Information processing device, information processing method, and information processing program

Abstract

The information processing device includes: a learning means for enabling an AI agent to learn the generative AI usage content performed by the user; and a recording means for recording the data required to utilize the AI ​​agent that has been learned by the learning means; and also includes: a prompting input means for inputting prompts input by the user into the learned AI agent; a converted prompt acquisition means for acquiring the converted prompts by the AI ​​agent; and a converted prompt input means for inputting the converted prompts acquired by the converted prompt acquisition means into the generative AI.

Claims

1. An information processing apparatus, characterized by comprising: a prompting input means for inputting a prompt inputted by a user into a learned AI agent that has learned the content utilized by a user-generated AI; a converted prompt acquisition means for acquiring a prompt that has been converted by the previous AI agent; a converted prompt input means for inputting the converted prompt acquired by the previous converted prompt acquisition means into the previous generative AI; an inference result acquisition means for acquiring an inference result output from the previous generative AI in response to the input of the converted prompt; an inference result input means for inputting a previous inference result acquired by the previous inference result acquisition means into the previous AI agent; a converted inference result acquisition means for acquiring an inference result that has been converted by the previous AI agent; and a prompting means for prompting the user with the converted inference result acquired by the previous converted inference result acquisition means.

2. The information processing apparatus as described in claim 1, wherein, The previously learned AI agent learns from the content of the prompts input by the user to the previously generated AI and the user's actions in response to the inferences output by the previously generated AI, treating these as the content of the user's use of the generated AI.

3. The information processing apparatus as described in claim 2, wherein, The aforementioned learned AI agent is one that learns from the content indicating what actions the user takes in response to the output of the generative AI, treating it as the user's action in response to the inference results from the output of the aforementioned generative AI.

4. The information processing apparatus as described in claim 3, wherein, The AI ​​agent learned in the preceding text learns from the preceding generative AI. When the user corrects the inference results output by the preceding generative AI, the user's corrections are treated as actions taken by the user in response to the inference results output by the preceding generative AI, and are thus learned.

5. The information processing apparatus as described in claim 3, wherein, The AI ​​agent learned in the preceding text is that when a user asks a follow-up question about the inference results output by the preceding generative AI, the content of the user's follow-up question is treated as the user's action content in response to the inference results output by the preceding generative AI, and is thus learned.

6. The information processing apparatus as described in claim 1, wherein, The aforementioned prompting method explains the intention behind the generation of the generative AI when presenting the inference result to the user.

7. An information processing apparatus, characterized by comprising: an inference result acquisition means for acquiring an inference result output from a generative AI; an inference result input means for inputting a previously acquired inference result obtained by the aforementioned inference result acquisition means into a learned AI agent that has learned the content of generative AI used by a user; a converted inference result acquisition means for acquiring an inference result converted by the aforementioned AI agent; and a prompting means for prompting a user with the converted inference result obtained by the aforementioned converted inference result acquisition means; wherein the aforementioned prompting means, when prompting the user with the inference result, explains the intention of the generative AI in generating the inference result.

8. An information processing method performed in a computer, comprising: The steps include: inputting the user-inputted prompts into a learned AI agent that has learned from the generative AI content created by the user using a prompting input method; obtaining the prompts that have been converted by the aforementioned AI agent using a converted prompt acquisition method; inputting the converted prompts obtained by the previously acquired converted prompt acquisition method into the aforementioned generative AI using a converted prompt input method; obtaining the inference result output from the aforementioned generative AI in response to the input of the previously acquired converted prompts using an inference result acquisition method; inputting the previously acquired inference result obtained by the previously acquired inference result acquisition method into the aforementioned AI agent using an inference result input method; obtaining the inference result that has been converted by the previously acquired AI agent using a converted inference result acquisition method; and prompting the user with the converted inference result obtained by the previously acquired converted inference result acquisition method using a prompting method.

9. The information processing method as described in request item 8, wherein, The previously learned AI agent learns from the content of the prompts input by the user to the previously generated AI and the user's actions in response to the inferences output by the previously generated AI, treating these as the content of the user's use of the generated AI.

10. The information processing method as described in claim 9, wherein, The aforementioned learned AI agent is one that learns from the content indicating what actions the user takes in response to the output of the generative AI, treating it as the user's action in response to the inference results from the output of the aforementioned generative AI.

11. The information processing method as described in request item 10, wherein, The AI ​​agent learned in the preceding text learns from the preceding generative AI. When the user corrects the inference results output by the preceding generative AI, the user's corrections are treated as actions taken by the user in response to the inference results output by the preceding generative AI, and are thus learned.

12. The information processing method as described in request item 10, wherein, The AI ​​agent learned in the preceding text is that when a user asks a follow-up question about the inference results output by the preceding generative AI, the content of the user's follow-up question is treated as the user's action content in response to the inference results output by the preceding generative AI, and is thus learned.

13. The information processing method as described in request item 8, wherein, The aforementioned prompting method explains the intention behind the generation of the generative AI when presenting the inference result to the user.

14. An information processing method, which is an information processing method performed in a computer, characterized by comprising: a step of obtaining an inference result output from a generative AI by an inference result obtaining means; a step of inputting a previously obtained inference result obtained by the inference result obtaining means into a learned AI agent that has learned the content utilized by the generative AI made by a user by an inference result input means; a step of obtaining an inference result transformed by the previously obtained AI agent by a transformed inference result obtaining means; and a step of prompting a user with the transformed inference result obtained by the previously obtained transformed inference result obtaining means; wherein, The aforementioned prompting method explains the intention behind the generation of the generative AI when presenting the inference result to the user.

15. An information processing program for causing a computer to perform the information processing method described in any one of claims 8 to 14.

Images