicts the character with the selected at least one characteristic performing the described action.
31. A method for generating personalized videos from textual information, the method comprising:
obtaining an indication of a preference of a user;
obtaining textual information for generating a personalized video, the textual information includes a description of an action, the action includes usage of a particular device;
selecting at least one characteristic of a character based on the preference of the user; and
using an artificial neural network, the textual information and the selected at least one characteristic of the character to generate the personalized video depicting the character with the selected at least one characteristic, the generated personalized video depicts the character with the selected at least one characteristic performing the described action.