Story generation system, and program for story generation system

Abstract

To provide a story generation system capable of storing a story obtained after a user as a story creator reflects user's intension about a story to tune the same.SOLUTION: A story generation system 100 includes a user terminal 110A and a server 120. The server uses pre-learned artificial intelligence means 131 to execute text data generation of a plurality of chapters of stories on the basis of title information TL and outline information AB of a story from a user terminal, and transmits the obtained generation text data to the user terminal. The server uses the pre-learned artificial intelligence means to execute a change in the generation text data on the basis of change instruction information from the user terminal, and transmits obtained changed generation text data GT1 to the user terminal. When there is a storage / disclosure operation in the user terminal, the server stores and discloses the changed generation text data GT1.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a story creation system that includes a user terminal and a server, in which the server creates a story based on information input from the user terminal, and a program for the system. [Background technology]

[0002] Conventionally, there is known an information processing device that includes a language data receiving unit that receives language data in response to a request from a user terminal, a language data processing unit that processes the language data to generate basic summary information that forms the basis for generating a summary, a transmitting unit that transmits presentation information including the basic summary information to the user terminal, an editing information receiving unit that receives editing information related to the presentation information from the user terminal, and a summary generation unit that provides the editing information to a large-scale language model that receives input of the basic summary information and generates a summary sentence that reflects the editing information (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2023-73095 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional information processing devices described above were limited to generating summaries of basic summary information using large-scale language models, and therefore had the problem that it was difficult to respond to the generation of new stories such as novels.

[0005] Therefore, the present invention is intended to solve the problems of the prior art as described above. In other words, the object of the present invention is to provide a story generation system and a program therefor that allow a user, as a story creator, to tune a story to reflect his or her own intentions as desired, and to save the final product when he or she is relatively satisfied with it. [Means for solving the problem]

[0006] The invention according to claim 1 is a story generation system comprising a user terminal and a server, in which the server generates a story based on information input from the user terminal, and when story title information and summary information are transmitted from a first user terminal, the server uses a pre-trained artificial intelligence means to generate text data for a multi-chapter story based on the received title information and summary information, and transmits the generated text data for the multi-chapter story obtained by the execution to the first user terminal, and the first user terminal displays the received generated text data for the multi-chapter story on a browser or outputs it as audio, and transmits the generated text data for the multi-chapter story from the first user terminal. When the change instruction information is sent to a server, the server uses a pre-trained artificial intelligence means to change the generated text data of the multi-chapter story based on the received change instruction information, and sends the changed generated text data of the multi-chapter story obtained through the change to a first user terminal, and the first user terminal displays or audibly outputs the received changed generated text data of the multi-chapter story in a browser, and when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data or changed generated text data of the multi-chapter story that was being displayed or audibly output on the first user terminal at that time, thereby solving the above-mentioned problem.

[0007] The invention of claim 2 further solves the above-mentioned problem by, in addition to the configuration of the story generation system described in claim 1, a second user terminal different from the first user terminal and capable of communicating with the server accesses the server, and the browser of the second user terminal displays title information and summary information for the multi-chapter story, which is the published generated text data or changed generated text data, and when character attribute information and identification information of the second user are input into the browser of the second user terminal and the character attribute information for the multi-chapter story and identification information of the second user are sent from the second user terminal to the server, the server uses a pre-trained artificial intelligence means to generate character-reflected changed generated text data that reflects the character attribute information based on the generated text data or the changed generated text data, and sends it to the second user terminal based on the identification information of the second user, and the second user terminal displays the received character-reflected changed generated text data on the browser or outputs it as audio.

[0008] The invention of claim 3 further solves the above-mentioned problem by, in addition to the configuration of the story generation system described in claim 1 or claim 2, configuring the following: post-change generated text data reflecting the characters of a story having multiple chapters is sent from the server to the second user terminal, divided by chapter, and when desired information for the next story is input in the browser of the second user terminal and the desired information for the next story is sent from the second user terminal to the server, the server uses a pre-trained artificial intelligence means to generate post-change generated text data reflecting the desired information for the next story based on the post-change generated text data reflecting the characters for the next story and thereafter, and at a specified timing, sends the next post-change generated text data reflecting the desires to the second user terminal, and the second user terminal displays or outputs as audio the received post-change generated text data reflecting the desires in the browser.

[0009] The invention according to claim 4 further comprises the structure of the story generation system as recited in claim 3, wherein a third user terminal which is capable of communicating with the server and is different from the first user terminal and the second user terminal accesses the server, and a browser of the third user terminal displays title information and summary information for the multi-chapter story which is the published generated text data or the changed generated text data, and when attribute information of a character different from the target of a character entered by the second user and identification information of the third user are entered in the browser of the third user terminal and the attribute information of the character for the multi-chapter story and the identification information of the third user are transmitted from the third user terminal to the server, the server uses a pre-trained artificial intelligence means to generate changed generated text data reflecting the attribute information of the characters based on the generated text data or the changed generated text data, and transmits the generated text data to the third user based on the identification information of the third user. The above-mentioned problem is further solved by the configuration in which the server transmits the requested information for the next story from the second user to the third user terminal, the third user terminal displays the received post-change generated text data reflecting the requested information for the next story by the second user and the requested information for the next story by the third user, and when requested information for the next story is input into the browser of the third user terminal and sent from the third user terminal to the server, the server uses the pre-trained artificial intelligence means to generate post-change generated text data reflecting the requested information for the next story by the second user and the requested information for the next story by the third user based on the post-change generated text data reflecting the requested information for the next story by the second user and the requested information for the next story by the third user, and when the specified timing arrives, the server transmits the next post-change generated text data reflecting the requested information for the next story by the second user terminal and the third user terminal, and the second user terminal and the third user terminal display the received post-change generated text data reflecting the requested information in the browser or output it as sound.

[0010] The invention of claim 5 further solves the above-mentioned problem by configuring the story generation system as described in claim 4, in addition to the above-mentioned problem, so that the second user terminal and the third user terminal each transmit location information of the user terminal to a server, and the server generates position / request-reflecting changed generated text data that reflects the location information received as location information for the actions of the characters that have been set respectively using a pre-trained artificial intelligence means, and when the specified timing arrives, transmits the next set of position / request-reflecting changed generated text data to the second user terminal and the third user terminal, and the second user terminal and the third user terminal display or output as audio the received position / request-reflecting changed generated text data in a browser.

[0011] The invention according to claim 6 is a program for a story generation system in which a server generates a story based on information input from a user terminal, the program including a title / summary transmission step in which the first user terminal transmits title information and summary information of the input story to the server based on an operation of a first user at a first user terminal, the first user terminal being the user terminal; a generation execution step in which the server executes text data generation of a multi-chapter story using pre-trained artificial intelligence means based on the received title information and summary information; a rough story transmission step in which the server transmits the generated text data of the multi-chapter story obtained by execution to the first user terminal; a rough story display / audio output step in which the first user terminal displays or sounds the received generated text data of the multi-chapter story on a browser; The above-mentioned problem is solved by having the above-mentioned system including a change instruction sending step of sending change instruction information for the generated text data of a chapter story to a server, a story change execution step in which the server executes changes to the generated text data of the multi-chapter story using a pre-trained artificial intelligence means based on the received change instruction information, a changed story sending step in which the server transmits the changed generated text data of the multi-chapter story obtained by the execution to a first user terminal, a changed story display / audio output step in which the first user terminal displays or outputs as audio the changed generated text data of the multi-chapter story received in a browser, and a save / publish step in which, when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data of the multi-chapter story or the changed generated text data that was being displayed or output as audio on the first user terminal at that time. Effect of the Invention

[0012] The story creation system of the present invention is equipped with a user terminal and a server, which not only enables the server to create a story based on information input from the user terminal, but also provides the following unique effects.

[0013] According to the story generation system of the invention of claim 1, a multi-chapter story is generated based on the story outline thought up by the first user of the first user terminal, and the specific intentions of the first user are reflected in the modified generated text data according to the first user's wishes. The modified generated text data is then made public by a save and publish operation, allowing the first user to have a creator experience. In other words, the first user, as the story creator, can tune the story to reflect his or her own intentions as desired, and can save it when he or she is relatively satisfied with the final product.

[0014] According to the story generation system of the invention of claim 2, in addition to the effects achieved by the invention of claim 1, the attribute information of the characters set by the second user is reflected in the multi-chapter story, and the reflected multi-chapter story is displayed or output as audio on the second user's own terminal, allowing the second user to enjoy a multi-chapter story in which the second user is a character. Additionally, second users can also have a creator experience.

[0015] According to the story generation system of the invention of claim 3, in addition to the effects of the invention of claim 1 or claim 2, the second user's requests are appropriately reflected in the next play and thereafter, so that the story is created in accordance with the second user's requests while maintaining the plot of the first user to a certain extent, allowing the second user to enjoy a story that suits his or her tastes. Additionally, second users can also have a creator experience.

[0016] According to the story generation system of the invention of claim 4, in addition to the effect achieved by the invention of claim 3, a story is created in which multiple readers each participate as a character, so that second and third users, who are also readers, can enjoy the distributed story together. Furthermore, the requests of the second and third users, who are readers, are reflected appropriately in the next story to be distributed without the second and third users knowing the content of their requests, and since the story does not develop according to one's own requests, an element of surprise is added, allowing readers to enjoy stories with interesting developments that they could not have predicted.

[0017] According to the story generation system of the invention of claim 5, in addition to the effects achieved by the invention of claim 4, location information of the movement ranges of the second and third readers is displayed as information on the movement ranges of the characters in the story being distributed, so that the second and third readers can enjoy the story while feeling a sense of familiarity with the characters that have been set up. Furthermore, since the location information of the range of movement of the second and third users, who are readers, affects the behavior of the characters from the next time onwards, it is possible to create a sense of realism as if the reader and the characters are linked.

[0018] According to the program of the story generation system of the invention of claim 6, similar to the effect achieved by the invention of claim 1, a multi-chapter story is generated based on the outline of the story thought up by the first user of the first user terminal, and the specific intentions of the first user are reflected in the generated text data after modification according to their wishes, and the data is then made public by a save and publish operation, allowing the first user to have a creator experience. In other words, the first user, as the story creator, can tune the story to reflect his or her own intentions as desired, and can save it when he or she is relatively satisfied with the final product. [Brief description of the drawings]

[0019] [Figure 1] 1 is a diagram showing the concept of a story generation system according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a flowchart showing an example of the operation of the story generation system according to the embodiment of the present invention. [Diagram 3] FIG. 13 is a diagram showing an example of a state in which title information and summary information have been input on a story creation screen for a story setter displayed on a browser of a first user terminal in the story creation system according to an embodiment of the present invention. [Figure 4] FIG. 13 is a diagram showing an example of generated text data displayed on a story create screen for a story setter displayed on a browser of a first user terminal of the story creation system according to an embodiment of the present invention. [Diagram 5] FIG. 13 is a diagram showing an example of changed generated text data displayed on a story create screen for a story setter displayed on a browser of a first user terminal in the story creation system according to an embodiment of the present invention. [Figure 6] FIG. 13 is a diagram showing an example of a story creation publishing screen displayed on a browser of a second user terminal of the story creation system according to an embodiment of the present invention. [Figure 7] FIG. 13 is a diagram showing an example of how characters are selected and attribute information is entered on a story subscriber creation screen displayed on a browser of a second user terminal in the story generation system according to an embodiment of the present invention. [Figure 8] FIG. 13 is a diagram showing an example of generated text data after changes reflecting characters displayed on a story subscriber creation screen displayed on a browser of a second user terminal of a story generation system according to an embodiment of the present invention. [Figure 9] FIG. 13 is a diagram showing an example of request information input on a story subscriber creation screen displayed on a browser of a second user terminal of the story creation system according to an embodiment of the present invention. [Figure 10] A figure showing an example of generated text data after request reflection changes displayed on a story subscriber creation screen displayed on a browser of a second user terminal of a story creation system which is an embodiment of the present invention. [Figure 11]FIG. 13 is a diagram showing an example of how characters are selected and attribute information is entered on a story subscriber creation screen displayed on a browser of a third user terminal of the story generation system according to an embodiment of the present invention. [Figure 12] A figure showing an example of requested information being input after the generated text data after changes reflecting characters are displayed on the story subscriber creation screen displayed on the browser of a third user terminal of a story creation system which is an embodiment of the present invention. [Figure 13] 11 is a diagram for explaining an example of the operation of the story creation system according to an embodiment of the present invention when request information from a second user terminal and request information from a third user terminal are reflected in a story. FIG. [Figure 14] A figure showing an example of generated text data after request reflection changes displayed on a story subscriber creation screen displayed on a browser of a third user terminal of a story generation system which is an embodiment of the present invention. [Figure 15] A diagram showing the state in which the location information setting of a second user terminal of a story creation system according to an embodiment of the present invention is ON. [Figure 16] FIG. 13 is a diagram for explaining an example of the operation of the story creation system according to an embodiment of the present invention when reflecting location information of a second user terminal and location information of a third user terminal in a story. [Figure 17] FIG. 13 is a diagram showing an example of generated text data after position and request reflection changes are displayed on a story subscriber creation screen displayed on a browser of a second user terminal in a story generation system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] The story generation system of the present invention includes a user terminal and a server, and when story title information and summary information are transmitted from a first user terminal to the server, the server generates text data for the multi-chapter story using pre-trained artificial intelligence means based on the received title information and summary information, and transmits the generated text data for the multi-chapter story obtained by the generation to the first user terminal, and the first user terminal displays the received generated text data for the multi-chapter story on a browser or outputs it as audio, and when modification instruction information for the generated text data of the multi-chapter story is transmitted from the first user terminal to the server, the server modifies the generated text data of the multi-chapter story using the pre-trained artificial intelligence means based on the received modification instruction information. The system is configured so that the multi-chapter story is executed, and the modified generated text data of the multi-chapter story obtained by the execution is sent to the first user terminal, and the first user terminal displays the received modified generated text data of the multi-chapter story in a browser or outputs it as audio, and when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data or modified generated text data of the multi-chapter story that was being displayed or output as audio on the first user terminal at that time, thereby allowing the first user, as a story creator, to tune the story to reflect his or her own intentions as desired, and allowing the first user to save the story when he or she is relatively satisfied with the final product, so that the specific implementation can be any one. Furthermore, the program for the story generation system of the present invention includes a title / summary transmission step in which the first user terminal transmits input story title information and summary information to the server based on an operation of the first user at the first user terminal, which is a user terminal; a generation execution step in which the server executes text data generation of the multi-chapter story using pre-trained artificial intelligence means based on the received title information and summary information; a rough story transmission step in which the server transmits the generated text data of the multi-chapter story obtained by execution to the first user terminal; a rough story display / audio output step in which the first user terminal displays or outputs as audio the received generated text data of the multi-chapter story on a browser; a change instruction transmission step in which the first user terminal transmits change instruction information for the input generated text data of the multi-chapter story to the server based on a change instruction operation at the first user terminal; the server transmits the modified generated text data of the multi-chapter story obtained by the execution to the first user terminal; a modified story display / audio output step in which the first user terminal displays the received modified generated text data of the multi-chapter story in a browser or outputs it as audio; and a save / publish step in which, when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data or modified generated text data of the multi-chapter story that was being displayed or output as audio on the first user terminal at that time, thereby allowing the first user, as a story creator, to tune the story to reflect his or her own intentions as desired and to save the story when he or she is reasonably satisfied with the result.The specific implementation of this system is not critical as long as it is possible to do so.

[0021] For example, the user terminal may be a desktop personal computer terminal, a notebook personal computer terminal, a smartphone terminal, a tablet terminal, or the like that sends and receives information, and may be any terminal that can be freely connected to a server via a communication network including a wide area network, such as the Internet, a local network, or a telephone line. Furthermore, the first server and the second server may each be a single server or multiple servers on a cloud. The pre-trained artificial intelligence means may be composed of an interactive model, also known as a large-scale language model, such as ChatGPT (Generative Pre-trained Transformer) (hereinafter referred to as ChatGPT), and may be configured to be installed on one server or multiple servers on the cloud. EXAMPLES

[0022] A story creation system 100 according to an embodiment of the present invention will be described below with reference to FIGS. 1 is a diagram showing the concept of a story creation system 100 according to an embodiment of the present invention, FIG. 2 is a chart showing an example of the operation of the story creation system 100 according to an embodiment of the present invention, FIG. 3 is a diagram showing an example of how title information TL and summary information AB are input on a story setter's story create screen 112 displayed on a browser 111 of a first user terminal 110A of the story creation system 100 according to an embodiment of the present invention, FIG. 4 is a diagram showing an example of generated text data GT displayed on a story setter's story create screen 112 displayed on a browser 111 of a first user terminal 110A of the story creation system 100 according to an embodiment of the present invention, FIG. 5 is a diagram showing an example of changed generated text data GT1 displayed on a story setter's story create screen 112 displayed on a browser 111 of a first user terminal 110A of the story creation system 100 according to an embodiment of the present invention, and FIG. 6 is a diagram showing an example of how changed generated text data GT1 are displayed on a story setter's story create screen 112 displayed on a browser 111 of a second user terminal 110B of the story creation system 100 according to an embodiment of the present invention. FIG. 11 shows an example of a story create public screen 113 shown in FIG. 7, FIG. 8 shows an example of a state in which characters are selected and attribute information CT is input on a story subscriber create screen 114 shown on a browser 111 of a second user terminal 110B of the story generation system 100 according to an embodiment of the present invention, and FIG. 9 shows an example of a state in which characters are selected and attribute information CT is input on a story subscriber create screen 114 shown on a browser 111 of a second user terminal 110B of the story generation system 100 according to an embodiment of the present invention. FIG. 9 is a diagram showing an example of requested information RQ being input on the story subscriber create screen 114 shown on the browser 111 of the second user terminal 110B of the story generation system 100 according to an embodiment of the present invention. FIG. 10 is a diagram showing an example of requested reflected version post-change generated text data GT3 being displayed on the story subscriber create screen 114 shown on the browser 111 of the second user terminal 110B of the story generation system 100 according to an embodiment of the present invention. FIG.FIG. 12 is a diagram showing an example of how characters are selected and attribute information CT is input on the story subscriber create screen 114 displayed on the browser 111 of the third user terminal 110C of the story generation system 100, which is an embodiment of the present invention. FIG. 13 is a diagram explaining an example of the operation when the requested information RQ from the second user terminal 110B and the requested information RQ from the third user terminal 110C of the story generation system 100, which is an embodiment of the present invention, are reflected in the story. FIG. 14 is a diagram showing an example of the operation when the requested information RQ from the second user terminal 110B and the requested information RQ from the third user terminal 110C of the story generation system 100, which is an embodiment of the present invention, are reflected in the story. FIG. 15 is a diagram showing an example of the location information LC setting of the second user terminal 110B of the story creation system 100 according to an embodiment of the present invention being ON. FIG. 16 is a diagram explaining an example of the operation when the location information LC of the second user terminal 110B and the location information LC of the third user terminal 110C of the story creation system 100 according to an embodiment of the present invention are reflected in a story. FIG. 17 is a diagram showing an example of the location and request-reflecting changed generated text data GT4 displayed on the story subscriber create screen 114 shown by the browser 111 of the second user terminal 110B of the story creation system 100 according to an embodiment of the present invention.

[0023] As shown in FIG. 1, a story generation system 100 according to an embodiment of the present invention includes a first user terminal 110A and a second user terminal 110B as examples of user terminals, and a first server 120 and a second server 130 as examples of servers. The first server 120 is configured to generate a story using chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the information input from the first user terminal 110A. In this embodiment, the story title information TL and summary information AB are transmitted to the first server 120 from the first user terminal 110A. Then, the first server 120 generates text data of a multi-chapter story using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received title information TL and summary information AB.

[0024] Then, the first server 120 transmits the generated text data GT of the multi-chapter story obtained by the execution to the first user terminal 110A. The first user terminal 110A then displays the received generated text data GT of the multi-chapter story on the browser 111 or outputs it as audio. Furthermore, it is assumed that modification instruction information PT for the generated text data GT of a multi-chapter story is transmitted from the first user terminal 110A to the server. Then, the first server 120 executes modification of the generated text data GT of the multi-chapter story using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received modification instruction information PT.

[0025] Then, the first server 120 transmits the changed generated text data GT1 of the multi-chapter story obtained by the execution to the first user terminal 110A. Then, the first user terminal 110A displays on the browser 111 or outputs as audio the received post-change generated text data GT1 of the multi-chapter story. Furthermore, when a save / publish operation is performed on the first user terminal 110A, the first server 120 is configured to save and publish the generated text data GT or the changed generated text data GT1 of the multi-chapter story that was being displayed or output as audio on the first user terminal 110A at that time.

[0026] As a result, generated text data GT, which is a multi-chapter story, is generated in accordance with the outline of the story thought up by the first user of the first user terminal 110A, and modified generated text data GT1 is created to reflect the specific intentions of the first user according to his or her wishes, and is then made public by a save and publish operation. As a result, the first user can have a creator experience. In other words, the first user, as the story creator, can tune the story to reflect his or her own intentions as desired, and can save it when he or she is relatively satisfied with the final product.

[0027] Next, an example of the operation of the story creation system 100 will be described in more detail. As shown in FIG. 2, in step S1, which is a step for determining whether or not a title / summary input / send operation has been performed, title information TL and summary information AB are input by the first user at the first user terminal 110A, and the first user terminal 110A further determines whether or not a send operation has been performed. More specifically, as shown in FIG. 3, when an operation for logging in to the story generation system 100 is performed on the first user terminal 110A, the browser 111 of the first user terminal 110A displays a story creation screen 112 for the story setter.

[0028] The story creation screen 112 is provided with a title input field 112a, a summary input field 112b, a story element item selection field 112c, and a "Send" button 112d. Then, if the first user terminal 110A determines that title information TL has been entered in the title input field 112a and summary information AB has been entered in the summary input field 112b, and that the "Send" button 112d has been operated, it proceeds to step S2; on the other hand, if it determines that this has not yet been done, it repeats step S1. When a story element item selection 112c is selected by checking it, the content of that item is input into summary input field 112b.

[0029] In step S2, which is a title / summary transmission step, the first user terminal 110A transmits the input story title information TL and summary information AB to the server. In step S3, as a generation execution step, the first server 120 generates text data for a multi-chapter story using chat GPT, an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received title information TL and summary information AB. In step S4, which is a rough story transmission step, the first server 120 transmits generated text data GT of the executed multi-chapter story to the first user terminal 110A.

[0030] In step S5, as a rough story display / audio output step, the first user terminal 110A displays on the browser 111 or outputs as audio the generated text data GT of the received multi-chapter story. More specifically, as shown in FIG. 4, the received generated text data GT of a story of multiple chapters is displayed, for example, in a story draft display area 112e of a story create screen 112 of the browser 111 of the first user terminal 110A. At this time, the change instruction input area 112f of the story creation screen 112 allows the user to freely input change instructions.

[0031] The story creation screen 112 also has a "Send change instructions" button 112g and a "Save and publish" button 112h. When a speaker icon button provided on the story creation screen 112 is operated, the generated text data GT corresponding to that portion is output as voice by the speaker of the first user terminal 110A. This allows the first user to check the contents of a story that spans multiple chapters. If the first user wishes to further improve the content, a change instruction input area 112f of the story creation screen 112 is provided where change instructions can be freely input. The change instruction input field in the change instruction input area 112f is provided for each chapter of the story. That is, for example, if the content of chapter 3 is to be changed, a change instruction may be input in the change instruction input field in the change instruction input area 112f corresponding to the location of chapter 3 in the story draft display area 112e.

[0032] In step S6, as a change instruction presence / absence determination step, the first user terminal 110A determines whether or not a change instruction has been input and a transmission operation has been performed on the story creation screen 112 of the browser 111 of the first user terminal 110A. More specifically, as shown in FIG. 4, for example, if it is determined that the first user has input a change instruction into the portion of the change instruction input area 112f corresponding to the story of chapter 3 and operated the “Send change instruction” button 112g, it is determined that a change instruction has been input and a send operation has been performed, and the process proceeds to step S7; on the other hand, if it is determined that no change instruction has been input yet, the process proceeds to step S11.

[0033] In step S7, as a modification instruction sending step, first user terminal 110A sends to first server 120 modification instruction information PT of created text data GT of the input multi-chapter story. The change instruction information PT includes information on the input fields for change instructions in the change instruction input area 112f that correspond to the locations of each chapter of the story in the story draft display area 112e. That is, the change instruction information PT includes information regarding which chapter the change instruction pertains to. In step S8, as a story change execution step, the first server 120 executes changes to the generated text data GT of the multi-chapter story using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received change instruction information PT. In other words, a change is made to reflect the first user's request in the generated text data GT.

[0034] In step S9, as a changed story transmitting step, first server 120 transmits changed generated text data GT1 of the multi-chapter story obtained by execution to first user terminal 110A. In step S10, as a changed story display / audio output step, the first user terminal 110A displays on the browser 111 or outputs as audio the received changed generated text data GT1 of the story of the multiple chapters.

[0035] More specifically, as shown in FIG. 5, in a story draft display area 112e of a story create screen 112 of the browser 111 of the first user terminal 110A, as an example, post-change generated text data GT1 of the received multi-chapter story is displayed. At this time, the change instruction input area 112f of the story creation screen 112 allows the user to freely input change instructions. The story creation screen 112 also has a "Send change instructions" button 112g and a "Save and publish" button 112h.

[0036] This allows the first user to check the content of the polished multi-chapter story. If the first user wishes to further improve the content, a change instruction input area 112f of the story creation screen 112 is provided where change instructions can be freely input. Also, a "Save / Publish" button 112h is provided for the first user to save and publish the content if he / she is satisfied with it.

[0037] In step S11, as a save / publish operation presence / absence determination step, the first user terminal 110A determines whether or not the "save / publish" button 112h has been operated on the story creation screen 112 of the browser 111 of the first user terminal 110A. If it is determined that the button has been operated, the process proceeds to step S12; if it is determined that the button has not been operated yet, the process returns to step S6 and waits for either the operation of the “Send change instruction” button 112g or the operation of the “Save and publish” button 112h.

[0038] In step S12, which is a save / publish step, the first server 120 saves and publishes the generated text data GT or the changed generated text data GT1 of the multi-chapter story that was being displayed or output as audio on the first user terminal 110A when the "Save / Publish" button 112h was operated. As a result, as described above, generated text data GT, which is a multi-chapter story based on the plot of the story thought up by the first user of first user terminal 110A, is generated, and the specific intentions of the first user are reflected in the generated text data GT1 after modification according to the wishes of the first user, which is then made public by a save and publish operation. As a result, the first user can have a creator experience. In other words, the first user, as the story creator, can tune the story to reflect his or her own intentions as desired, and can save it when he or she is relatively satisfied with the final product.

[0039] Furthermore, as shown in FIG. 6, when a second user terminal 110B, which is capable of communicating with the first server 120 and is different from the first user terminal 110A, accesses the first server 120, the browser 111 of the second user terminal 110B displays a story creation public screen 113. This story creation public screen 113 displays the title information TL and summary information AB of the story that the first user has set to be public. Furthermore, the story creation public screen 113 is provided with a "Proceed to purchase procedure" button 113a, which allows a second user to purchase the story set by the first user. Then, when the second user operates the "Proceed to purchase procedure" button 113a to complete the procedure, the generated text data GT of the story set by the first user or the changed generated text data GT1 is displayed in the browser 111 of the second user terminal 110B.

[0040] Furthermore, in this embodiment, as shown in FIG. 7, the second user terminal 110B accesses the first server 120, and the browser 111 of the second user terminal 110B displays a create screen 114 for story subscribers. The create screen 114 for story subscribers includes a character selection field 114a, an attribute information input field 114b, and a "Send" button 114c. When the character selection 114a is selected, the attribute information input field 114b for that character becomes available for input, and the name of that character becomes available for modification. It is also assumed that the attribute information CT of the characters is input on the create screen 114 for story subscribers on the browser 111 of the second user terminal 110B, and the "Send" button 114c is operated. Then, the attribute information CT of the characters in the multi-chapter story and the identification information of the second user are transmitted from the second user terminal 110B to the first server 120. Here, the identification information of the second user may be login information at the time of login, identification information at the time of purchase, email address information of the second user, or the like. It is also possible to change the name of the character selected as the character's attribute information CT to the name of the second user or any other name.

[0041] Furthermore, the first server 120 generates character-reflecting changed generated text data GT2 that reflects the received character attribute information CT based on the generated text data GT or the changed generated text data GT1 using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 transmits the post-change generated text data GT2 reflecting the characters to the second user terminal 110B based on the identification information of the second user. Then, as shown in FIG. 8, the second user terminal 110B is configured to display the received post-change generated text data GT2 reflecting the characters on the story subscriber create screen 114 of the browser 111 or output it as audio.

[0042] As a result, the attribute information CT of the characters set by the second user is reflected in the changed generated text data GT2 reflecting the characters, which is a multi-chapter story, and the changed generated text data GT2 reflecting the characters, which is a multi-chapter story, is displayed or output as audio on the second user's own terminal 110B. As a result, the second user can enjoy the character-reflecting post-change generated text data GT2, which is a multi-chapter story in which the second user is a character. Additionally, second users can also have a creator experience.

[0043] In this embodiment, as shown in FIG. 9, the post-change generated text data GT2 reflecting the characters of a story having multiple chapters is transmitted from the first server 120 to the second user terminal 110B for each chapter. Then, the story subscriber create screen 114 of the browser 111 of the second user terminal 110B displays the post-change generated text data GT2 reflecting the characters in the story for each chapter.

[0044] Here, the create screen 114 for story subscribers includes a request input field 114d for the next time onwards and a "Send" button 114c. It is also assumed that the request information RQ for the next story is entered in the request input field 114d on the story subscriber create screen 114 of the browser 111 of the second user terminal 110B, and the "Send" button 114c is operated. Then, request information RQ for the next story is transmitted to the first server 120 from the second user terminal 110B.

[0045] Next, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate post-change generated text data GT3 reflecting the received request information RQ for the next story based on the post-change generated text data GT2 reflecting the characters for the next story and thereafter. Then, at a predetermined timing, for example, three days after the distribution date of the current story, the first server 120 transmits the next request-reflecting post-change generated text data GT3 to the second user terminal 110B. Then, as shown in FIG. 10, the second user terminal 110B is configured to display the received request-reflecting post-change generated text data GT3 on the story subscriber create screen 114 of the browser 111 or output it as audio.

[0046] This allows the second user's requests to be reflected appropriately in future episodes, resulting in a story that meets the second user's requests while maintaining the first user's plot to some extent. As a result, the second user can enjoy the story in their own way. Additionally, second users can also have a creator experience.

[0047] Furthermore, in this embodiment, it is assumed that a third user different from the first and second users purchases the story set by the first user on the story creation public screen 113. In this case, as shown in FIG. 11, a third user terminal 110C, which is different from the first user terminal 110A and the second user terminal 110B, accesses the first server 120, and the browser 111 of the third user terminal 110C displays a create screen 114 for story subscribers. The create screen 114 for story subscribers includes a character selection field 114a, an attribute information input field 114b, and a "Send" button 114c. When the character selection 114a is selected, the attribute information input field 114b for that character becomes available for input, and the name of that character becomes available for modification.

[0048] Suppose that on the create screen 114 for story subscribers on the browser 111 of the third user terminal 110C, attribute information CT of a character different from the target character already entered by the second user is entered, and the "Send" button 114c is operated. Then, the attribute information CT of the characters in the multi-chapter story and the identification information of the third user are transmitted from the third user terminal 110C to the first server 120. Here, the identification information of the third user may be login information, identification information at the time of purchase, email address information of the third user, or the like. It is also possible to change the name of the character selected as the character's attribute information CT to the name of a third user or any other name.

[0049] Furthermore, the first server 120 generates character-reflecting changed generated text data GT2 that reflects the received character attribute information CT based on the generated text data GT or the changed generated text data GT1 using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, the first server 120 transmits the character-reflecting post-change generated text data GT2 to the third user terminal 110C based on the identification information of the third user. Then, as shown in FIG. 12, the third user terminal 110C displays the received post-change generated text data GT2 reflecting the characters on the story subscriber create screen 114 of the browser 111 or outputs the same as sound.

[0050] The post-change generated text data GT2 reflecting the characters of a story having multiple chapters is transmitted from the first server 120 to the third user terminal 110C for each chapter. Then, the story subscriber create screen 114 of the browser 111 of the third user terminal 110C displays the post-change generated text data GT2 reflecting the characters in the story for each chapter. Here, the create screen 114 for story subscribers includes a request input field 114d for the next time onwards and a "Send" button 114c. Then, as shown in FIG. 12, it is assumed that the request information RQ for the next story is entered in the request input field 114d on the story subscriber create screen 114 on the browser 111 of the third user terminal 110C, and the "Send" button 114c is operated. Then, request information RQ for the next story is transmitted to the first server 120 from the third user terminal 110C.

[0051] Next, as shown in FIG. 13, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate changed generated text data GT3 reflecting the received requested information RQ for the next story from the second user and the requested information RQ for the next story from the third user, based on the changed generated text data GT2 reflecting the characters for the next story and thereafter. In other words, the first server 120 combines the requested information RQ for the next story by the second user and the requested information RQ for the next story by the third user, and prompts the combined requested information RQ and sends it to the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130.

[0052] Here, a multi-chapter story is delivered to a user terminal at a predetermined time, for example, every three days or every week, and the second user and third user are users who subscribe to the same story and who have entered and sent request information RQ for the next story for each chapter within the same period (the period from when the current chapter is delivered to when the next chapter is delivered). Then, at a predetermined timing, for example, three days after the current story is distributed, the first server 120 transmits the next request-reflecting post-change generated text data GT3 to the second user terminal 110B and the third user terminal 110C. Then, as shown in FIG. 14, the second user terminal 110B and the third user terminal 110C are configured to display or output as audio the received post-request reflected modified generated text data GT3 on the story subscriber create screen 114 of the browser 111.

[0053] This results in a story in which multiple readers, a second user (Elena Tanaka) and a third user (Alice Ito), participate as characters such as Sakie Matsumoto and Rika Yasuda, respectively. As a result, second and third-party readers can enjoy the stories being delivered together. Furthermore, the requests of the second and third users, who are readers, are reflected appropriately in the next story to be distributed without the other user knowing the content of their requests, creating an element of surprise as the story does not develop according to one's own requests. As a result, you can enjoy a story with unexpected and interesting developments.

[0054] Furthermore, if the second user (Elena Tanaka) and the third user (Alice Ito) finish reading the multi-chapter story through to the end and then subscribe again, and at least one of them enters and submits a request information RQ for the next story that is different from the request information RQ for the previous subscription, the content of the story for each chapter in this subscription will be different from the content of each chapter in the previous subscription. As a result, even if a second user (Elena Tanaka) and a third user (Alice Ito) subscribe again with the same members, they will be able to enjoy different developments each time.

[0055] In this embodiment, as shown in FIG. 15, second user terminal 110B and third user terminal 110C each transmit position information LC of the user terminal to first server 120 based on a setting operation by the user. Then, as shown in FIG. 16, the first server 120 generates position / request-reflecting changed generated text data GT4 that reflects the position information LC received as position information LC for the actions of each set character using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130. Then, at a predetermined timing, for example, three days after the current story is distributed, the first server 120 transmits the next set of position / desire-reflecting changed generated text data GT4 to the second user terminal 110B and the third user terminal 110C. Then, as shown in FIG. 17, the second user terminal 110B and the third user terminal 110C are configured to display or output as audio the received position / request-reflecting post-change generated text data GT4 on the story subscriber create screen 114 of the browser 111.

[0056] As a result, the location information LC of the movement ranges of the second and third users, who are readers, appears as information on the movement ranges of the characters in the story being distributed. As a result, second and third user readers can enjoy the story while feeling a sense of familiarity with the characters. Furthermore, the location information LC of the movement range of the second and third users, who are readers, will affect the behavior of the characters from the next time onwards. As a result, it is possible to create a sense of realism in which the reader feels connected to the characters.

[0057] The story generation system 100, which is an embodiment of the present invention obtained in this manner, includes a user terminal, a first server 120, and a second server 130. When the title information TL and summary information AB of the story are transmitted from the first user terminal 110A, which is a user terminal, to the first server 120, the first server 120 executes text data generation of the multi-chapter story using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, based on the received title information TL and summary information AB, and transmits the generated text data GT of the multi-chapter story obtained by the execution to the first user terminal 110A. The first user terminal 110A displays or outputs as audio the received generated text data GT of the multi-chapter story on the browser 111. When the change instruction information PT of the generated text data GT of the multi-chapter story is transmitted from the first user terminal 110A to the first server 120, the first server 120 converts the received change instruction information P Based on T, the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, is used to modify the generated text data GT of the multi-chapter story, and the modified generated text data GT1 of the multi-chapter story obtained by the modification is transmitted to the first user terminal 110A, and the first user terminal 110A displays the received modified generated text data GT1 of the multi-chapter story on the browser 111 or outputs it as audio. When a save / publish operation is performed on the first user terminal 110A, the first server 120 saves and publishes the generated text data GT or modified generated text data GT1 of the multi-chapter story that was being displayed or output as audio on the first user terminal 110A at that time. This allows the first user, as a story creator, to tune the story to reflect his or her own intentions as desired, and can save the story when he or she is relatively satisfied with the final product.

[0058] Furthermore, a second user terminal 110B, which is free to communicate with the first server 120 and different from the first user terminal 110A, accesses the first server 120, and the browser 111 of the second user terminal 110B displays the title information TL and summary information AB about the multi-chapter story, which is the published generated text data GT or the changed generated text data GT1. When the attribute information CT of the characters and the identification information of the second user are input in the browser 111 of the second user terminal 110B, the attribute information CT of the characters about the multi-chapter story and the identification information of the second user are transmitted from the second user terminal 110B to the first server 120, The second server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate changed generated text data GT2 reflecting the character's attribute information CT based on the generated text data GT or changed generated text data GT1, and transmits it to the second user terminal 110B based on the identification information of the second user.The second user terminal 110B then displays the received changed generated text data GT2 reflecting the character on the browser 111 or outputs it as audio.This allows the second user to enjoy a multi-chapter story in which the second user becomes a character, and the second user can also have a creator experience.

[0059] In addition, the character-reflecting version of the changed generated text data GT2 of a story having multiple chapters is transmitted from the first server 120 to the second user terminal 110B for each chapter. When the desired information RQ for the next story is input in the browser 111 of the second user terminal 110B and transmitted from the second user terminal 110B to the first server 120, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate the character-reflecting version of the changed generated text data GT2 for the next story and thereafter. Based on the data GT2, post-change generated text data GT3 reflecting the request information RQ for the next story is generated, and at a specified timing, the next post-change generated text data GT3 reflecting the request is transmitted to the second user terminal 110B, and the second user terminal 110B displays or outputs as audio the received post-change generated text data GT3 reflecting the request on the browser 111. This allows the second user to enjoy a story of his or her liking, and also allows the second user to have a creator experience.

[0060] Furthermore, a third user terminal 110C that is free to communicate with the first server 120 and is different from the first user terminal 110A and the second user terminal 110B accesses the first server 120, and the browser 111 of the third user terminal 110C displays the title information TL and summary information AB about the multi-chapter story that is the published generated text data GT or the changed generated text data GT1, and displays the attribute information CT of the characters that are different from the target of the characters entered by the second user in the browser 111 of the third user terminal 110C and the third user information AB. When the identification information of the third user is input and the character attribute information CT for the multi-chapter story and the identification information of the third user are transmitted from the third user terminal 110C to the first server 120, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate the character-reflected changed generated text data GT2 that reflects the character attribute information CT based on the generated text data GT or the changed generated text data GT1, and transmits the character-reflected changed generated text data GT2 to the third user terminal 110C based on the identification information of the third user. The third user terminal 110C displays or outputs the received character-reflecting version changed generated text data GT2 on the browser 111. When the request information RQ for the next story is input in the browser 111 of the third user terminal 110C and the request information RQ for the next story is transmitted from the third user terminal 110C to the first server 120, the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate the character-reflecting version changed generated text data GT2 for the next and subsequent stories based on the chat GPT. and generate request-reflecting changed generated text data GT3 that reflects the request information RQ for the next story from the second user and the request information RQ for the next story from the third user, and at a predetermined timing, transmit the next request-reflecting changed generated text data GT3 to the second user terminal 110B and the third user terminal 110C, and the second user terminal 110B and the third user terminal 110C display or output the received request-reflecting changed generated text data GT3 on the browser 111, therebyThe second and third users, who are readers, can enjoy the stories being distributed together, and can also enjoy their own unpredictable and interesting developments in the story.

[0061] In addition, the second user terminal 110B and the third user terminal 110C each transmit the location information LC of the user terminal to the first server 120, and the first server 120 uses the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130, to generate position / desire reflected post-change generated text data GT4 that reflects the location information LC received as position information LC for the actions of the respective set characters, and at a specified timing, transmits the next position / desire reflected post-change generated text data GT4 to the second user terminal 110B and the third user terminal 110C, and the second user terminal 110B and the third user terminal 110C display or output the received position / desire reflected post-change generated text data GT4 on the browser 111. This configuration allows the second and third users, who are readers, to enjoy the story while feeling a sense of familiarity with the respective set characters, and further creates a sense of realism as if the reader and the characters are linked.

[0062] Furthermore, the program of the story generation system 100 according to the embodiment of the present invention includes a title / summary transmission step S2 in which the first user terminal 110A transmits the title information TL and summary information AB of the input story to the first server 120 based on an operation of the first user on the first user terminal 110A which is a user terminal; a generation execution step S3 in which the first server 120 executes generation of text data of the multi-chapter story using the chat GPT which is an example of the pre-trained artificial intelligence means 131 of the second server 130 based on the received title information TL and summary information AB; a rough story transmission step S4 in which the first server 120 transmits the generated text data GT of the multi-chapter story obtained by the execution to the first user terminal 110A; a rough story display / audio output step S5 in which the first user terminal 110A displays or outputs as audio the received generated text data GT of the multi-chapter story on the browser 111; the first server 120 executes a change to the generated text data GT of the multi-chapter story based on the received change instruction information PT using the chat GPT, which is an example of the pre-trained artificial intelligence means 131 of the second server 130; a changed story sending step S9 in which the first server 120 transmits the changed generated text data GT1 of the multi-chapter story obtained by the execution to the first user terminal 110A; a changed story display / audio output step S10 in which the first user terminal 110A displays or outputs as audio the changed generated text data GT1 of the multi-chapter story received on the browser 111; and a save / publish step S12 in which, when a save / publish operation is performed on the first user terminal 110A, the first server 120 saves and publishes the generated text data GT or the changed generated text data GT1 of the multi-chapter story that was displayed or output as audio on the first user terminal 110A at that time.As a story creator, you can tune the story to reflect your own intentions as you wish, and when you are satisfied with the finished product, you can save it, so the effects are enormous. [Explanation of symbols]

[0063] 100 ··· Story Generation System 110A First user terminal 110B Second user terminal 110C Third user terminal 111 ··· Browser 112 (Story creator) Story creation screen 112a··· Title input field 112b... Description input field 112c... Story element selection 112d... "Send" button 112e··· Story draft display area 112f...Change instruction input area 112g... "Send Change Instructions" button 112h... "Save and Publish" button 113 ··· Story creation release screen (for purchase) 113a "Proceed to checkout" button 114 ··· Story subscriber creation screen 114a... Character selection 114b... Attribute information input field 114c... "Send" button 114d··· Request input field (for next time and beyond) 120 ··· First Server 130 Second Server 131 ··· Pre-trained AI method (Chat GPT) TL ··· Title Information AB ··· General Information GT: generated text data (for multi-chapter stories) GT1: Post-change generated text data (for multi-chapter stories) GT2: Text data generated after the characters are reflected GT3 ··· Text data generated after changes reflecting requests GT4 ··· Position · Request reflected version after change generated text data PT...Change instruction information CT ··· (Character) attribute information RQ: Request information (for the next story) LC ··· (user device) location information

Claims

1. A story generation system comprising a user terminal and a server, the server generating a story based on information input from the user terminal, When the title information and summary information of the story are transmitted from the first user terminal, which is the user terminal, to the server, the server generates text data of the story of multiple chapters using the pre-trained artificial intelligence means based on the received title information and summary information, and transmits the generated text data of the story of multiple chapters obtained by the execution to the first user terminal; The first user terminal displays or outputs the received generated text data of the story of the multiple chapters on a browser; When modification instruction information for the generated text data of the story of the multiple chapters is transmitted from the first user terminal to the server, the server executes modification of the generated text data of the story of the multiple chapters using the pre-trained artificial intelligence means based on the received modification instruction information, and transmits the modified generated text data of the story of the multiple chapters obtained by the modification to the first user terminal; The first user terminal displays or outputs the received post-change generated text data of the story of the multiple chapters on a browser; A story generation system characterized in that, when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data or changed generated text data of a multi-chapter story that was being displayed or output as audio on the first user terminal at that time.

2. a second user terminal that is capable of communicating with the server and is different from the first user terminal accesses the server, and a browser of the second user terminal displays title information and summary information about the multi-chapter story that is the published generated text data or the changed generated text data; When the character attribute information and the second user identification information are input into the browser of the second user terminal, and the character attribute information and the second user identification information for the multi-chapter story are transmitted from the second user terminal to a server, the server uses a pre-trained artificial intelligence means to generate character-reflecting changed generated text data that reflects the character attribute information based on the generated text data or the changed generated text data, and transmits the character-reflecting changed generated text data to the second user terminal based on the second user identification information; 2. The story generation system according to claim 1, wherein the second user terminal is configured to display the received post-change generated text data reflecting the characters on a browser or output the same as audio.

3. The generated text data after the character reflection version of the story having multiple chapters is transmitted from the server to the second user terminal for each chapter, When the desired information for the next story is input in the browser of the second user terminal and transmitted from the second user terminal to the server, the server uses the pre-trained artificial intelligence means to generate post-change generated text data reflecting the desired information for the next story based on the post-change generated text data reflecting the characters from the next story onward, and transmits the post-change generated text data reflecting the desired information for the next story to the second user terminal at a predetermined timing.

3. The story generation system according to claim 1, wherein the second user terminal is configured to display the received post-change generated text data reflecting the user's request on a browser or output the same as audio.

4. a third user terminal which is capable of communicating with the server and is different from the first user terminal and the second user terminal, accesses the server, a browser of the third user terminal displays title information and summary information for the multi-chapter story which is the published generated text data or the changed generated text data, character attribute information different from the target of the character input by the second user and identification information of the third user are input in the browser of the third user terminal, and the character attribute information for the multi-chapter story and the identification information of the third user are transmitted from the third user terminal to the server, the server uses a pre-trained artificial intelligence means to generate character-reflecting changed generated text data which reflects the character attribute information based on the generated text data or the changed generated text data, and transmits it to the third user terminal based on the identification information of the third user; The third user terminal displays the received character reflection version post-change generated text data on a browser or outputs it as audio; When the desired information for the next story is input in the browser of the third user terminal and transmitted from the third user terminal to the server, the server uses the pre-trained artificial intelligence means to generate post-change generated text data reflecting the desired information for the next story by the second user and the desired information for the next story by the third user based on the post-change generated text data reflecting the characters for the next story and thereafter, and transmits the next request-reflecting post-change generated text data to the second user terminal and the third user terminal at the predetermined timing; The story generation system according to claim 3, characterized in that the second user terminal and the third user terminal are configured to display the received post-request reflected modified generated text data on a browser or output it as audio.

5. The second user terminal and the third user terminal respectively transmit location information of the user terminal to a server; The server uses the pre-trained artificial intelligence means to generate position / request-reflecting post-change generated text data that reflects the position information received as position information for the actions of the respective set characters, and when the predetermined timing arrives, transmits the next position / request-reflecting post-change generated text data to the second user terminal and the third user terminal; The story generation system according to claim 4, characterized in that the second user terminal and the third user terminal are configured to display or output the received position / request reflected version of the generated text data in a browser or as audio.

6. A program for a story generation system in which a server generates a story based on information input from a user terminal, a title and summary transmission step in which the first user terminal transmits input story title information and summary information to the server based on an operation of the first user at the first user terminal, which is the user terminal; a generation execution step in which the server executes generation of text data of a multi-chapter story using a pre-trained artificial intelligence means based on the received title information and summary information; a rough story transmission step in which the server transmits generated text data of a story of multiple chapters obtained by the execution to a first user terminal; a rough story display / audio output step in which the first user terminal displays the received generated text data of the story of the multiple chapters on a browser or outputs the same as audio; a modification instruction sending step in which the first user terminal sends modification instruction information for the input generated text data of the story of the multiple chapters to a server based on a modification instruction operation on the first user terminal; a story modification execution step in which the server executes modification of the generated text data of the multi-chapter story using a pre-trained artificial intelligence means based on the received modification instruction information; a post-change story transmission step in which the server transmits post-change generated text data of the story of the multiple chapters obtained by the execution to a first user terminal; a changed story display / audio output step in which the first user terminal displays or outputs the received changed text data of the story of the multiple chapters on a browser; A program for a story generation system characterized in that it has a save / publish step in which, when a save / publish operation is performed on the first user terminal, the server saves and publishes the generated text data or changed generated text data of a multi-chapter story that was being displayed or output as audio on the first user terminal at that time.

Images