Device and method

Abstract

Provided are a device and a method capable of appropriately generating a story by using multiple content items.　In a prompt generation device 100 according to the present disclosure, a news information acquisition unit 101 acquires multiple news information items (content items) from a news site 600. Then, a story instruction unit 104 generates and transmits a prompt for instructing a generative AI model 400 to generate a story, on the basis of the acquired multiple news information items. Then, a storage unit 105 stores story information generated by the generative AI model 400. The story information includes at least one of an introduction, a development, a turn, and a conclusion indicating a plot of the story.

Description

Apparatus and method

[0001] The present invention relates to an apparatus and method that utilizes a Large Language Model (LLM).

[0002] Patent Document 1 describes generating a story with an introduction, development, twist and conclusion using knowledge obtained from sensor data and dialogue with a user.

[0003] JP 2012-8839 A

[0004] However, the invention described in Patent Document 1 cannot be applied to content such as news articles distributed over the Internet. For example, when news of someone's death is announced, some news articles may be posted that provide detailed information about the person's background. Other news articles may only state the fact of death and the name of the illness. For such content, there is a demand to generate news content in the form of a story, but the invention described in Patent Document 1 has difficulty using the news article to generate news content in the form of an appropriate story.

[0005] Therefore, an object of the present invention is to provide an apparatus and method that can appropriately generate a story using a plurality of contents.

[0006] The device of the present invention comprises a content acquisition unit that acquires multiple contents, a story instruction unit that generates and outputs a prompt to instruct a generation AI to generate story information based on the multiple contents, and a story information acquisition unit that acquires the story information generated in the generation AI.

[0007] According to the present invention, a story can be appropriately generated using multiple contents.

[0008] FIG. 1 is a diagram illustrating a system configuration including a prompt generation device 100 according to the present disclosure. FIG. 2 is a diagram illustrating an outline of an operation for acquiring news information, such as the most recently published news information. FIG. 3 is a diagram illustrating an outline of an operation for tagging news information. FIG. 4 is a diagram illustrating an outline of an operation for acquiring news information based on target news information. FIG. 5 is a diagram illustrating a prompt generation process for extracting key points. FIG. 6 is a diagram illustrating a prompt generation process for generating a story. FIG. 7 is a diagram illustrating a functional configuration of the prompt generation device 100 according to the present disclosure. FIG. 8 is a diagram illustrating an article table stored in the article DB 300. FIG. 9 is a diagram illustrating an example of a prompt for indicating key points. FIG. 10 is a diagram illustrating an example of a prompt for instructing story generation. FIG. 11 is a flowchart illustrating the operation of the prompt generation device 100. FIG. 12 is a diagram illustrating an outline of generating story information (scenario) from collected news information according to the present disclosure. FIG. 13 is a diagram illustrating a functional configuration of a user terminal 500 equipped with the functions of the prompt generation device 100. FIG. 14 is a diagram illustrating an example of a hardware configuration of the prompt generation device 100 according to an embodiment of the present disclosure.

[0009] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0010] FIG. 1 is a diagram showing a system configuration including a prompt generation device 100 according to the present disclosure. As shown in the figure, the system includes the prompt generation device 100, an exclusion content prompt DB 200, an article DB 300, a file server 310, and a generation AI model 400. In response to a request (including instruction information for the target news) from a user terminal 500, the prompt generation device 100 accesses a news site 600, acquires the requested news information, stores it in the file server 300, and also stores the path to the article DB 300. The prompt generation device 100 then generates a prompt including the news information stored in the file server 310 and instructions for extracting the main points of the news information, and sends the prompt to the generation AI model 400. The generation AI model 400 generates story information according to the prompt.

[0011] The excluded content prompt DB 200 is a memory unit that stores expressions and content that are to be excluded from the content generated by the generation AI model 400, and the prompt generation device 100 generates the above prompt based on these expressions and content that are to be excluded.

[0012] 2 to 6 are diagrams showing an overview of the operation of the prompt generation device 100 of the present disclosure. As shown in Fig. 2, the prompt generation device 100 acquires target news information from a user terminal 500. The prompt generation device 100 also acquires recently published articles with a large number of views and news information that ranks highly in search results (process (1)), and stores this news information in the file server 310. The prompt generation device 100 also stores the paths of the news information stored in the file server 310 in the article DB 300 (process (3)).

[0013] As shown in FIG. 3 , the prompt generation device 100 then references the path in the article DB 300 (process (4)) and retrieves news information from the file server 310 (process (5)). Using the generation AI model 400 for the target news information, the prompt generation device 100 tags news information similar to the target news information in the article table in the article DB 300. Information such as genre is assigned to each piece of news information in advance, and tagging is performed on news information that is similar to the target news information (e.g., that has the same genre) based on the genre. In this disclosure, tagging refers to association processing. If there is no similar news information (or if genre information is not assigned), the prompt generation device 100 uses the generation AI model 400 to determine a category from the sentences that make up the news information and tag the news information indicating its similarity to the target news information (process (6)).

[0014] 4, the prompt generation device 100 extracts, from the tagged news information acquired in process (4) for the target news information specified by the user, news information that was generated on a date close to the target news information, based on the information in the article DB 300 (process (7)). The target news information is news information specified by the user in advance or when narrowing down the news information, and news information related to the target news information is extracted.

[0015] 5, the prompt generation device 100 generates a prompt that instructs the extraction of news information and its main points obtained from the article DB 300. The prompt generation device 100 then sends the prompt to the generation AI model 400 (process (9)). If there are expressions and content that the prompt generation device 100 wants to exclude, the prompt generation device 100 references the excluded content prompt DB 200 to exclude those expressions and content, and generates a prompt that reflects that (process (8)). The prompt generation device 100 sends the prompt for extracting the main points to the generation AI model 400 and obtains the generated main points.

[0016] As shown in Figure 6, the prompt generation device 100 generates a prompt that instructs the generation of a story with an introduction, development, twist, and conclusion at the acquired key points, and sends it to the generation AI model 400 (process (10)).

[0017] Next, a description will be given of the functional configuration of the prompt generation device 100. Fig. 7 is a diagram showing the functional configuration of the prompt generation device 100 of the present disclosure. As shown in the figure, the prompt generation device 100 includes a news information acquisition unit 101, a tag management unit 102, a gist indication unit 103, a story indication unit 104, a storage unit 105, and an output unit 106.

[0018] The news information acquisition unit 101 acquires news information that satisfies acquisition conditions from news sites 600 on a network (e.g., the Internet). The acquisition conditions are, for example, news information that was recently published (published within a recent specified period), news information with a large number of views, or news information with a large number of search results. For example, the news information acquisition unit 101 acquires news information that was published within the past week from each news site 600. The news information acquisition unit 101 stores the acquired news information in the file server 310 and also stores the path to the news information in the article DB 300. Note that this is just an example, and other conditions may also be used as acquisition conditions.

[0019] FIG. 8( a) is a diagram showing an article table stored in the article DB 300. As shown in the diagram, this article table associates news titles, publication dates, path information, and genres. The news titles and publication dates are information acquired by the news information acquisition unit 101 from the news site 600. The substantive information of the news information (text information, image information, etc.) is stored in the file server 310 and is configured to be acquireable by referencing the path information of the article table. The genre is management information assigned to each piece of news information. FIG. 8( b) is a diagram showing a tag table. Based on the genres stored in the article table, tag information is assigned to news information similar to the target news information (i.e., news information that matches the genre). In the diagram, check information (circles in the diagram) is assigned to the tag information column.

[0020] The tag management unit 102 is a part that checks the tag column of news information that matches the genre of the target news information in the tag table of the article DB 300. If the tag management unit 102 cannot find news information similar to the target news information based on the genre, it acquires news information similar to the target news information based on the sentences that make up the news information. In this case, news information similar in meaning to the target news information is acquired based on natural language analysis, which is a publicly known technology, but the similar news information may also be determined by the generation AI model 400. For example, the tag management unit 102 may generate a prompt including the target news information, the news information, and instructions for selecting similar news information, and send the prompt to the generation AI model 400 to acquire news information similar to the target news information and store it in the tag table.

[0021] The gist instruction unit 103 is a part that generates and requests a gist instruction prompt to the generation AI model 400 to generate the gist of the acquired news information. FIG. 9 is a diagram showing an example of the gist instruction prompt. As shown in the figure, a gist instruction prompt is generated from the news information (path information or actual information of the news information) stored in the article DB 300, indicating an instruction to acquire news information similar to the target news information and its gist. The request portion is a standard portion, and pre-stored information is reflected in the prompt. The gist instruction unit 103 acquires the generation result (similar news information and its gist) from the generation AI model 400.

[0022] The story instruction unit 104 generates and instructs a prompt for generating a story with a clear beginning, development, twist, and conclusion (development information) based on the key points acquired by the key point instruction unit 103. FIG. 10 is a diagram showing an example of the prompt. As shown in the figure, this prompt includes a command to generate a story with a clear beginning, development, twist, and conclusion based on the key points, and includes the gist of each news item as a news information group. The request portion is a fixed portion, and pre-stored information is reflected in the prompt.

[0023] The story direction unit 104 obtains the story information (information constituting the beginning, development, twist and conclusion) that is the generated result from the generative AI model 400 and stores it in the memory unit 105.

[0024] The storage unit 105 is a part that stores story information that is the result of generation obtained by the story direction unit 104 .

[0025] The output unit 106 is a part that outputs the stored story information to an external device, etc. For example, it outputs it to the user terminal 500 that has requested the generation of the story information.

[0026] The operation of the prompt generation device 100 configured as above will now be described. Fig. 11 is a flowchart showing the operation of the prompt generation device 100.

[0027] When the news information acquisition unit 101 receives the designation of target news information, it acquires news information (including genre information) that satisfies the acquisition conditions, such as recently published news information or news information that ranks highly in search results (S101). The news information acquisition unit 101 uploads the acquired news information to the file server 310 and stores the path to the news information in the article DB 300 (S102, S103).

[0028] The tag management unit 102 assigns tag information to news information similar to the target news information in the article table stored in the article DB 200 (S104).

[0029] The gist designation unit 103 refers to the tag table and acquires from the article table news information tagged with tags whose creation date and time is close to that of the target news information (within a predetermined time period) (S105).The gist designation unit 103 then generates a prompt requesting the acquisition of similar news information and the extraction of its gist, and transmits it to the generation AI model 400 (S106).

[0030] The story instruction unit 104 generates a prompt to instruct the generation of a story with a clear beginning, development, twist, and conclusion based on the generation results (similar news information and its gist) obtained by the gist instruction unit 103, and transmits the generated prompt to the generation AI model 400 (S107). The story instruction unit 104 obtains the generation results (story information) from the generation AI model 400 and stores the information in the memory unit 105 (S108). The output unit 106 transmits the stored story information to an external device, for example, a user terminal 500 (S109).

[0031] FIG. 12 is a diagram showing an overview of generating story information (scenario) from news information collected according to the present disclosure. FIG. 12(a) shows scraping of news information, showing news information that meets the acquisition conditions. FIG. 12(b) is a diagram showing the main points of the news information. As described above, the main points of each piece of news information are extracted using the generation AI model 400. FIG. 12(c) is a diagram showing the story information (scenario). As shown in the figure, the story information is divided into an introduction, development, twist, and conclusion, and generated by the generation AI model 400. This story information organized into an introduction, development, twist, and conclusion is output to a user terminal, etc., and story information for a certain target news item can be generated.

[0032] Next, the effects of the prompt generation device 100 of the present disclosure will be described. In the prompt generation device 100 of the present disclosure, the news information acquisition unit 101 functions as a content acquisition unit and acquires, from a news site 600, news information (content) that satisfies acquisition conditions (such as recently published news) from among multiple pieces of news information. The story instruction unit 104 then generates and transmits a prompt to instruct the generation AI model 400 to generate a story based on the multiple pieces of acquired news information. The memory unit 105 then stores the story information generated by the generation AI model 400. This story information includes at least one of an introduction, development, twist, and conclusion that indicates the development of the story.

[0033] This configuration allows a story to be appropriately generated using content such as multiple pieces of news information. In particular, news information is covered differently by different news organizations, and because off-topic parts are often exaggerated to increase view counts, there is a time-consuming process of checking multiple information sources and identifying the main points and gist of the news. In the present disclosure, this time can be reduced by using the generative AI model 400. Furthermore, to turn news information into a story, such as a comic, a writer needs to understand the news information and create a scenario, which takes time and money. However, the present disclosure can reduce this time and cost.

[0034] In the present disclosure, the system further includes a gist instruction unit 103 that generates and requests a prompt to instruct the generation of gist of multiple news information to the generation AI model 400. Then, the story instruction unit 104 generates the prompt based on the gist generated by the generation AI model 400.

[0035] In the present disclosure, the gist of each news item is grasped, and a prompt for generating story information is generated based on the gist. This allows more appropriate story information to be generated. In the above disclosure, the gist indicator 103 is used for the explanation, but this is not necessarily required, and the prompt for generating story information may be generated using the news item itself.

[0036] In the present disclosure, the story direction unit 104 generates a prompt based on news information of the same genre and within a predetermined time range among a plurality of pieces of news information. For example, the story direction unit 104 narrows down the news information that is the source of the generation of the story information based on news information that has the same tag information (such as genre) as the target news information and date information such as the publication date of the target news information, the registration date on the site, or the occurrence date of the target news information, and generates a prompt using the news information.

[0037] According to this configuration, news information related to the target news information can be selected, and a prompt for generating appropriate story information can be generated.

[0038] The news information acquisition unit 101 also acquires news information that meets acquisition conditions from news sites 600 on a network such as the Internet. For example, the acquisition conditions may include the publication date and time of the news information (or the date and time of the incident), the number of views by other users, or the number of searches. The number of views and the number of searches are numbers managed by each site, and these can be used.

[0039] The present disclosure further includes an article DB 300 (content DB) that stores news information acquired by the news information acquisition unit 101 together with tag information indicating the genre and date and time information (e.g., publication date, incident occurrence date, etc.) related to the news information. The story direction unit 104 generates a prompt using the tag information and the date and time information.

[0040] According to this configuration, it is possible to generate story information by narrowing down the news information to news information related to the target news information, and to provide appropriate content.

[0041] Furthermore, the story direction unit 104 references exclusion content information indicating predetermined exclusion content, and generates prompts so that the story information reflects the exclusion content information. The exclusion content information is, for example, information stored in an external database, the exclusion content prompt DB 200, and is information that prescribes expressions and content to be excluded.

[0042] According to this configuration, it is possible to generate appropriate story information without obtaining story information that includes unpleasant expressions or content.

[0043] As shown in FIG. 13 , all or some of the generative AI model 400 and article DB 300 in the present disclosure may be located in the prompt generation device 100 or the user terminal 500. Furthermore, the user terminal 500 may have the functions of the prompt generation device 100 and function as the prompt generation device 100. There are generative AI models of a type, such as tsuzumi, in which the generative AI model is located within the user terminal 500. In this type, the RAG app is also provided in the user terminal 500. However, the information accessed by the RAG (knowledge DB) may be located within the user terminal 500 or on the network. There are also types, such as ChatGPT, in which the generative AI model is located on the network. In this type, the RAG app is provided in the user terminal 500. However, the information accessed by the RAG (knowledge DB) is located on the network.

[0044] A generative AI model, such as an LLM, is a model that can generate content in response to a prompt containing input information, based on the instructions, context, question, and output format indicated by the prompt, and return the content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeted at the input information. The generative AI model may be, for example, an interactive AI model that includes a large language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, and the like. In this embodiment, the prompt generation device 100 is capable of providing content provision functions using interactive AI models, which are multiple types of models. These interactive AI models may be stored within the prompt generation device 100, or may be stored in another device connected to the prompt generation device 100 via a network so that information can be exchanged with the user via the prompt generation device 100. Although only one prompt generation device 100 is shown in the figure, multiple prompt generation devices 100 may be included.

[0045] In this disclosure, a prompt is information indicating an instruction or question entered by a user in an interactive system such as an interaction with a generative AI model or a command line interface (CLI).

[0046] The device and method of the present disclosure have the following configuration.

[0047] [1] An apparatus comprising: a content acquisition unit that acquires multiple pieces of content; a story instruction unit that generates and outputs a prompt to instruct a generation AI to generate story information based on the multiple pieces of content; and a story information acquisition unit that acquires story information generated by the generation AI.

[0048] [2] The device described in [1] further comprises a gist instruction unit that generates and outputs a prompt to instruct a generation AI to generate the gist of the multiple contents based on the multiple contents, and the story instruction unit generates the prompt based on the gist generated by the generation AI.

[0049] [3] The device according to [1] or [2], wherein the story direction unit selects content from the plurality of pieces of content that is in the same genre and within a predetermined time range based on the target content, and generates the prompt based on the selected content.

[0050] [4] The device described in [3], wherein the story instruction unit accesses a content DB that stores the content acquired by the content acquisition unit together with tag information indicating a genre and date and time information related to the content, and generates the prompt using the tag information and date and time information.

[0051] [5] The device according to any one of [1] to [4], wherein the content acquisition unit acquires content that satisfies acquisition conditions from a site on a network.

[0052] [6] The device according to any one of [1] to [5], wherein the story instruction unit references exclusion content information indicating predetermined exclusion content, and generates the prompt so that the story reflects the exclusion content information.

[0053] [7] The device according to any one of [1] to [6], wherein the story information includes at least one of an introduction, development, twist, and conclusion that indicate the development of the story information.

[0054] [8] A method for an apparatus, comprising: a content acquisition step of acquiring a plurality of pieces of content; a story instruction step of generating and requesting a prompt to instruct a generation AI to generate a story based on the plurality of pieces of content; and a storage step of storing the story development information in a storage unit.

[0055] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0056] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0057] For example, the prompt generation device 100 according to an embodiment of the present disclosure may function as a computer that performs processing of the prompt generation method of the present disclosure. Fig. 14 is a diagram illustrating an example of the hardware configuration of the prompt generation device 100 according to an embodiment of the present disclosure. The prompt generation device 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0058] In the following description, the term "device" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the prompt generation device 100 may be configured to include one or more of the devices shown in the figures, or may be configured to exclude some of the devices.

[0059] Each function in the prompt generating device 100 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0060] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned tag management unit 102, gist indication unit 103, story indication unit 104, etc. may be realized by the processor 1001.

[0061] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the tag management unit 102 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0062] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be referred to as a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store executable programs (program codes), software modules, etc. for implementing a prompt generation method according to one embodiment of the present disclosure.

[0063] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0064] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the news information acquisition unit 101, the output unit 106, etc., described above may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmission unit and a reception unit that are physically or logically separated.

[0065] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0066] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0067] Furthermore, prompt generation device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by such hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

[0068] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0069] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0070] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0071] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0072] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0073] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0074] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0075] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0076] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0077] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0078] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0079] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0080] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0081] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0082] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0083] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0084] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0085] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0086] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0087] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0088] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0089] 100...prompt generation device, 200...exclusion content prompt DB, 300...article DB, 310...file server, 400...generative AI model, 500...user terminal, 600...news site, 300...file server, 101...news information acquisition unit, 102...tag management unit, 103...main point indication unit, 104...story indication unit, 105...memory unit, 106...output unit.

Claims

1. An apparatus comprising: a content acquisition unit that acquires multiple pieces of content; a story instruction unit that generates and outputs a prompt to instruct a generation AI to generate story information based on the multiple pieces of content; and a story information acquisition unit that acquires story information generated by the generation AI.

2. The device described in claim 1, further comprising a gist instruction unit that generates and outputs a prompt to instruct a generation AI to generate the gist of the multiple contents based on the multiple contents, and the story instruction unit generates the prompt based on the gist generated by the generation AI.

3. The device according to claim 1, wherein the story direction unit selects, from the plurality of pieces of content, content that is in the same genre and within a predetermined time range based on the target content, and generates the prompt based on the selected content.

4. The device described in claim 3, wherein the story instruction unit accesses a content DB that stores the content acquired by the content acquisition unit together with tag information indicating the genre and date and time information related to the content, and generates the prompt using the tag information and date and time information.

5. The device according to claim 1, wherein the content acquisition unit acquires content that satisfies acquisition conditions from a site on a network.

6. The device according to claim 1, wherein the story instruction unit references exclusion content information indicating predetermined exclusion content, and generates the prompt so that the story reflects the exclusion content information.

7. The device according to claim 1, wherein the story information includes at least one of an introduction, development, twist, and conclusion that indicate the development of the story information.

8. A method of an apparatus comprising: a content acquisition step of acquiring a plurality of pieces of content; a story instruction step of generating and requesting a prompt to instruct a generation AI to generate a story based on the plurality of pieces of content; and a storage step of storing the story development information in a storage unit.

Images