# US 2020/0401868 A1 · Apparatus and methods for generating context-aware artificial intelligence characters > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401868 A1 - Document ID: US20200401868A1 - Status: Published application - Kind: A1 - Application number: 16/921,473 - Filed: 2020-07-06 - Published: 2020-12-24 - Earliest claimed: 2018-09-17 - Assignees: Intel Corporation - Applicants: Intel Corporation - Inventors: Jason Garcia - Web page: https://patentgrep.com/patent/US20200401868A1 ## CPC - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 5/02: Knowledge representation; Symbolic representation - G06N 20/00: Machine learning - G06T 13/40: of characters, e.g. humans, animals or virtual beings - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Example apparatus and methods for generating context-aware artificial intelligence characters are disclosed. An example apparatus to animate an artificial intelligence character includes a data tagger to tag data in a media data stream to generate a plurality of data files of tagged data, the data files corresponding to different time periods in a storyline, the tagged data associated with a first character in the media data stream, the artificial intelligence character to portray the first character. The example apparatus includes a trainer to generate a response model of the first character based on the data file corresponding to a current data time period and one or more data files corresponding to one or more earlier time periods of the storyline and a response generator to apply the response model based on a stimulus input to animate the artificial intelligence character. ## Claims ### Claim at position 1 -41. (canceled) ### Claim 42 An apparatus comprising: a trainer to generate a response model based on training data indicative of one or more of a vocabulary, behavior, knowledge, or emotion of a character; and a response generator to execute the response model to: in response to a first user input, output a first response of a virtual assistant personality, the first response associated with the character, the first response different than the training data, the first response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character; and in response to a second user input, output a second response of the virtual assistant personality, the second response associated with the character, the second response different than the training data, the second response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character, the first response different than the second response. ### Claim 43 (depends on 42) The apparatus of claim 42, wherein the response generator is to execute the response model to portray the character in the first response and the second response. ### Claim 44 (depends on 42) The apparatus of claim 42, wherein the first user input is different from the second user input. ### Claim 45 (depends on 42) The apparatus of claim 42, wherein the first user input and the second user input are the same type of input. ### Claim 46 (depends on 42) The apparatus of claim 42, wherein the response generator is to base the first response on a context of the character. ### Claim 47 (depends on 42) The apparatus of claim 42, wherein the response generator is to base the first response on a situation of the character. ### Claim 48 (depends on 42) The apparatus of claim 42, wherein the response generator is to output the first response as an audio output. ### Claim 49 (depends on 48) The apparatus of claim 48, wherein the response generator is to mimic a speech pattern of the character in the first response. ### Claim 50 (depends on 42) The apparatus of claim 42, wherein the training data includes tagged data from a media data stream, and the response generator is to include dialogue data in the media data stream in the first response. ### Claim 51 (depends on 42) The apparatus of claim 42, wherein the character is a fictional character. ### Claim 52 (depends on 42) The apparatus of claim 42, wherein the character is a non-fictional character. ### Claim 53 At least one non-transitory computer readable storage device comprising instructions that, when executed, cause at least one processor to at least: generate a response model based on training data indicative of one or more of a vocabulary, behavior, knowledge, or emotion of a character; and execute the response model to: in response to a first user input, output a first response of a virtual assistant personality, the first response to portray the character, the first response different than the training data, the first response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character; and in response to a second user input, output a second response of the virtual assistant personality, the second response to portray the character, the second response different than the training data, the second response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character, the first response different than the second response. ### Claim 54 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the first response is an audio output and the instructions, when executed, cause the at least one processor to represent a speech pattern of the character in the first response. ### Claim 55 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the first user input is different from the second user input. ### Claim 56 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the first user input and the second user input are the same type of input. ### Claim 57 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the instructions, when executed, cause the at least one processor to base the first response on a context of the character. ### Claim 58 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the instructions, when executed, cause the at least one processor to base the first response on a situation of the character. ### Claim 59 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the training data includes tagged data from a media data stream and the instructions, when executed, cause the at least one processor to include dialogue data in the media data stream in the first response. ### Claim 60 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the character is a fictional character. ### Claim 61 (depends on 53) The at least one non-transitory computer readable storage device of claim 53, wherein the character is a non-fictional character. ### Claim 62 An apparatus comprising: memory; and processor circuitry to execute machine readable instructions to: generate a response model based on training data indicative of one or more of a vocabulary, behavior, knowledge, or emotion of a character; and execute the response model to: in response to a first user input, output a first response of a virtual assistant personality, the first response to represent a personality of the character, the first response different than the training data, the first response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character; and in response to a second user input, output a second response of the virtual assistant personality, the second response to represent a personality of the character, the second response different than the training data, the second response associated with the one or more of the vocabulary, behavior, knowledge, or emotion of the character, the first response different than the second response. ### Claim 63 (depends on 62) The apparatus of claim 62, wherein the processor circuitry is to execute the instructions to include a voice of the character in the first response. ### Claim 64 (depends on 62) The apparatus of claim 62, wherein the training data includes tagged data from a media data stream and the processor circuitry is to execute the instructions to include dialogue data in the media data stream in the first response. ### Claim 65 (depends on 62) The apparatus of claim 62, wherein the processor circuitry is to execute the instructions to base the first response on a context of the character. ### Claim 66 (depends on 62) The apparatus of claim 62, wherein the character is a fictional character. ### Claim 67 (depends on 62) The apparatus of claim 62, wherein the character is a non-fictional character.