Artificial intelligence-based content generation method, apparatus, intelligent agent system, electronic device, storage medium, and program

Abstract

The present disclosure provides a content generation method, apparatus, intelligent agent system, electronic device, storage medium, and program based on artificial intelligence, and relates to the field of artificial intelligence technology. [Solution] A specific solution includes: a first intelligent agent sending a task execution request to a second intelligent agent based on task guidance information, where the task guidance information includes guidance information for generating content, and the task execution request includes a target task that the second intelligent agent needs to perform to generate the content; and the first intelligent agent receiving a task execution result from the second intelligent agent, where the task execution result includes an execution result generated by the second intelligent agent by performing the target task.

Claims

1. A content generation method based on artificial intelligence, The first intelligent agent transmits a task execution request to the second intelligent agent based on task guidance information, wherein the task guidance information includes guidance information for generating content, and the task execution request includes a target task that the second intelligent agent needs to perform in order to generate content. The first intelligent agent receives task execution results from the second intelligent agent, wherein the task execution results include execution results generated by the second intelligent agent performing the target task. A content generation method based on artificial intelligence.

2. The first intelligent agent sends a task execution request to the second intelligent agent based on task guidance information. The first intelligent agent adds a first system message generated based on the task guidance information to a first message pool, the first message pool further including a first local message. The first intelligent agent generates a first task message based on messages in the first message pool, The first intelligent agent transmits a task execution request to the second intelligent agent based on a first task message, wherein the task execution request includes a target task that the second intelligent agent needs to perform in order to generate content. A method for generating content based on artificial intelligence as described in claim 1.

3. The first intelligent agent receives the task execution result from the second intelligent agent, The first intelligent agent receives a second task message from the second intelligent agent, the second task message includes the task execution result, the second task message is generated by the second intelligent agent based on messages in a second message pool, the second message pool includes a second system message and a second local message, the second system message is generated by the second intelligent agent based on task guidance information, and the second local message includes the task execution request from the first intelligent agent. The artificial intelligence-based content generation method described in claim 2.

4. The aforementioned artificial intelligence-based content generation method is The first intelligent agent adds the second task message as a newly added first local message to the first message pool, further comprising the first message pool further including the first task message corresponding to the processed first local message and the newly added first local message. The artificial intelligence-based content generation method described in claim 3.

5. The aforementioned artificial intelligence-based content generation method is If the number of messages in the first message pool exceeds a set threshold, delete one or more sets of messages from the first message pool, wherein each set of messages includes a first local message and a corresponding first task message. The artificial intelligence-based content generation method described in claim 2.

6. The aforementioned artificial intelligence-based content generation method is The first intelligent agent receives the task guidance information from the system intelligent agent, the task guidance information being generated by the system intelligent agent based on input text information and the system intelligent agent's prompt template, further comprising: A method for generating content based on artificial intelligence as described in claim 1.

7. The aforementioned target task includes at least one of the following: a search task, a segmentation task, a shot division task, a matching task, a generation task, and a content synthesis task. The target tools that need to be invoked to perform the aforementioned target task include at least one of the following: search tool, splitting tool, shot splitting tool, matching tool, generation tool, and synthesis tool. The task execution result includes at least one of the following: search results, splitting results, shot splitting results, matching results, generation results, and synthesis results. A method for generating content based on artificial intelligence as described in claim 1.

8. If the objective task includes a search task, the objective tool that needs to be invoked to perform the search task includes a search tool, and the task execution result includes search results obtained by invoking the search tool and performing the search task. The artificial intelligence-based content generation method described in claim 7.

9. If the target task includes a splitting task, the target tool that needs to be invoked to perform the splitting task includes a splitting tool, and the task execution result includes content segments obtained by invoking the splitting tool and performing the splitting task based on the search results. The artificial intelligence-based content generation method described in claim 8.

10. If the aforementioned target task includes a shot division task, the target tool that needs to be invoked to perform the shot division task includes a shot division tool, and the task execution result includes the shot division result obtained by invoking the shot division tool and performing the shot division task. The artificial intelligence-based content generation method described in claim 7.

11. If the objective task includes a matching task, the objective tool that needs to be invoked to perform the matching task includes a matching tool, the task execution result includes a matching result obtained by invoking the matching tool and performing matching based on the shot division result, and / or If the aforementioned target task includes a generation task, the target tool that needs to be invoked to perform the generation task includes a generation tool, and the task execution result includes a generated content segment for the shot segmentation result for which there are no matching results or content needs to be generated by invoking the generation tool. The artificial intelligence-based content generation method described in claim 10.

12. If the aforementioned target task includes a content synthesis task, the target tool that needs to be invoked to perform the content synthesis task includes a content synthesis tool, and the task execution result includes target content obtained by invoking the content synthesis tool and synthesizing content segments corresponding to multiple shot division results. The artificial intelligence-based content generation method described in claim 11.

13. A content generation method based on artificial intelligence, The second intelligent agent receives a task execution request transmitted by the first intelligent agent based on task guidance information, wherein the task guidance information includes guidance information for generating content, and the task execution request includes a target task that the second intelligent agent needs to perform in order to generate content. The second intelligent agent executes the target task based on the task execution request and generates a task execution result, The second intelligent agent includes transmitting the task execution result to the first intelligent agent, A content generation method based on artificial intelligence.

14. The second intelligent agent executes the target task based on the task execution request and generates a task execution result. The second intelligent agent adds the second system message generated based on the task guidance information to the second message pool, The second intelligent agent adds the task execution request from the first intelligent agent as a second local message to the second message pool, The second intelligent agent includes, , executing the target task based on the messages in the second message pool and generating the task execution result, A method for generating content based on artificial intelligence as described in claim 13.

15. The aforementioned artificial intelligence-based content generation method is The second intelligent agent further includes adding a second task message containing the task execution result to the second message pool. The second intelligent agent transmitting the task execution result to the first intelligent agent includes the second intelligent agent transmitting the second task message to the first intelligent agent. The artificial intelligence-based content generation method described in claim 14.

16. The aforementioned artificial intelligence-based content generation method is If the number of messages in the second message pool exceeds a set threshold, delete one or more sets of messages from the second message pool, wherein each set of messages includes a second local message and a corresponding second task message. The artificial intelligence-based content generation method described in claim 14.

17. The aforementioned artificial intelligence-based content generation method is The second intelligent agent receives the task guidance information from the system intelligent agent, the task guidance information being generated by the system intelligent agent based on input text information and the system intelligent agent's prompt template, further comprising: The artificial intelligence-based content generation method described in claim 14.

18. The aforementioned target task includes at least one of the following: a search task, a segmentation task, a shot division task, a matching task, a generation task, and a content synthesis task. The target tools that need to be invoked to perform the aforementioned target task include at least one of the following: search tool, splitting tool, shot splitting tool, matching tool, generation tool, and synthesis tool. The task execution result includes at least one of the following: search results, splitting results, shot splitting results, matching results, generation results, and synthesis results. The artificial intelligence-based content generation method described in claim 14.

19. The second intelligent agent executes the target task based on the messages in the second message pool and generates the task execution result, If the objective task includes a search task, the objective tool that needs to be invoked to perform the search task includes a search tool, and the second intelligent agent includes invoking the search tool to perform the search task and obtain search results based on messages in the second message pool and newly added second local messages. The artificial intelligence-based content generation method described in claim 18.

20. The second intelligent agent executes the target task based on the messages in the second message pool and generates the task execution result, If the target task includes a splitting task, the target tool that needs to be invoked to perform the splitting task includes a splitting tool, and the second intelligent agent further includes invoking the splitting tool based on messages in the second message pool to perform the splitting task based on the search results to obtain content segments. A method for generating content based on artificial intelligence as described in claim 19.

21. The second intelligent agent executes the target task based on the messages in the second message pool and generates the task execution result, If the objective task includes a shot division task, the objective tool that needs to be invoked to perform the shot division task includes a shot division tool, and the second intelligent agent further includes invoking the shot division tool to perform the shot division task and obtain a shot division result based on messages in the second message pool. The artificial intelligence-based content generation method described in claim 18.

22. The second intelligent agent executes the target task based on the messages in the second message pool and generates the task execution result, If the objective task includes a matching task, the objective tool that needs to be invoked to perform the matching task includes a matching tool, and the second intelligent agent invokes the matching tool based on the messages in the second message pool, performs matching based on the shot division results, and obtains a matching result. If the target task includes a generation task, the target tool that needs to be invoked to perform the generation task includes a generation tool, and the second intelligent agent further includes, at least one of the following: invoking the generation tool based on messages in the second message pool to generate content segments for the shot splitting results where there are no matching results or where content needs to be generated. The artificial intelligence-based content generation method described in claim 21.

23. The second intelligent agent executes the target task based on the messages in the second message pool and generates the task execution result, If the target task includes a content synthesis task, the target tool that needs to be invoked to perform the content synthesis task includes a content synthesis tool, and the second intelligent agent further includes invoking the content synthesis tool based on messages in the second message pool to synthesize content segments corresponding to multiple shot division results to obtain target content. The artificial intelligence-based content generation method described in claim 22.

24. An artificial intelligence-based content generation device, used in a first intelligent agent, A first transmission module for sending a task execution request to a second intelligent agent based on task guidance information, wherein the task guidance information includes guidance information for generating content, and the task execution request includes a target task that the second intelligent agent needs to perform in order to generate content. A first receiving module for receiving task execution results from the second intelligent agent, wherein the task execution results include execution results generated by the second intelligent agent performing the target task. An artificial intelligence-based content generation device.

25. The first transmission module is, A first generation submodule for adding a first system message generated based on the task guidance information to a first message pool, wherein the first message pool further includes a first local message, A first generation submodule for generating a first task message based on messages in the first message pool, A first transmission submodule for sending a task execution request to a second intelligent agent based on the first task message, the task execution request includes a target task that the second intelligent agent needs to perform to generate content, and the first transmission submodule includes: The artificial intelligence-based content generation device according to claim 24.

26. The first receiving module is, The method further includes receiving a second task message from the second intelligent agent, the second task message containing the task execution result, the second task message being generated by the second intelligent agent based on messages in a second message pool, the second message pool containing a second system message and a second local message, the second system message being generated by the second intelligent agent based on task guidance information, and the second local message containing the task execution request from the first intelligent agent. The artificial intelligence-based content generation device according to claim 25.

27. The aforementioned artificial intelligence-based content generation device is A first add-on module for adding the second task message as a newly added first local message to the first message pool, wherein the first message pool further includes the first add-on module, which further includes a first task message corresponding to a processed first local message and the newly added first local message. The artificial intelligence-based content generation device according to claim 26.

28. The aforementioned artificial intelligence-based content generation device is A first deletion module for deleting one or more sets of messages from the first message pool if the number of messages in the first message pool exceeds a set threshold, wherein the first deletion module further comprises a set of messages including a first local message and a corresponding first task message. An artificial intelligence-based content generation device according to any one of claims 25 to 27.

29. The aforementioned artificial intelligence-based content generation device is A second receiving module for receiving task guidance information from a system intelligent agent, wherein the task guidance information is generated by the system intelligent agent based on input text information and the system intelligent agent's prompt template, further comprising the second receiving module. The artificial intelligence-based content generation device according to claim 24.

30. The aforementioned target task includes at least one of the following: a search task, a segmentation task, a shot division task, a matching task, a generation task, and a content synthesis task. The target tools that need to be invoked to perform the aforementioned target task include at least one of the following: search tool, splitting tool, shot splitting tool, matching tool, generation tool, and synthesis tool. The task execution result includes at least one of the following: search results, splitting results, shot splitting results, matching results, generation results, and synthesis results. The artificial intelligence-based content generation device according to claim 24.

31. If the objective task includes a search task, the objective tool that needs to be invoked to perform the search task includes a search tool, and the task execution result includes search results obtained by invoking the search tool and performing the search task. The artificial intelligence-based content generation device according to claim 30.

32. If the target task includes a splitting task, the target tool that needs to be invoked to perform the splitting task includes a splitting tool, and the task execution result includes content segments obtained by invoking the splitting tool and performing the splitting task based on the search results. The artificial intelligence-based content generation device according to claim 31.

33. If the aforementioned target task includes a shot division task, the target tool that needs to be invoked to perform the shot division task includes a shot division tool, and the task execution result includes the shot division result obtained by invoking the shot division tool and performing the shot division task. The artificial intelligence-based content generation device according to claim 30.

34. If the objective task includes a matching task, the objective tool that needs to be invoked to perform the matching task includes a matching tool, the task execution result includes a matching result obtained by invoking the matching tool and performing matching based on the shot division result, and / or If the aforementioned target task includes a generation task, the target tool that needs to be invoked to perform the generation task includes a generation tool, and the task execution result includes a generated content segment for the shot segmentation result for which there are no matching results or content needs to be generated by invoking the generation tool. The artificial intelligence-based content generation device according to claim 33.

35. If the aforementioned target task includes a content synthesis task, the target tool that needs to be invoked to perform the content synthesis task includes a content synthesis tool, and the task execution result includes target content obtained by invoking the content synthesis tool and synthesizing content segments corresponding to multiple shot division results. The artificial intelligence-based content generation device according to claim 34.

36. An artificial intelligence-based content generation device, used in a second intelligent agent, A third receiving module for receiving a task execution request transmitted by a first intelligent agent based on task guidance information, wherein the task guidance information includes guidance information for generating content, and the task execution request includes a target task that the second intelligent agent needs to perform in order to generate content. A calling module for executing the target task based on the task execution request and generating the task execution result, The system includes a second transmission module for transmitting the task execution result to the first intelligent agent. An artificial intelligence-based content generation device.

37. The aforementioned calling module, A first additional submodule for adding a second system message generated based on the task guidance information to a second message pool, A second additional submodule for adding the task execution request from the first intelligent agent as a second local message to the second message pool, A third generation submodule for executing the target task based on messages in the second message pool and generating the task execution result, The artificial intelligence-based content generation device according to claim 36.

38. The aforementioned artificial intelligence-based content generation device is The system further comprises a second add-on module for adding a second task message containing the task execution result to the second message pool, The second transmission module is further used to transmit the second task message to the first intelligent agent. The artificial intelligence-based content generation device according to claim 37.

39. The aforementioned artificial intelligence-based content generation device is A second deletion module for deleting one or more sets of messages from the second message pool if the number of messages in the second message pool exceeds a set threshold, wherein the second deletion module further comprises a set of messages including a second local message and a corresponding second task message. The artificial intelligence-based content generation device according to claim 37.

40. The aforementioned artificial intelligence-based content generation device is A fourth receiving module for receiving task guidance information from a system intelligent agent, wherein the task guidance information is generated by the system intelligent agent based on input text information and the system intelligent agent's prompt template, further comprising the fourth receiving module. The artificial intelligence-based content generation device according to claim 37.

41. The aforementioned target task includes at least one of the following: a search task, a segmentation task, a shot division task, a matching task, a generation task, and a content synthesis task. The target tools that need to be invoked to perform the aforementioned target task include at least one of the following: search tool, splitting tool, shot splitting tool, matching tool, generation tool, and synthesis tool. The task execution result includes at least one of the following: search results, splitting results, shot splitting results, matching results, generation results, and synthesis results. The artificial intelligence-based content generation device according to claim 37.

42. The third generation submodule is, If the aforementioned target task includes a search task, the target tool that needs to be invoked to perform the search task includes a search tool, which is further used to invoke the search tool and perform the search task to obtain search results based on the messages in the second message pool and the newly added second local messages. Content generation device based on artificial intelligence as described in claim 41.

43. The third generation submodule is, If the target task includes a splitting task, the target tool that needs to be invoked to perform the splitting task includes a splitting tool, which is further used to invoke the splitting tool based on messages in the second message pool and to perform the splitting task based on the search results to obtain content segments. The artificial intelligence-based content generation device according to claim 42.

44. The third generation submodule is, If the aforementioned target task includes a shot splitting task, the target tool that needs to be invoked to perform the shot splitting task includes a shot splitting tool, which is further used to invoke the shot splitting tool to perform the shot splitting task and obtain the shot splitting result based on the messages in the second message pool. Content generation device based on artificial intelligence as described in claim 41.

45. The third generation submodule is, If the aforementioned target task includes a matching task, the target tool that needs to be invoked to perform the matching task includes a matching tool, which invokes the matching tool based on the messages in the second message pool, performs matching based on the shot division results, and obtains a matching result. If the target task includes a generation task, the target tool that needs to be invoked to perform the generation task includes a generation tool, and is further used to invoke the generation tool based on messages in the second message pool to generate content segments for the shot splitting results where there are no matching results or where content needs to be generated, The artificial intelligence-based content generation device according to claim 44.

46. The third generation submodule is, If the aforementioned target task includes a content synthesis task, the target tool that needs to be invoked to perform the content synthesis task includes a content synthesis tool, which is further used to invoke the content synthesis tool based on messages in the second message pool to synthesize content segments corresponding to multiple shot division results in order to obtain target content. The artificial intelligence-based content generation device according to claim 45.

47. An intelligent agent system comprising a first intelligent agent and a second intelligent agent, The first intelligent agent is used to send a task execution request to the second intelligent agent based on task guidance information and to receive task execution results from the second intelligent agent, wherein the task guidance information includes guidance information for generating content, the task execution request includes a target task that the second intelligent agent needs to execute in order to generate content, and the task execution results include execution results generated by the second intelligent agent executing the target task. The second intelligent agent is used to receive a task execution request transmitted by the first intelligent agent based on task guidance information, to execute the target task based on the task execution request and generate a task execution result, and to transmit the task execution result to the first intelligent agent. Intelligent agent system.

48. The aforementioned intelligent agent system The system further comprises a system intelligent agent for transmitting the task guidance information to the first intelligent agent and the second intelligent agent, respectively, wherein the task guidance information is generated by the system intelligent agent based on input text information and the system intelligent agent's prompt template. The intelligent agent system according to claim 47.

49. At least one processor, The system comprises at least one processor and a memory that is communicated with by it, The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the method according to any one of claims 1 to 12 or any one of claims 13 to 23. Electronic devices.

50. A non-temporary computer-readable storage medium storing computer instructions that cause a computer to perform the method according to any one of claims 1 to 12, or the method according to any one of claims 13 to 23.

51. A program for implementing the method according to any one of claims 1 to 12, or any one of claims 13 to 23, when executed by a processor in a computer.

Images