Computer systems and programs

Abstract

To provide a new technology that enables improved efficiency in generating texts such as scenarios. [Solution] The server system 1100 generates a first detailed document (scenario) in its generation unit and generates a summary document by summarizing it. Furthermore, while ensuring that the content of the summary does not change, it develops and expands the story from the summary to generate scenes and generates a new detailed document (second detailed document). The server system 1100 evaluates the new detailed document and repeats the summarization and expansion process by replacing the original detailed document with the new detailed document until it passes the evaluation.

Description

Technical Field

[0001] The present invention relates to a computer system and the like.

Background Art

[0002] Patent Document 1 describes a scenario plot generation device that generates a scenario plot of a story composed of a plurality of phases (corresponding to the beginning, middle, turning point, and end of a story). The scenario plot generation device of Patent Document 1 has a database in which blocks, which are samples of each phase of the scenario plot, are tagged and recorded in advance. The scenario plot generation device receives an input of tags from a user, reads out the blocks corresponding to the input tags, and generates a scenario plot.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As a technique different from the technique of Patent Document 1, a method of generating scenario data using a generation unit typified by generative AI (Artificial Intelligence) is known. For example, in the field of game production, methods for using the scenarios generated by the generation unit in game production are being explored.

[0005] In order to cause the generation unit to generate data, it is necessary to give the generation unit information (generation instruction information) for a generation instruction called a prompt. The generation instruction information includes a plurality of types of contexts that describe what to generate, under what prerequisite conditions (generation conditions) to generate, and what data to refer to for generation.

[0006] The user creates generation instruction information to obtain a scenario (output) with the desired specifications and content, and provides this to the generation unit. However, the generation unit does not always produce the scenario that the user envisioned.

[0007] In particular, as the amount of text increases, the generated scenarios tend to contain inconsistencies, excessive leaps in the story's development (so-called "super-realistic plot developments"), and unnecessary or boring plot points. Users have to read through long scenarios, and if the specifications and content do not match what they envisioned, they revise the generation instructions and feed them back to the generation unit to restart the generation process. Users have to repeat this process, which is one reason why production efficiency does not improve as much as desired despite utilizing the generation unit.

[0008] Furthermore, these problems are not limited to screenplays for films, plays, and games, but also apply to other forms of writing such as novels.

[0009] The problem that this invention aims to solve is to provide a new technology that enables improved efficiency in generating texts such as scenarios. [Means for solving the problem]

[0010] The first invention for solving the above problems is a computer system comprising: a summary text information acquisition control means (for example, the summary text information acquisition control unit 224 in Figure 23, steps S42 to S44 in Figure 24) that controls the acquisition of a first summary text information for a first detailed text information using a summary generation means (for example, the summary generation AI 12 in Figure 1, the summary generation unit 226 in Figure 23) capable of generating a summary or outline (hereinafter collectively referred to as "summary") for a given detailed text information; and a detailed text information acquisition control means (for example, the detailed text information acquisition control unit 210 in Figure 23, step S74 in Figure 25) that controls the acquisition of a second detailed text information for the first summary text information using an extension generation means (for example, the extension generation AI 14 in Figure 1, the extension generation unit 232 in Figure 23) capable of extending a given summary text information to generate detailed text information.

[0011] According to the first invention, a computer system can generate a new document based on the first detailed document by summarizing the original first detailed document and generating a second detailed document by expanding on the summary. This makes it possible to improve the efficiency of document generation.

[0012] Even if the initial detailed text contains inconsistencies, abrupt plot developments, or unnecessary and boring sections, summarizing it is highly likely that one or more of these flaws will be eliminated. Then, the story is developed and expanded based on this summary to generate new text. This makes it possible to generate a better text with fewer actual flaws compared to generating new text from scratch.

[0013] Of course, some inconsistencies may remain during the summarization process, but the expansion will be carried out based on those remaining inconsistencies. Therefore, parts that didn't make sense before summarization may become consistent, and parts that seemed like absurd developments are likely to be corrected into more appropriate developments.

[0014] The second invention is a computer system further comprising the above-described computer system, a repeat control means (for example, a repeat control unit 240 in Figure 23) that performs a cyclical repeat control, which repeatedly causes the summary text information acquisition control means to acquire new first summary text information for the second detailed text information as new first detailed text information, and then causes the detail text information acquisition control means to acquire new second detailed text information for the new first summary text information.

[0015] According to the second invention, the computer system can repeatedly perform summarization and expansion. Therefore, by repeatedly performing summarization and expansion, the original first detailed text is gradually corrected for inconsistencies and illogical developments, and transformed into a better text.

[0016] Furthermore, the third invention is a computer system further comprising detailed text information evaluation means (for example, detailed text evaluation AI17 in Figure 1, detailed text information evaluation unit 238 in Figure 23, and step S106 in Figure 25) for evaluating the second detailed text information, wherein the repeat control means executes the cycle repeat control based on the evaluation results of the detailed text information evaluation means.

[0017] According to the third invention, the computer system can evaluate the second detailed text information and perform summarization and expansion again based on the evaluation results. The computer system can automatically perform summarization and expansion multiple times until it can be evaluated that the original first detailed text has become a better text.

[0018] The fourth invention is a computer system in which, in the above-described computer system, the summary text information acquisition control means variably controls the amount of summarization by the summary generation means based on the number of repetitions of the loop repeat control (for example, step S138 in Figure 26).

[0019] The summarization amount is the length of the first summary text, indicating how much detail from the original first detailed text is omitted. On the other hand, the loop repeat control revises the original first detailed text to generate the second detailed text. However, if the second detailed text is summarized again with the same summarization amount, there is a possibility that even the parts that have become good sentences will be cut out. Therefore, according to the fourth invention, the computer system can suppress the waste of the results obtained by the loop repeat control by variably controlling the summarization amount based on the number of repetitions of the loop repeat control.

[0020] The fifth invention is a computer system in which the repeat control means performs a redo control that starts from either acquiring new first summary text information (for example, returning from step S54 to step S42 in Figure 24) or acquiring new second detailed text information (for example, returning from step S86 to step S72 in Figure 25).

[0021] According to the fifth invention, the computer system can restart from either acquiring new first summary text information or acquiring new second detailed text information.

[0022] The sixth invention further comprises, in the above-described computer system, a generation instruction information receiving means (for example, a generation instruction information receiving unit 204 in Figure 23) that receives given generation instruction information for generating new detailed text information, the summary generation means having a generation unit capable of generating the summary (for example, a summary generation AI 12 in Figure 1), and the summary text information acquisition control means generating summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information (for example, summary instruction information 604 in Figure 4, step S42 in Figure 24), The extended generation means has a generation unit capable of performing the extended generation and generating the detailed text information (for example, the extended generation AI 14 in Figure 1), and the detailed text information acquisition control means generates extended instruction information to be given to the generation unit of the extended generation means based on the generation instruction information (for example, the extended instruction information 612 in Figure 5, step S62 in Figure 25), and is a computer system.

[0023] Furthermore, the seventh invention is a computer system in which the summary instruction information includes information that indicates the summarization amount.

[0024] According to the sixth or seventh invention, a computer system can generate extension instruction information based on generation instruction information. For example, if extension instruction information is generated to instruct extension up to the amount of text required by the generation instruction information, it becomes possible to obtain second detailed text information with an amount of text comparable to that of the first detailed text information.

[0025] According to the eighth invention, in the above computer system, there is further provided generation instruction information receiving means for receiving given generation instruction information for generating new detailed text information. The summary generation means has a generation unit capable of generating the summary. The summary text information acquisition control means generates summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information. The extension generation means has a generation unit capable of performing the extension to generate the detailed text information. The detailed text information acquisition control means generates extension instruction information to be given to the generation unit of the extension generation means based on the generation instruction information. There is further provided loop repeat number determination means (for example, loop repeat number determination unit 242 in FIG. 23, step S32 in FIG. 24) for determining the number of repetitions by loop repeat control based on the generation instruction information. This is a computer system.

[0026] According to the eighth invention, a computer system can determine the number of repetitions by loop repeat control based on generation instruction information.

[0027] The ninth invention is a computer system further comprising: a generation instruction information receiving means for receiving given generation instruction information for generating new detailed text information; a summary generation means having a generation unit capable of generating the summary; a summary text information acquisition control means generating summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information; an extension generation means having a generation unit capable of performing the extension to generate the detailed text information; a detailed text information acquisition control means generating extension instruction information to be given to the generation unit of the extension generation means based on the generation instruction information; and a feedback control means (for example, the feedback control unit 244 in Figure 23, step S138 in Figure 26) for variably controlling the summary instruction information in the loop repeat control based on the evaluation result of the detailed text information evaluation means.

[0028] According to the ninth invention, the computer system can change the summary instruction information in the loop repeat control based on the evaluation results of the detailed text information evaluation means.

[0029] The tenth invention is a computer system in which the repeat control means performs the repeat control based on given retry instruction information (for example, summary instruction information 604 obtained via step S54 in Figure 24, and extended instruction information 612 obtained via step S86 in Figure 25).

[0030] According to the tenth invention, the computer system becomes capable of performing retry control based on retry instruction information.

[0031] The eleventh invention is a computer system further comprising a remaining portion designation means (for example, the remaining portion designation unit 222 in Figure 23, step S18 in Figure 24) for designating a specific portion of the first detailed text information to be retained in the summary, wherein the summary text information acquisition control means performs control to acquire the first summary text information while retaining the specific portion.

[0032] According to the eleventh invention, the computer system can retain a specific portion of the first detailed text information in the summary text information, and as a result, it can generate a second detailed text information that includes the specific portion.

[0033] The twelfth invention is a computer system further comprising a remaining portion designation means (for example, the remaining portion designation unit 222 in Figure 23, step S124 in Figure 26) for designating a specific portion of the second detailed text information to be retained in the summary, wherein the summary text information acquisition control means performs control in the loop repeat control to acquire the new first summary text information while retaining the specific portion.

[0034] According to the twelfth invention, the computer system can retain a specific portion of the first detailed text information in the summary text information during loop repeat control, and as a result, it becomes possible to generate a second detailed text information that includes the specific portion.

[0035] The thirteenth invention is a computer system further comprising a highly expanded portion designation means (for example, the highly expanded portion designation unit 234 in Figure 23, step S60 in Figure 25) for designating a specific portion of the first summary text information to have a relatively high degree of expansion, and the detailed text information acquisition control means controls the acquisition of the second detailed text information by performing the expansion with a relatively high degree of expansion on the designated portion.

[0036] According to the 13th invention, the computer system can perform a relatively high degree of expansion on a specific part of the first summary text information and convert it into second detailed text information.

[0037] The fourteenth invention is a computer system in which, in the above-described computer system, the summary text information acquisition control means has a summary generation condition setting means (for example, the summary generation condition setting unit 212 in Figure 23, step S42 in Figure 24) for setting summary generation conditions, and acquires the first summary text information by causing the summary generation means to generate a summary based on the summary generation conditions.

[0038] According to the 14th invention, a computer system can set summary generation conditions and generate a summary based on these conditions.

[0039] The fifteenth invention is a computer system in which, in the above-described computer system, the summary generation condition setting means sets the summary generation conditions based on the number of repetitions of the loop repeat control (for example, step S138 in Figure 26).

[0040] According to the 15th invention, the computer system becomes capable of setting summary generation conditions based on the number of repetitions of the loop repeat control.

[0041] Furthermore, the sixteenth invention is a computer system in which, in the above-described computer system, the summary generation condition setting means sets the summary generation conditions based on the first detailed text information (for example, step S42B in Figure 28).

[0042] According to the 16th invention, the computer system becomes capable of setting summary generation conditions based on first detailed text information.

[0043] The seventeenth invention is a computer system in which, in the above-described computer system, the summary text information acquisition control means acquires the first summary text information as text information in list format.

[0044] According to the 17th invention, a computer system can obtain first summary text information as text information in list format.

[0045] The eighteenth invention is a computer system in which the extension generation means performs the extension by adding new list-format information to the list-format information of the first summary text information.

[0046] According to the 18th invention, the computer system becomes capable of obtaining a second detailed text information which is added to the first summary text information.

[0047] Furthermore, the 19th invention is a computer system in which the detailed text information acquisition control means has an extended generation condition setting means (for example, the extended generation condition setting unit 218 in Figure 23, step S62 in Figure 25) for setting extended generation conditions, and the second detailed text information is acquired by causing the extended generation means to perform the extended generation based on the extended generation conditions.

[0048] According to the 19th invention, the computer system can set extended generation conditions and obtain second detailed text information based on these conditions.

[0049] The 20th invention is a computer system in which, in the above-described computer system, the extended generation condition setting means sets the extended generation conditions based on the first detailed text information (for example, step S62B in Figure 29).

[0050] According to the 20th invention, the computer system becomes capable of setting extended generation conditions based on first detailed text information.

[0051] The 21st invention is a computer system further comprising a repeat control means (for example, a repeat control unit 240 in Figure 23) that performs detailed repeat control to cause the detailed text information acquisition control means to repeatedly acquire the second detailed text information.

[0052] According to the 21st invention, the computer system becomes capable of repeatedly acquiring second detailed text information.

[0053] The 22nd invention is a computer system further comprising detailed text information evaluation means (for example, the detailed text information evaluation unit 238 in Figure 23, step S106 in Figure 25) for evaluating the second detailed text information, wherein the repeat control means executes the detailed repeat control based on the evaluation result of the detailed text information evaluation means.

[0054] According to the 22nd invention, the computer system can evaluate the second detailed text information and perform detailed repeat control based on the evaluation result.

[0055] The 23rd invention is a computer system in which the extended generation means further comprises means for variably controlling the extended randomness control parameter value based on the number of repetitions of the detailed repeat control and / or the evaluation result of the detailed text information evaluation means (for example, the extended randomness control unit 216 in Figure 23, step S84 in Figure 25) in the above computer system.

[0056] According to the 23rd invention, the computer system can control the randomness related to the expansion and control the degree of creativity related to the second detailed text information.

[0057] The 24th invention is a computer system further comprising a repeat control means (for example, a repeat control unit 240 in Figure 23) that performs summary repeat control to cause the summary text information acquisition control means to repeatedly acquire the first summary text information.

[0058] According to the 24th invention, the computer system becomes capable of repeatedly acquiring the first summary text information.

[0059] The 25th invention is a computer system further comprising a summary text information evaluation means (for example, the summary text information evaluation unit 230 in Figure 23, step S46 in Figure 24) for evaluating the first summary text information, wherein the repeat control means executes the summary repeat control based on the evaluation result of the summary text information evaluation means.

[0060] According to the 25th invention, the computer system becomes capable of performing summary repeat control based on the evaluation results of the summary text information evaluation means.

[0061] The 26th invention is a computer system in which the summary generation means generates a summary using a given summary randomness control parameter value for controlling the randomness related to the generation of the summary, and further comprises means for variably controlling the summary randomness control parameter value based on the number of repetitions of the summary repeat control and / or the evaluation result of the summary text information evaluation means (for example, the summary randomness control unit 228 in Figure 23, and steps NO to S54 in step S50 of Figure 24).

[0062] According to the 26th invention, the computer system can change the creativity and diversity in the summarization process based on the number of repetitions of the summary repeat control and / or the evaluation results of the summary text information.

[0063] The 27th invention is a computer system in which the detailed text information acquisition control means acquires the second detailed text information for the first summary text information selected from a plurality of first summary text information acquired by the summary repeat control based on given conditions.

[0064] According to the 27th invention, a computer system becomes capable of obtaining second detailed text information about a first summary text information selected based on given conditions.

[0065] The 28th invention is a computer system in which, in the above-described computer system, the detailed text information acquisition control means is instructed to acquire a plurality of second detailed text information from the first summary text information (for example, the number of requested outputs in step S150 of Figure 26), and the repeat control means, in the cycle repeat control, selects the second detailed text information from the plurality of second detailed text information based on given conditions as new first detailed text information, and causes the summary text information acquisition control means to acquire new first summary text information (for example, the processing from NO onwards in step S120 of Figure 26).

[0066] According to the 28th invention, the computer system can obtain a plurality of second detailed text information from a first summary text information, select a second detailed text information from among them as new first detailed text information, and obtain new first summary text information.

[0067] The 29th invention is a computer system in which the first detailed text information is information from a game play log of a given game, and new game play log information can be acquired as the second detailed text information.

[0068] According to the 29th invention, a computer system can generate a new gameplay log based on the original gameplay log by summarizing the original gameplay log and expanding from the summary.

[0069] The 30th invention is a program for causing a computer system to function as a summary document information acquisition control means that controls the acquisition of a first summary document information for a first detailed document information using a summary generation means capable of generating a summary or outline (hereinafter collectively referred to as "summary") for a given detailed document information, and a detailed document information acquisition control means that controls the acquisition of a second detailed document information for the first summary document information using an extension generation means capable of generating detailed document information by extending the given summary document information.

[0070] According to the 30th invention, it becomes possible to realize a program that makes a computer system perform the same functions as the first invention. [Brief explanation of the drawing]

[0071] [Figure 1] A system configuration diagram showing an example of a proofreading system. [Figure 2] A diagram showing an example of a user interface. [Figure 3] A diagram illustrating the overview of automated proofreading. [Figure 4] A diagram illustrating the process of automated proofreading, the data used, and the AI ​​used. [Figure 5] A diagram illustrating the process of automated proofreading, the data used, and the AI ​​used. [Figure 6] A diagram illustrating the machine learning process used in detailed text generation AI. [Figure 7] A diagram showing an example of origin generation instruction information described in natural language. [Figure 8] A diagram illustrating the machine learning process used in summary generation AI. [Figure 9] A diagram showing an example of summary instruction information described in natural language. [Figure 10] A diagram illustrating an example of the structure of summary text information. [Figure 11] A diagram illustrating the machine learning process used in summary evaluation AI. [Figure 12] A diagram showing an example of summary evaluation instruction information described in natural language. [Figure 13] A diagram illustrating machine learning in augmented generative AI. [Figure 14] A diagram showing an example of extended instruction information described in natural language. [Figure 15] A diagram showing an example of the structure of the second detailed information section. [Figure 16] A diagram illustrating machine learning in augmented evaluation AI. [Figure 17]A diagram showing an example of extended evaluation instruction information described in natural language. [Figure 18] A diagram illustrating the machine learning process used in text classification AI. [Figure 19] A diagram showing an example of classification instruction information described in natural language. [Figure 20] A diagram illustrating the machine learning process used in detailed text evaluation AI. [Figure 21] A diagram showing an example of detailed text evaluation instruction information described in natural language. [Figure 22] A diagram showing examples of programs and data stored by a server system. [Figure 23] A diagram showing an example of the functional configuration of the server processing unit. [Figure 24] A flowchart to explain the editing process. [Figure 25] Flowchart continuing from Figure 24. [Figure 26] Flowchart continuing from Figure 25. [Figure 27] A diagram illustrating variations of the correction system. [Figure 28] A flowchart illustrating the flow of a modified version of the editing process (editing process β). [Figure 29] Flowchart continuing from Figure 28. [Figure 30] Flowchart continuing from Figure 29. [Figure 31] A diagram showing an example of extended instruction information in a modified version of the editing process. [Figure 32] A diagram showing an example of detailed text evaluation instruction information in a modified version of the editing process. [Figure 33] A diagram showing a modified example of machine learning in summary generation AI. [Figure 34] A diagram illustrating a modified example of machine learning in augmented generative AI. [Figure 35] A diagram illustrating a modified example of machine learning for detailed text evaluation AI. [Modes for carrying out the invention]

[0072] Examples of embodiments of the present invention will be described below, but it goes without saying that the embodiments to which the present invention can be applied are not limited to the following embodiments.

[0073] Figure 1 is a system configuration diagram showing an example of the configuration of the editing system according to this embodiment. The editing system 1000 is a computer system that generates and edits text data and provides it to user 2. In this embodiment, a scenario is used as an example of text for explanation.

[0074] The proofreading system 1000 is a computer system that includes a server system 1100 and user terminals 1500 for each user, all connected via a network 9 for data communication.

[0075] Network 9 refers to a communication path capable of data transmission. In other words, Network 9 includes not only LANs (Local Area Networks) using dedicated lines (dedicated cables) or Ethernet (registered trademark) for direct connections, but also telephone networks, cable networks, and the Internet.

[0076] The server system 1100 is a computer system that performs various processes such as managing and controlling registered user information and controlling editing.

[0077] The server system 1100 has a control board 1150 mounted on the main unit 1101. The control board 1150 is equipped with various microprocessors such as a CPU (Central Processing Unit) 1151, a GPU (Graphics Processing Unit), and a DSP (Digital Signal Processor), various IC memories 1152 such as VRAM, RAM, and ROM, and a communication device 1153. Some or all of the functions mounted on the control board 1150 may be implemented using an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a SoC (System on a Chip).

[0078] In Figure 1, the server system 1100 is depicted as a single server device, but it may also be implemented using multiple devices. For example, the server system 1100 may be configured with multiple server devices, each responsible for a specific function, connected to each other via an internal bus or network 9 for data communication. Furthermore, the server system 1100 may include a database and online storage.

[0079] The server system 1100 has a generation unit called a generation AI 10. The AI ​​model of the generation AI 10 is a Large Language Model (LLM) realized by deep learning based on hardware employing a multi-core architecture (for example, a group of GPUs and memory, a group of AI chips, etc.).

[0080] The generation AI10 generates text data for the source scenario based on the given generation instruction information. The generation instruction information is, for example, information called a prompt. The source scenario is referred to as the "first detailed document".

[0081] The generation AI 10 may be implemented with a single AI model, or it may be configured using multiple sub-AI models. In this embodiment, the generation unit, generation AI 10, is described as having the following sub-AI models, which are sub-generation units: detailed text generation AI 11, summary generation AI 12, summary evaluation AI 13, extended generation AI 14, extended evaluation AI 15, text classification AI 16, and detailed text evaluation AI 17. All of these sub-AI models are constructed as LLMs. The construction of the AI ​​model will be described later.

[0082] The detailed text generation AI11 generates the first detailed text information, which is the text data of the scenario, according to the given generation instruction information. The text format of the scenario and the elements included in the story follow the generation conditions specified in the generation instruction information.

[0083] The summary generation AI12 generates text data that summarizes the given first detailed text information, which is the scenario, according to the given summary instruction information. The data containing the generated text is called "summary text information".

[0084] The summary evaluation AI13 evaluates whether the given summary text information was generated in accordance with the summary evaluation instruction information as a summary of the first detailed text information, and determines whether it is a pass or fail as a summary.

[0085] The extended generation AI14 generates new scenario text data by treating the given summary text information as a scenario plot, according to the given extended instruction information. In other words, it extends the summary text information to generate new detailed text that inherits the core of the first detailed text information. The data containing the generated text is called the "second detailed text information." The second detailed text information can be described as the result of adding to the summary text information.

[0086] The extended evaluation AI15 evaluates the extension from the given summary text information to the second detailed text information according to the given extended evaluation instruction information, and determines whether it passes or fails.

[0087] The text classification AI 16 classifies the text according to the given classification instruction information. The classification items are set in correspondence with the prompt items (items that can be specified by prompt) of the generation instruction information given to the generation AI 10. Other classification items and classification options within classification items follow the given classification instruction information.

[0088] The detailed text evaluation AI17 evaluates the "quality" and "quality of content" of a given detailed text information according to the given detailed text evaluation instruction information. Specifically, it evaluates the second detailed text information.

[0089] Furthermore, the generated AI 10 is not limited to the server system 1100. For example, the server system 1100 may be implemented as an external device that can be connected via the network 9, and may be an external system that can be used by customers other than those using the editing system 1000.

[0090] The user terminal 1500 serves as the Man-Machine Interface (MMIF) for the correction system 1000. Although only one terminal is depicted in Figure 1, in actual operation, multiple user terminals 1500 typically communicate with the server system 1100 simultaneously.

[0091] The user terminal 1500 is a computer system that can connect to the network 9, such as a personal computer, smartphone, wearable computer, portable game console, home game console, or tablet computer.

[0092] The user terminal 1500 is a computer equipped with an operation input device, an image display device, a communication device, and a control board 1550 for performing calculations. Examples of operation input devices include a touch panel 1506, a keyboard, a game controller, and a mouse. Examples of image display devices include a touch panel 1506, a head-mounted display, and a glasses-type display.

[0093] The control board 1550 is equipped with a CPU 1551, various microprocessors such as a GPU and DSP, various IC memories 1552 such as VRAM, RAM, and ROM, and a communication module 1553 that connects to the network 9. These elements mounted on the control board 1550 are electrically connected via bus circuits and the like, enabling data reading and writing, and signal transmission and reception. Part or all of the control board 1550 may be an ASIC, FPGA, or SoC.

[0094] The control board 1550 stores programs and various data necessary to realize the functions of the user terminal 1500 in the IC memory 1552. The user terminal 1500 realizes its functions as a terminal by executing a predetermined application program (for example, a client program) on the CPU 1551.

[0095] User 2 performs a predetermined request operation on user terminal 1500 to cause server system 1100 to generate a base scenario (first detailed text information) and obtains the text data for the desired scenario.

[0096] Figure 2 shows an example of a user interface (UI) related to request operations. When the server system 1100 detects that a predetermined request function has been invoked on the user terminal 1500, it displays the request setting UI 5 (5a, 5b, ...) for each setting item on the user terminal 1500.

[0097] The settings items mentioned here are not limited to the example shown in Figure 2. Also, while the Request Settings UI5 is illustrated as a pull-down menu, the UI design is not limited to this. For example, Request Settings UI5 could be a text input field that allows natural language input for each request item.

[0098] The Request Settings UI5 is provided for each prompt item that describes the generation conditions (prerequisites), quality, supplementary information, etc., in the generation instruction information given to the Generation AI10. For example, Request Setting UI5 (5a, 5b, ...) is provided separately for "Genre," "Synopsis Keywords," "Character Settings," "Dialogue," "Plot Points," "Story Length," and "User-Specified Plot." In a single Request Setting UI5, multiple options are presented for selection. Some items include options that the user can input in their own words (natural language).

[0099] The user terminal 1500 transmits the input result from the request setting UI 5 to the server system 1100 along with a predetermined request signal. The server system 1100 generates origin generation instruction information based on the input results in the received request setting UI5 and provides this to the detailed text generation AI 11. Then, it causes the generation AI 10 to generate and output the original first detailed text information. Next, it automatically edits this information.

[0100] Figure 3 is a diagram illustrating the overview of automated text correction. In Figure 3, text is shown as a horizontal strip, and its length represents the amount of text.

[0101] The automated correction process consists of the following four stages: (1) A first process in which the detailed text to be summarized is presented to User 2, and User 2 is given instructions to select specific parts (specific part a, specific part b, ...) from the detailed text that they wish to keep. (2) A second process in which a summary text is generated from the detailed text to be summarized, retaining specific parts. (3) A third process in which a new detailed text is generated by creating and expanding the content of the summary while inheriting the remaining specific parts from the generated summary text. (4) The fourth step involves evaluating the newly generated detailed text and determining whether it is acceptable as an output text corresponding to the request.

[0102] The resulting structure of the new detailed text after the third process depends on how the generating AI10 performs in that process. In other words, whether the new detailed text has a four-part structure (introduction, development, turn, conclusion) or a five-part structure (introduction, development, turn, turn, conclusion), it will be an extension of the summary text.

[0103] If the detailed document evaluated in the fourth process passes, the server system 1100 determines that the editing is complete and outputs it as the output document in response to the request. If the detailed document evaluated in the fourth process fails, the server system 1100 sets that detailed document as the new detailed document to be summarized and repeats the processes from the first to the fourth process.

[0104] In this embodiment, the text presented in the first step, i.e., the first detailed text to be summarized, is the original first detailed text initially generated by the detailed text generation AI 11 in response to the request. The text generated by the extended generation AI 14 in the third step is the second detailed text.

[0105] In Figure 3, each time the second detailed text is presented to user 2 as the detailed text to be summarized next, the designation of specific parts gradually increases to "specific part a," "specific part b," "specific part c," and "specific part d." Note that although the bands representing specific parts (specific part a, specific part b, ...) are attached to the end of the band representing the summarized text in Figure 3, this is a conceptual diagram, and the actual structure of the summarized text is not limited to what is shown in Figure 3.

[0106] Even if the initially generated original first detail text contains inconsistencies in context, abrupt plot developments, or unnecessary and uninteresting sections, summarization eliminates one or more of these flaws, compressing the text to its core essence. Then, by developing and expanding the story based on this summary to generate a second detail text, the original first detail text is revised into a better piece of writing.

[0107] Even if there are flaws that weren't removed during the summarization process, the expansion will be based on those remaining flaws. Therefore, parts that didn't make sense before summarization may become consistent, and parts that seemed like absurd developments are likely to be corrected to a more appropriate development. Unnecessary and tedious developments are likely to be cut out.

[0108] Any minor flaws that may remain even after summarization and expansion will be corrected as the process repeats from the first to the fourth stage, ultimately resulting in a well-written document. The number of iterations required to produce the second detailed document depends on the content of the request and the performance of the AI ​​model of Generator AI10.

[0109] Figures 4 and 5 are diagrams that provide a more detailed explanation of the workflow, data used, and AI used in the automated proofreading process. As shown in Figure 4, when the server system 1100 receives a request signal and the content of the request from the user terminal 1500 [Communication A], it generates origin generation instruction information 600 to be given to the detailed text generation AI 11.

[0110] Figure 6 is a diagram illustrating the machine learning of the detailed text generation AI 11. The detailed text generation AI 11 is pre-trained to take learning origin generation instruction information and annotations as input and output detailed text information, and it supports generation instructions in natural language.

[0111] Figure 7 shows an example of the origin generation instruction information 600 described in natural language. The origin generation instruction information 600 is information that has been adapted to a format that the detailed text generation AI 11 can accept, based on the content of the request from user 2. The content of the request itself can also be considered equivalent to the generation instruction information for the generation AI 10. Therefore, the process by which the server system 1100 receives the content of the request from the user terminal 1500 and generates the origin generation instruction information 600 can be summarized as the process of receiving the generation instruction information for the generation AI 10.

[0112] Returning to Figure 4, the server system 1100 provides the origin generation instruction information 600 to the detailed text generation AI 11, causing it to generate and output the original first detailed text information 602.

[0113] Next, the server system 1100 prompts the user terminal 1500 to present the original first detailed document [Communication B]. During this presentation, the server system 1100 accepts the user 2's input indicating whether the original first detailed document is acceptable or unacceptable as the requested document, as well as a specific part specification operation.

[0114] If the original first detail document is satisfactory, that first detail document will be output as the output document, and the response to the request will be terminated.

[0115] If the original first detailed document fails, the user terminal 1500 sends information about the pass / fail judgment input and the specific part specification operation to the server system 1100 [Communication C]. If the detailed text to be summarized (the original first detailed text) is unsatisfactory, the server system 1100 generates summarization instruction information 604 to be given to the summarization generation AI 12.

[0116] Figure 8 is a diagram illustrating the machine learning process of the summary generation AI 12. The summary generation AI 12 is pre-trained to take detailed text information to be summarized, specific part specification information, and annotations as input, and to output a first summary text information, and it supports generation instructions in natural language.

[0117] Figure 9 shows an example of summary instruction information 604 described in natural language. The summary instruction information 604 includes the number of summarized sentences, specific partial information, and a summary randomness parameter value as summary generation conditions (prerequisites for summarization). The summary randomness parameter value is a parameter value that provides diversity in which parts of the detailed text of the summarized sentence are summarized. This corresponds to the parameter value commonly referred to as "Temperature." The number of summarized sentences and the summary randomness parameter value are set according to the number of times the summary is repeated (details below).

[0118] Figure 10 shows an example of the structure of the summary text information 606. The summary text information 606 is text data, specifically information in a list format containing summary sentences. Each summary sentence in the list is separated by blank spaces or lines. For summaries of specific sections, the text of that section is written after the summary, followed by blank spaces or lines. The method of describing specific sections is not limited to this. Furthermore, the summary text information 606 includes the generation date and time as metadata.

[0119] Moving to Figure 5, the server system 1100 provides the summary instruction information 604 to the summary generation AI 12 to generate the summary text information 606. Then, it generates summary evaluation instruction information 608 to cause the summary evaluation AI 13 to evaluate the summary text information 606, and provides this to the summary evaluation AI 13 to perform the evaluation.

[0120] Figure 11 is a diagram illustrating the machine learning of the summary evaluation AI 13. The summary evaluation AI 13 is pre-trained to take detailed text information of the text to be summarized, summary generation instruction information, summary text information, and annotations as input, and to output evaluation results and pass / fail judgment results for the summary text information, and supports generation instructions in natural language.

[0121] Depending on the performance of the AI ​​model of the summary generation AI 12, the summarized text information 606 may not necessarily match the summary instruction information 604. The summary evaluation AI 13 determines whether the result is a pass or fail based on the summary instruction information 604.

[0122] Figure 12 shows an example of the summary evaluation instruction information 608 described in natural language.

[0123] Returning to Figure 5, if the summary text indicated by the summary text information 606 is unacceptable, the server system 1100 again provides the summary instruction information 604 to the summary generation AI 12 to regenerate the summary text information 606. This is referred to as "summary repeat".

[0124] In addition, the summary instruction information 604 given to the summary generation AI 12 during summary repetition is modified so that the randomness of the summary randomness parameter value increases as the number of summary repetitions increases.

[0125] If the summary text indicated by the summary text information 606 is acceptable, the server system 1100 displays the summary text as text on the user terminal 1500 [communication D] and accepts instructions for the highly extended portion of the summary text.

[0126] The instruction operation for the highly extended portion is an operation in which user 2 specifies the part of the newly generated and extended text that they would like to be further extended or added to, and is an operation to select a range from the displayed text. The result of the instruction operation for the highly extended portion is transmitted from the user terminal 1500 to the server system 1100 [communication E]. When the server system 1100 receives the result of the instruction operation for the highly extended portion, it generates extension instruction information 612 to be given to the extension generation AI 14.

[0127] Figure 13 is a diagram illustrating the machine learning of the augmented generative AI 14. The augmented generative AI 14 is pre-trained to take origin generation instruction information, summary text information, and annotations as input, and to output detailed text information (second detailed text) created by expanding on the summary, and it supports generation instructions in natural language.

[0128] Figure 14 shows an example of extended instruction information 612 described in natural language. The extended instruction information 612 includes an extended generation condition (prerequisite for extension) that sets the degree of extension to the highly extended portion relatively high (underlined portion in Figure 14), and an extended randomness parameter value.

[0129] The extended randomness parameter value is a parameter value that provides diversity to the generated detail text (second detail text). This is the parameter value commonly referred to as "Temperature." Note that the extended randomness parameter value is set according to the number of extension repetitions (details below).

[0130] Figure 15 shows an example of the structure of the second detailed text information 614. The second detailed text information 614 is text data and includes an extended text that describes a scene based on the summary text, and metadata (including, for example, information on the date and time of creation). The extended text based on the summary text of a specific part includes the text of that specific part. In this case, the words used at the beginning and end of the specific part may be changed from the original specific part so that the flow of the text is smoothly connected.

[0131] The writing style of the detailed text in the second detailed text information 614 is basically the same as that of the detailed text in the first detailed text information 602. When compared side by side with the writing style of the summary text in the summary text information 606, it can be said that the second detailed text information 614 is an extension of the summary text in the summary text information 606, with additions made between the list-like summary texts.

[0132] Returning to Figure 5, the server system 1100 provides the extended instruction information 612 to the extended generation AI 14 to generate the second detailed text information 614. Then, it generates extended evaluation instruction information 616 to cause the extended evaluation AI 15 to evaluate the second detailed text information 614, and provides this to the extended evaluation AI 15 to perform the evaluation.

[0133] Figure 16 is a diagram illustrating the machine learning of the augmented evaluation AI 15. The augmented evaluation AI 15 is pre-trained to take the following inputs—summary text information to be used as the basis for augmentation, augmentation generation instruction information, detailed text information to be evaluated (second detailed text information), and annotations—as input, and to output an evaluation of the augmentation content and a pass / fail judgment for the augmentation, and it supports generation instructions in natural language.

[0134] Depending on the performance of the AI ​​model of the extended generation AI 14, the second detailed text information 614 may not necessarily be exactly as specified in the extended instruction information 612. The extended evaluation AI 15 determines whether the second detailed text information 614 passes or fails as a result of the extended instruction information 612.

[0135] Figure 17 shows an example of the extended evaluation instruction information 616 described in natural language. Extended evaluation instruction information 616 defines one or more evaluation items and evaluation criteria in the extended evaluation conditions (prerequisites for evaluation). For example, evaluation items may include "no overlap in content in the extended scenes," "matching content between the summary and the extended scenes," and "inheritance of specific parts." Of course, other evaluation items may also be set as appropriate.

[0136] Returning to Figure 5, if the extended evaluation result is unsuccessful, the server system 1100 again provides the extended instruction information 612 to the extended generation AI 14 to regenerate the second detailed text information 614. This is referred to as "detailed repeat".

[0137] In addition, the extended instruction information 612 given to the extended generation AI 14 during detailed repetition is modified by a given value to change the extended randomness parameter value so that the randomness improves as the number of detailed repetitions increases.

[0138] If the extended evaluation result is satisfactory, the server system 1100 will have successfully obtained the second detailed text information 614, which has been extended from the summary text information 606. Conversely, in the process of summary repetition, the summary repetition is repeated until a passing summary text information 606 is generated, and each time, a failing summary text information 606 is accumulated. Therefore, obtaining the second detailed text information 614, which is a passing result of the extended evaluation, corresponds to obtaining the second detailed text information 614 for the summary text information 606 selected based on the given conditions.

[0139] If the extended evaluation result is satisfactory, the server system 1100 generates classification instruction information 620 to be given to the text classification AI 16 and detailed text evaluation instruction information 622 to be given to the detailed text evaluation AI 17.

[0140] Figure 18 is a diagram illustrating the machine learning process of the text classification AI 16. The text classification AI 16 is pre-trained to take detailed text information and annotations prepared for training as input, perform text classification, and output evaluation scores for each classification, and it supports generation instructions in natural language.

[0141] The text classification is determined by analyzing the settings in the Request Settings UI5 (see Figure 2) and identifying which of the options in those settings corresponds to the text. As mentioned above, the settings in the Request Settings UI5 are the basis for the prompt items included in the generation conditions of the Origin Generation Instruction Information 600. The evaluation points for each classification are the match rate and similarity rate between the specified prompt items included in the generation conditions of the Origin Generation Instruction Information 600 and the classification result of the analysis item corresponding to those prompt items.

[0142] Figure 19 shows an example of classification instruction information 620 described in natural language. The classification instruction information 620 includes classification conditions, and the description of the classification conditions defines the analysis item and the classification type within that analysis item.

[0143] Figure 20 is a diagram illustrating the machine learning process of the detailed text evaluation AI 17. The detailed text evaluation AI 17 is pre-trained to take input from origin generation instruction information, detailed text information to be evaluated, detailed classification information of the detailed text, and annotations, and to output evaluation scores for each evaluation item and whether the detailed text is pass or fail, and it supports generation instructions in natural language. The pass or fail status of the detailed text refers to the pass or fail status of the output text, which is output in response to a request.

[0144] Figure 21 shows an example of the detailed text evaluation instruction information 622 described in natural language. Detailed evaluation instruction information 622 includes evaluation conditions (prerequisites for evaluation). The evaluation conditions describe the criteria for evaluation points for each evaluation item.

[0145] Returning to Figure 5, the server system 1100 outputs the second detailed document as a response to the request [communication H] if the total evaluation score of the second detailed document reaches a given passing score. If the passing score is not reached, the second detailed document will be displayed as text on the user terminal 1500, and additional operations on specific parts will be accepted [Communication F].

[0146] The operation to add a specific section is an operation to specify a part of the second detailed document that is otherwise unacceptable but which user 2 deems partially acceptable and wishes to keep. The result of the operation to add a specific section is transmitted from user terminal 1500 to server system 1100 [communication G].

[0147] When the server system 1100 receives the results of additional operations on a specific part, it considers the second detailed document that failed to pass the review as a target for summarization and repeats the process of summarization → evaluation of the summary → expansion → evaluation of the expansion → document classification and evaluation of the detailed document. This is called a "cycle repeat."

[0148] Specifically, in controlling the repeat cycle, the server system 1100 uses the summary instruction information 604 previously given to the summary generation AI 12 to designate the second detailed text that failed the previous cycle as the detailed text to be summarized. It then generates summary instruction information 604 instructing the AI ​​12 to include a specific part in the summary information and provides it to the summary generation AI 12.

[0149] Furthermore, in controlling the loop repeat, the server system 1100 generates summary instruction information 604 for the loop repeat based on the extension instruction information 612 previously given to the extension generation AI 14. The summary instruction information 604 for the loop repeat includes information specifying the highly extended portion and extension generation conditions that specify strengthening the extension to the highly extended portion (for example, doubling the number of scenes generated by expanding and extending from the summary). The server system 1100 then provides the extension instruction information 612 for the loop repeat to the extension generation AI 14.

[0150] Each time the loop is repeated, the detailed text of the first detailed text information 602 is revised to meet the request, resulting in a better text than the original that was initially generated, and then provided to user 2.

[0151] Figure 22 shows an example of programs and data stored by the server system 1100. The server system 1100 stores the server program 501 and the distribution client program 503, which is the original client program to be provided to the user terminal 1500, in the IC memory 1152. The server program 501 may include one or more generation AI programs 502 to realize the function of generation AI 10. Alternatively, the generation AI programs 502 may be stored separately from the server program 501.

[0152] Furthermore, the server system 1100 stores UI definition data 510 of the request setting UI 5, a trained generation AI model 512, request information 514 indicating the result of the request setting operation, and specific part specification information 516.

[0153] Furthermore, the server system 1100 stores origin generation instruction information 600, first detailed text information 602, summary instruction information 604, summary text information 606, summary evaluation instruction information 608, high-extension part designation information 610, and extension instruction information 612. The summary text information 606 is stored if it passes the summary evaluation and is discarded when the editing is completed.

[0154] Furthermore, the server system 1100 stores the second detailed document information 614, the extended evaluation instruction information 616, the classification instruction information 620, and the detailed document evaluation instruction information 622. The second detailed document information 614 is stored if it passes the extended evaluation and is discarded when the editing is completed.

[0155] Furthermore, the server system 1100 stores the summary repeat count 630, the detailed repeat count 632, the loop repeat count 634, and the upper limit repetition count 636, which corresponds to the upper limit of the loop repeat count. Of course, other data, such as evaluation results, may also be stored as appropriate.

[0156] The server system 1100 performs the server program 501 and calculates the results on the CPU 1151, thereby realizing the function of the server processing unit 200s shown in Figure 23.

[0157] The server processing unit 200s performs various controls related to the automatic editing of text, and in this embodiment, it performs various controls from generating a scenario using AI in response to a request operation from user 2 until it is output.

[0158] Specifically, the server processing unit 200s includes a generation instruction information receiving unit 204, a detailed text information acquisition control unit 210, a detailed text generation unit 220, a remaining portion designation unit 222, a summary text information acquisition control unit 224, and a summary generation unit 226.

[0159] Furthermore, the server processing unit 200s includes a summary randomness control unit 228, a summary text information evaluation unit 230, an extended generation unit 232, a highly extended portion designation unit 234, a text classification unit 236, and a detailed text information evaluation unit 238.

[0160] Furthermore, the server processing unit 200s includes a repeat control unit 240, a loop repeat count determination unit 242, and a feedback control unit 244.

[0161] The generation instruction information receiving unit 204 receives given generation instruction information for generating new detailed text information. This includes receiving request information from the user terminal 1500 and generating the origin generation instruction information 600.

[0162] The detailed text information acquisition control unit 210 uses an extended generation unit 232 capable of generating detailed text information by extending the given summary text information 606 to perform control to acquire detailed text information (second detailed text information 614) about the summary text information 606.

[0163] Furthermore, the detailed text information acquisition control unit 210 includes a summary instruction information generation unit 211 that generates summary instruction information 604, and an extended instruction information generation unit 214 that generates extended instruction information 612.

[0164] The summary instruction information generation unit 211 includes a summary generation condition setting unit 212 that sets summary generation conditions based on the first detailed text information 602.

[0165] The extended instruction information generation unit 214 includes an extended randomness control unit 216 and an extended generation condition setting unit 218 that sets extended generation conditions based on the first detailed text information 602.

[0166] The extended randomness control unit 216 variably controls the extended randomness control parameter values ​​based on the number of repetitions of the detailed repeat control and / or the evaluation result of the detailed text information evaluation means.

[0167] The detailed text generation unit 220 generates detailed text information based on the origin generation instruction information 600. The detailed text generation unit 220 has a detailed text generation AI 11.

[0168] The retained portion designation unit 222 designates specific portions of the first detailed text information 602 that are to be retained in the summary. This includes receiving the operation to designate specific portions on the user terminal 1500 and obtaining the result of the reception (see Figure 4).

[0169] The summary text information acquisition control unit 224 controls the acquisition of summary text information 606 for the first detailed text information 602 using a summary generation unit 226 capable of generating a summary of given detailed text information. At that time, the summary text information acquisition control unit 224 acquires the summary text information 606 while retaining a specific portion designated by the remaining portion designation unit 222.

[0170] The summary generation unit 226 is capable of generating summary text information 606 for given detailed text information. The summary generation unit 226 has a summary generation AI 12.

[0171] The summary randomness control unit 228 variably controls the summary randomness control parameter values ​​based on the number of repetitions of the summary repeat control and / or the evaluation result of the summary text information evaluation unit 230.

[0172] The summary text information evaluation unit 230 evaluates the summary text information 606.

[0173] The extended generation unit 232 extends the given summary text information 606 to generate second detailed text information 614. The extended generation unit 232 has an extended generation AI 14.

[0174] The highly extended portion designation unit 234 designates a specific portion of the summary text information 606 that has a relatively high degree of extension. As a result of the highly extended portion designation operation, the summary text is displayed on the user terminal 1500, so the highly extended portion designation unit 234 can be said to also function as a summary text notification unit 235 that notifies the user 2 of the summary text.

[0175] The document classification unit 236 classifies the detailed documents to be classified. The document classification unit 236 has a document classification AI 16.

[0176] The detailed text information evaluation unit 238 evaluates the second detailed text information 614. The detailed text information evaluation unit 238 has a detailed text evaluation AI 17.

[0177] The repeat control unit 240 performs a redo control, which restarts the process by either acquiring new first summary text information or acquiring new second detailed text information.

[0178] Specifically, the repeat control unit 240 performs summary repeat control, which causes the summary text information acquisition control unit 224 to repeatedly acquire the summary text information 606 based on the evaluation results of the summary text information evaluation unit 230.

[0179] Furthermore, the repeat control unit 240 performs detailed repeat control, causing the detailed text information acquisition control unit 210 to repeatedly acquire the second detailed text information 614 based on the evaluation results of the detailed text information evaluation unit 238.

[0180] Furthermore, the repeat control unit 240 performs a looping repeat control that, based on the evaluation results of the detailed text information evaluation unit 238, sets the second detailed text information 614 as new first detailed text information (new detailed text information to be summarized), acquires new summarized text information 606 for the second detailed text information, and has the detailed text information acquisition control unit 210 acquire new second detailed text information 614 for the new summarized text information 606.

[0181] The loop repeat count determination unit 242 determines the upper limit of the number of repetitions 636 for loop repeat control based on the origin generation instruction information 600. For example, the upper limit of the number of repetitions 636 is determined such that the larger the amount of text specified in the origin generation instruction information 600, the higher the number of repetitions.

[0182] The feedback control unit 244 variably controls the summary instruction information 604 in the loop repeat control based on the evaluation result of the detailed text information evaluation unit 238. For example, this includes the control of adding a specific part to the summary instruction information 604 for loop repeat.

[0183] Figures 24 to 26 are flowcharts illustrating the flow of the editing process performed by the server system 1100. The server system 1100 receives a request operation from user 2 at user terminal 1500 (step S10) and receives the number of request outputs, which is the number of scenarios to be output in relation to the request (step S12). This information is stored as request information 514.

[0184] Next, the server system 1100 generates origin generation instruction information 600 in response to the request operation (step S14), and provides the generated origin generation instruction information 600 to the detailed text generation AI 11 to obtain first detailed text information 602 (step S16).

[0185] The server system 1100 displays the generated first detailed document information 602 on the user terminal 1500 and accepts the user's judgment to determine whether the first detailed document information 602 is correct or incorrect, and to specify a particular part of the first detailed document (step S18).

[0186] If the user judgment result is unsuccessful (NO in step S30), the server system 1100 initializes the number of repetitions 634 to "0" and sets the upper limit of the number of repetitions 636 according to the amount of text in the first detail document (step S32). For example, the more text there is, the higher the upper limit of the number of repetitions 636 is set.

[0187] Next, the server system 1100 initializes the summary repeat count 630 to "0" (step S40), generates summary instruction information 604 (step S42), and provides this to the summary generation AI 12 to obtain summary text information 606 (step S44).

[0188] Next, the server system 1100 generates summary evaluation instruction information 608 and provides it to the summary evaluation AI 13 to evaluate the summary text of the summary text information 606 (step S46).

[0189] If the evaluation result of the summary text is unsatisfactory (NO in step S50), the server system 1100 discards the summary text information 606 that was just acquired and increases the summary repeat count 630 by "1" (step S52). Then, it sets the summary randomness parameter value according to the summary repeat count 630 (step S54) and returns to step S42. In other words, the summary instruction information 604 is set according to the summary repeat count 630. The summary instruction information 604 after step S54 corresponds to the first retry instruction information that executes the summary repeat control as the first retry control. Note that an upper limit on the number of retry operations may be set as appropriate.

[0190] If the evaluation result of the summary text is satisfactory (YES in step S50), the process moves to Figure 25, where the server system 1100 displays the summary text of the summary text information 606 as text on the user terminal 1500 and accepts the operation to specify the highly extended portion (step S60).

[0191] Then, extended instruction information 612 is generated (step S62), and if a highly extended portion was specified in step S60 (step S64), a description of the highly extended portion is added or modified to the extended generation conditions of the extended instruction information 612 (step S66).

[0192] Next, the server system 1100 initializes the detailed repeat count 632 to "0" (step S70), presents the extended instruction information 612 to the user terminal 1500, and accepts modifications from user 2 (step S72).

[0193] Then, the server system 1100 provides the extended instruction information 612 to the extended generation AI 14 to obtain the second detailed text information 614 (step S74). Then, it generates extended evaluation instruction information 616 (step S76) and provides this to the extended evaluation AI 15 to perform an evaluation of the extension (step S78).

[0194] If the extended evaluation result is unsuccessful (NO in step S80), the server system 1100 discards the second detailed text information 614 that was just acquired and increases the detailed repeat count 632 by "1" (step S82). Then, it changes the extended randomness control parameter value according to the detailed repeat count 632 of the extended instruction information 612 (step S84).

[0195] Furthermore, extended evaluation conditions are added to the extended instruction information 612 that instruct improvement for evaluation items that do not meet a predetermined standard among the evaluation scores for each evaluation item in the extended evaluation (see Figure 17) (step S86). Then, the process returns to step S72. In other words, the extended instruction information 612 after step S86 corresponds to second retry instruction information that executes detailed repeat control as a second retry control.

[0196] Steps S84 and S86 are referred to as "feedback control related to detailed repeat".

[0197] If the extended evaluation result is a pass (YES in step S80), the server system 1100 generates classification instruction information 620 (step S100) and provides it to the document classification AI 16 to classify the second detailed document information 614 (step S102).

[0198] Next, the server system 1100 generates detailed text evaluation instruction information 622 (step S104) and provides this to the detailed text evaluation AI 17 to evaluate the second detailed text information 614 (step S106).

[0199] Moving to Figure 26, if the second detailed text information 614 is unacceptable (NO in step S120), it is determined whether the number of lap repeats 634 has reached the upper limit of lap repeats 636 (step S122).

[0200] If the upper limit of 636 repetitions has not been reached (NO in step S122), the server system 1100 displays the second detailed text of the second detailed text information 614 as text on the user terminal 1500. At this time, already specified specific parts are identified and displayed, and operations to deselect or add specific parts are accepted.

[0201] Then, if there are any deletions or additions to a specific part (step S126), the server system 1100 updates the summary instruction information 604 according to the specified (step S128).

[0202] Next, the server system 1100 increases the number of cycle repeats 634 by "1" (step S136). Then, it changes the setting of the amount of summary in the summary generation conditions of the summary instruction information 604, for example, the setting of "number of sentences after summarization," according to the summary instruction information 604 for cycle repeats (step S138).

[0203] The number of sentences after summarization is one context that determines the summarization volume of the summary. In addition to the number of sentences after summarization, the number of characters after summarization may also be set and changed as a setting for the summarization volume in the summary generation conditions.

[0204] Next, the detailed text information to be summarized in the summary instruction information 604 is replaced with the second detailed text information 614 (step S140), and the process returns to step S72. In other words, loop repeat control is performed. Steps S138 and S140 are referred to as "feedback control related to lap repeating".

[0205] If the second detailed information 614 is successful (YES in step S120), the server system 1100 counts the number of successful second detailed information 614s. If the number of successful second detailed information 614s does not reach the number of request outputs received in step S12 (NO in step S150), the system returns to step S40. In other words, it performs "forced repeat control".

[0206] If the number of approved second detailed document information 614s reaches the number of requested outputs received in step S12 (YES in step S150), the server system 1100 uses them as output document information corresponding to the request. It then sends them to the user terminal 1500 and provides / outputs them to user 2 (step S152).

[0207] In summary, this embodiment makes it possible to provide a new technology that enables improved efficiency in text generation. Specifically, the editing system 1000 can generate better text by summarizing the first detailed text and expanding from the summary to generate a second detailed text.

[0208] Even if the first detailed text is generated by the generation unit and contains inconsistencies or unexpected plot developments, summarizing eliminates these flaws. Then, by expanding and extending the text based on this summary, it is automatically rewritten into a better text and provided to user 2.

[0209] [Variation] Although examples of embodiments to which the present invention is applied have been described above, the forms to which the present invention can be applied are not limited to the above forms, and it is possible to add, omit, or change the components as appropriate.

[0210] (Variation 1) For example, although the proofreading system 1000 was exemplified as a client-server type, multiple user terminals 1500 may be implemented using a P2P (Peer to Peer) architecture. In this case, programs and data corresponding to the functional division are stored in the user terminals 1500, and the functions corresponding to the server processing unit 200s in the above embodiment are distributed and implemented by the user terminals 1500, which act as P2P nodes. The same effects as in the above embodiment can be obtained in this configuration as well.

[0211] (Variation 2) In the above embodiment, the server system 1100 is exemplified as having a generation AI 10 (generation unit), but it is not limited to this configuration. As shown in the correction system 1000B in Figure 27, the user terminal 1500B may also have these generation AI 10 (generation units). In this configuration, the server system 1100B transmits various instruction information to the AI ​​of the user terminal 1500B via the network 9 to acquire data.

[0212] (Variation 3) Furthermore, in the above embodiment, the editing system 1000 may be implemented solely by the computer system that was the user terminal 1500 in the above embodiment, rather than as a client-server type system.

[0213] Specifically, the user terminal 1500B in Figure 27 stores all the data that the server system 1100 in the above embodiment is supposed to store (see Figure 22). However, instead of the server program 501 and the distribution client program 503, an editing program is provided as an application program for the user terminal 1500.

[0214] In the above embodiment, the editing program implements all of the functional units of the server system 1100 (see Figure 23) on the user terminal 1500B. In this modified example, the editing program is executed on the user terminal 1500B. The processing flow in the above embodiment (see Figures 24 to 26) can be interpreted by simply replacing the execution entity from the server system 1100 to the user terminal 1500B.

[0215] (Variation 4) Furthermore, in the above embodiment, the detailed text to be edited was generated by the detailed text generation AI 11, but the user 2 may also use a detailed text that they have already created separately as the subject of editing. For example, based on the above embodiment, the editing process β shown in Figures 28 to 30 is executed instead of the editing process. In editing process β, the server system 1100 executes steps S20 to S26 instead of steps S10 to S18.

[0216] Specifically, as shown in Figure 28, the server system 1100 inputs the data of the detailed document prepared in advance by user 2 as the first detailed document information 602 (step S20) and accepts the number of requested outputs (step S22).

[0217] Next, the server system 1100 generates classification instruction information 620 to classify the input first detailed text information 602, and provides this to the text classification AI 16 to classify the first detailed text information 602 (step S24). Then, it generates detailed text evaluation instruction information 622 to designate the first detailed text information 602 as the detailed text to be evaluated, and provides this to the detailed text evaluation AI 17 to evaluate the detailed text of the first detailed text information 602 (step S26). This evaluation result is later referenced in the evaluation of the second detailed text information 614 in the editing process β.

[0218] Furthermore, in the editing process β, step S42B is executed instead of step S42 in the above embodiment. That is, the server system 1100 sets the summarization conditions of the summarization instruction information 604 (see Figure 9) generated in step S42B based on the detailed text to be summarized, i.e., the input first detailed text information 602. For example, the number of sentences after summarization in the summarization conditions is set to increase as the amount of text in the input first detailed text information 602 increases.

[0219] Furthermore, in the editing process β, step S62B is executed instead of step S62 in the above embodiment. That is, the server system 1100 generates extended instruction information 612B as shown in Figure 31. The extended instruction information 612B includes a description in the extended generation conditions that sets the amount of text to approximately the same amount as that of the first detailed text information 602 in the editing process β. The underlined portion corresponds to this. In other words, in the editing process β, extended generation conditions based on the first detailed text information 602 are generated.

[0220] Furthermore, in the editing process β, step S104B is executed instead of step S104 in the above embodiment. That is, the server system 1100 generates detailed text evaluation instruction information 622B as shown in Figure 32. The evaluation conditions of the detailed text evaluation instruction information 622B are described in a comparative format between the classification result in step S24 and the evaluation result in step S26. The underlined portion corresponds to this.

[0221] According to the configuration of this modified example, the same effects as those of the above embodiment can be obtained.

[0222] (Variation 5) Furthermore, in variation 4, the detailed text prepared in advance by user 2 is not limited to a scenario. For example, it could be a gameplay log. The "gameplay log" referred to here is text data that describes events in the game in chronological order, and can be, for example, in prose form, novel-like text data, etc. The gameplay log may be generated by a generative AI that has been trained to take so-called replay data (a set of data that can reproduce gameplay) as input and output a gameplay log.

[0223] If user 2 uses gameplay logs as the detailed text provided in advance, it is assumed that the generating AI 10 has been trained to use gameplay logs as the detailed text and that the AI ​​model has been constructed accordingly.

[0224] For example, as shown in Figure 33, the summary generation AI 12C in this configuration is pre-trained on a training dataset that takes game play logs to be summarized as input. Also, as shown in Figure 34, the augmentation generation AI 14C in this configuration is pre-trained to output game play logs as detailed text information. Furthermore, as shown in Figure 35, the detailed text evaluation AI 17C in this configuration takes game play logs as detailed text information as input and is pre-trained to output evaluation scores for each item related to the fun factor of the game as evaluation score items.

[0225] Of course, not only for AI but also for various types of instruction information, this configuration uses the game play log as the detailed text in the above embodiment and is configured to generate the game play log.

[0226] According to this configuration, user 2 will be able to obtain a different gameplay log with a different storyline based on the gameplay log they initially entered. For example, they will be able to obtain a new document that serves as a sequel to the gameplay log they initially entered.

[0227] (Variation #6) You may use an outline instead of a summary.

[0228] (Example of change #7) You may set appropriate limits on the number of times summary repeats and detailed repeats occur. For example, you may set a higher limit the more generation conditions there are for the origin generation instruction information 600.

[0229] (Variation 8) In the above embodiment, the return position of the first redo control, which is the summary repeat control, and the return position of the second redo control, which is the detail repeat control, were described as fixed. However, these return positions may be changed depending on the situation.

[0230] Specifically, if the summarization fails (NO in step S50 of Figure 24), the process is restarted from just before the summary (step S42), but this is not the only option. For example, after step S50, the server system 1100 determines whether the number of cycle repeats has reached a predetermined value (e.g., "5" or more). If affirmative, it overwrites the first detailed text information 602 with the second detailed text information 614 whose generation date and time is one step earlier (meaning it has passed the extended evaluation up to the most recent cycle), and deletes the summary instruction information 604 whose generation date and time is the most recent. Then, it may return to step S42.

[0231] By doing this, it becomes possible, with a low probability, to discard the result of the previous loop repeat, i.e., the process of the previous expansion, and rewind to the expansion before that. This makes it possible to escape the situation in the summarization process where one is trapped in a meaningless loop that continues to produce the same unsatisfactory summary.

[0232] Furthermore, if the expansion fails (NO in step S80 of Figure 25), the process is restarted from just before the expansion (step S72), but this is not the only possible scenario. For example, after step S80, the server system 1100 determines whether the number of cycle repeats has reached a predetermined value (e.g., "5" or more). If affirmative, it overwrites the first detailed text information 602 with the second detailed text information 614 whose generation date and time is one step earlier (meaning it has passed the extended evaluation up to the most recent cycle), and deletes the summary instruction information 604 whose generation date and time is the most recent. Then it may return to step S72. Alternatively, it may return to step S42.

[0233] By doing this, it becomes possible, with a low probability, to discard the result of the previous loop repeat, i.e., the previous expansion process, and rewind to the expansion before that. This makes it possible to escape from a situation where the expansion process is stuck in a meaningless loop that continues to output the same unsuccessful expansion.

[0234] (Modification #9) When extending the list-format summary text information 606 to the second detailed text information 614, for example, one configuration may be used where each of the list-format summary texts in the summary text information 606 is created and extended one by one, and then the extension is evaluated. Specifically, steps S70 to S86 may be executed for each summary text.

[0235] This allows for editing each summary text individually, for example. This configuration also makes it possible to escape a situation where the extension process becomes trapped in a meaningless loop of continuously outputting unacceptable extensions.

[0236] (Modification #10) The above embodiment shows an example of generating one second detailed information 614 from one summary information 606, but it is not limited to this. For example, a configuration may be used to generate multiple second detailed information 614 from one summary information 606.

[0237] Specifically, in step S74, multiple second detailed document information 614s are generated, and steps S76 to S106 are executed for each of the generated second detailed document information 614s.

[0238] Furthermore, in step S120, if all of the second detailed document information 614 are unsatisfactory, the evaluation determined for each in step S106 may be referenced, and a loop may be executed only for the unsatisfactory second detailed document information 614 with the highest evaluation.

[0239] As another example for step S120, suppose three second detailed document information 614s, A pattern, B pattern, and C pattern, are generated, but all are unsatisfactory. Alternatively, the second detailed document information 614 of pattern C, which received the highest evaluation, may be used as the first detailed document information 602, and a loop may be executed.

[0240] As another example for step S120, suppose three second detailed document information 614s are generated for pattern A, pattern B, and pattern C, but all are unsatisfactory. Furthermore, the evaluations of patterns B and C do not meet the predetermined minimum evaluation, but only pattern A meets the predetermined minimum evaluation. In this case, a loop may be executed for patterns B and C. [Explanation of Symbols]

[0241] 10…Generation AI 11…Detailed sentence generation AI 12…Summary generation AI 13…Summary Evaluation AI 14…Extended Generative AI 15…Extended Evaluation AI 17…Detailed text evaluation AI 200s... Server Processing Unit 204...Generation Instruction Information Reception Unit 210...Detailed Text Information Acquisition Control Unit 211…Summary instruction information generation unit 212...Summary generation condition setting section 214... Extended instruction information generation unit 216...Extended Randomness Control Unit 218... Extended generation condition setting section 220…Detailed text generation section 222...Remaining part specification part 224... Summary Text Information Acquisition Control Unit 226…Summary generator 228…Summary Randomness Control Unit 230…Summary Text Information Evaluation Department 232...Extended generation unit 234... Designated high-extension section 238...Detailed Text Information Evaluation Department 240... Repeat control unit 242... Loop Repeat Count Determination Unit 244… Feedback control unit 501…Server program 512... Pre-trained generative AI models 516…Specific part specification information 600…Origin generation instruction information 602…1st detailed text information 604…Summary Instructions 606…Summary text information 608…Summary Evaluation Instructions 610... High-extension portion designation information 612... Extended Instruction Information 614…Second detailed text information 616... Extended evaluation instruction information 622...Detailed text evaluation instruction information 636... Number of repetitions 1000... Correction System 1100…Server System 1500... User terminal

Claims

1. Summary text information acquisition control means that controls the acquisition of a first summary text information for a first detailed text information using a summary generation means capable of generating a summary or outline (hereinafter collectively referred to as "summary") for a given detailed text information, Detailed text information acquisition control means that performs control to acquire second detailed text information for the first summary text information using an extension generation means capable of generating detailed text information by extending given summary text information, A computer system equipped with the following features.

2. The computer system according to claim 1, further comprising a repeat control means that performs a cyclical repeat control, which repeatedly causes the summary text information acquisition control means to acquire new first summary text information for the second detailed text information as new first detailed text information, and then causes the detail text information acquisition control means to acquire new second detailed text information for the new first summary text information.

3. Detailed text information evaluation means for evaluating the second detailed text information, Furthermore, The repeat control means executes the loop repeat control based on the evaluation result of the detailed text information evaluation means. The computer system according to claim 2.

4. The summary text information acquisition control means controls the amount of summary generated by the summary generation means variably based on the number of repetitions of the cycle repeat control. The computer system according to claim 2.

5. The repeat control means performs a retry control that restarts the process by either acquiring new first summary text information or acquiring new second detailed text information. The computer system according to claim 2.

6. A generation instruction information receiving means that receives given generation instruction information for generating new detailed text information, Furthermore, The summary generation means has a generation unit capable of generating the summary, The summary text information acquisition control means generates summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information. The extension generation means has a generation unit capable of performing the extension and generating the detailed text information, The detailed text information acquisition control means generates extended instruction information to be given to the generation unit of the extended generation means based on the generation instruction information. The computer system according to claim 1.

7. The summary instruction information includes information indicating the amount to summarize, The computer system according to claim 6.

8. A generation instruction information receiving means that receives given generation instruction information for generating new detailed text information, Furthermore, The summary generation means has a generation unit capable of generating the summary, The summary text information acquisition control means generates summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information. The extension generation means has a generation unit capable of performing the extension and generating the detailed text information, The detailed text information acquisition control means generates extended instruction information to be given to the generation unit of the extended generation means based on the generation instruction information. A loop repeat count determination means that determines the number of repetitions by the loop repeat control based on the generation instruction information, It also has, The computer system according to claim 2.

9. A generation instruction information receiving means that receives given generation instruction information for generating new detailed text information, Furthermore, The summary generation means has a generation unit capable of generating the summary, The summary text information acquisition control means generates summary instruction information to be given to the generation unit of the summary generation means based on the generation instruction information. The extension generation means has a generation unit capable of performing the extension and generating the detailed text information, The detailed text information acquisition control means generates extended instruction information to be given to the generation unit of the extended generation means based on the generation instruction information. A feedback control means that variably controls the summary instruction information in the loop repeat control based on the evaluation result of the detailed text information evaluation means. It also has, The computer system according to claim 3.

10. The repeat control means performs the repeat control based on the given repeat instruction information. The computer system according to claim 5.

11. The system further comprises means for specifying a particular portion of the first detailed text information to be retained in the summary, The summary text information acquisition control means performs control to acquire the first summary text information while retaining the specific portion. The computer system according to claim 1.

12. Remaining portion designation means for designating specific portions of the second detailed text information to be retained in the summary, Furthermore, The summary text information acquisition control means performs the following control in the loop repeat control: acquiring new first summary text information while retaining the specific portion. The computer system according to claim 4.

13. The system further includes a high-extension portion designation means for designating a specific portion of the first summary text information in which the degree of extension is relatively high, The detailed text information acquisition control means performs the expansion with a relatively high degree of expansion for the specific portion and controls the acquisition of the second detailed text information. The computer system according to claim 1.

14. The aforementioned summary text information acquisition control means is Summary generation condition setting means for setting summary generation conditions, The system has a summary generation means that generates a summary based on the summary generation conditions, thereby acquiring the first summary text information. The computer system according to claim 2.

15. The summary generation condition setting means sets the summary generation conditions based on the number of repetitions of the loop repeat control. The computer system according to claim 14.

16. The summary generation condition setting means sets the summary generation conditions based on the first detailed text information. The computer system according to claim 14.

17. The summary text information acquisition control means acquires the first summary text information as information in list format. The computer system according to claim 1.

18. The extension generation means performs the extension by adding new list-format information to the list-format information of the first summary text information. The computer system according to claim 17.

19. The aforementioned detailed text information acquisition control means is Extended generation condition setting means for setting extended generation conditions, The system has the following characteristics, and the second detailed text information is obtained by causing the extension generation means to perform the extension based on the extension generation conditions. The computer system according to claim 1.

20. The extended generation condition setting means sets the extended generation conditions based on the first detailed text information. The computer system according to claim 19.

21. A repeat control means that performs detailed repeat control to cause the detailed text information acquisition control means to repeatedly acquire the second detailed text information, The computer system according to claim 1, further comprising:

22. Detailed text information evaluation means for evaluating the second detailed text information, Furthermore, The repeat control means executes the detailed repeat control based on the evaluation result of the detailed text information evaluation means. The computer system according to claim 21.

23. The extension generation means generates detailed text information using a given extension randomness control parameter value for controlling the randomness related to the extension. Means for variably controlling the extended randomness control parameter value based on the number of repetitions of the detailed repeat control and / or the evaluation result of the detailed text information evaluation means, The computer system according to claim 22, further comprising:

24. A repeat control means that performs summary repeat control to cause the summary text information acquisition control means to repeatedly acquire the first summary text information, The computer system according to claim 1, further comprising:

25. Summary text information evaluation means for evaluating the first summary text information, Furthermore, The repeat control means executes the summary repeat control based on the evaluation result of the summary text information evaluation means. The computer system according to claim 24.

26. The summary generation means generates a summary using a given summary randomness control parameter value for controlling the randomness related to the generation of the summary, Means for variably controlling the summary randomness control parameter value based on the number of repetitions of the summary repeat control and / or the evaluation result of the summary text information evaluation means, The computer system according to claim 25, further comprising:

27. The detailed text information acquisition control means acquires the second detailed text information for the first summary text information selected from a plurality of first summary text information acquired by the summary repeat control based on a given condition. The computer system according to claim 24.

28. The detailed text information acquisition control means is instructed to acquire a plurality of second detailed text information from the first summary text information. In the loop repeat control, the repeat control means causes the summary text information acquisition control means to acquire new first summary text information, which is a second detailed text information selected from a plurality of second detailed text information based on a given condition, as new first detailed text information. The computer system according to claim 2.

29. The first detailed text information is information from a gameplay log of a given game, The computer system according to claim 1, which is capable of acquiring new gameplay log information as the second detailed text information.

30. Computer systems, Summary text information acquisition control means that controls the acquisition of first summary text information for first detailed text information using a summary generation means capable of generating a summary or outline (hereinafter collectively referred to as "summary") for given detailed text information. Detailed text information acquisition control means that performs control for acquiring second detailed text information about the first summary text information using an extension generation means capable of generating detailed text information by extending given summary text information, A program designed to function as such.

Images