Device and method

Abstract

Provided is a device capable of generating a sentence that verbalizes a verbalization target. This device is provided with: a reception unit that receives target information regarding a verbalization target; and a prompt generation unit that generates, on the basis of the target information, a prompt instructing that a sentence that verbalizes the verbalization target be generated.

Description

Apparatus and method

[0001] The present disclosure relates to an apparatus and method for generating a sentence that verbalizes a subject to be verbalized.

[0002] Patent Literature 1 describes a device that, when a user inputs a song to be searched for, outputs information about songs similar to the song. By using this device, a user can, for example, input information about a song they like and obtain information about songs similar to the song they like.

[0003] International Publication No. 2014 / 068744

[0004] For example, there are non-verbal things such as music. If such non-verbal things are expressed as text, it becomes easier for a user to understand, for example, why a certain piece of music is liked. The above-mentioned device cannot obtain a text that verbalizes a favorite piece of music, but can only obtain information about similar pieces of music.

[0005] Therefore, the present disclosure describes an apparatus and method capable of generating a sentence that verbalizes a verbalization target.

[0006] The device according to the present disclosure includes a receiving unit that receives target information related to the target to be verbalized, and a prompt generating unit that generates a prompt that instructs the generation of a sentence verbalizing the target to be verbalized based on the target information.

[0007] According to the present disclosure, it is possible to generate a sentence that verbalizes a subject to be verbalized.

[0008] FIG. 1 is a diagram showing the overall configuration of a system including a prompt generation device of the present disclosure. FIG. 2 is a block diagram showing the functional configuration of the prompt generation device. FIG. 3 is a diagram showing an example of a prompt generated by a prompt generation unit when the verbalization target is a song. FIG. 4 is a diagram showing an example of an answer generated by an LLM based on a prompt when the verbalization target is a song. FIG. 5 is a diagram showing an example of a prompt generated by a prompt generation unit when the verbalization target is alcohol. FIG. 6 is a diagram showing an example of an answer generated by an LLM based on a prompt when the verbalization target is alcohol. FIG. 7 is a flowchart showing the processing flow of a method performed by a prompt generation device to generate a sentence verbalizing a verbalization target. FIG. 8 is a diagram showing an example of the hardware configuration of a prompt generation device.

[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 the overall configuration of a system including a prompt generation device according to the present disclosure. This system generates sentences that verbalize a target for verbalization. As shown in FIG. 1, this system includes a prompt generation device (device) 100 and an LLM (generative AI model) 200. The prompt generation device 100 and the LLM 200 are communicatively connected to each other via a network (NM). A user terminal 300 is communicatively connected to the prompt generation device 100 via the network.

[0011] The user terminal 300 transmits a request for verbalization to the prompt generation device 100, expressing the verbalization target in words. Here, the user terminal 300 transmits target information regarding the verbalization target as the request for verbalization of the verbalization target. This verbalization target may be non-verbal. The verbalization target may be, for example, a piece of music, food or drink, a picture, etc. This picture may include a painting or a photograph. For example, the user can input target information for the verbalization target by operating the user terminal 300.

[0012] The prompt generation device 100 generates a prompt in response to a verbalization request from the user terminal 300, transmits the prompt to the LLM 200, and receives a response. The prompt generation device 100 transfers the response to the user terminal 300. For example, the user terminal 300 displays the response transferred from the prompt generation device 100 on a display screen or the like. This allows the user of the user terminal 300 to recognize the response.

[0013] The LLM 200 generates an answer based on the prompt sent from the prompt generation device 100. The LLM 200 sends the generated answer to the prompt generation device 100. The LLM 200 may be located within the prompt generation device 100. Alternatively, the prompt generation device 100 or the LLM 200 may be located within the user terminal 300.

[0014] In this disclosure, the LLM 200 is used as the language model, but other models may be used as long as they are generative AI models. In this disclosure, a generative AI model is a model that can generate content in response to a prompt containing input information, according to 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, etc. In this disclosure, the prompt generation device 100 is capable of providing content provision functions using multiple types of interactive AI 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.

[0015] 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).

[0016] 2 is a block diagram showing the functional configuration of the prompt generation device. As shown in FIG. 2, the prompt generation device 100 includes a receiving unit 110 and a prompt generation unit 120. The receiving unit 110 receives object information related to a target to be verbalized from a user terminal 300. The object information is information that represents the target to be verbalized.

[0017] For example, if the target to be verbalized is a song, the target information received by the receiving unit 110 includes song information about the song to be verbalized. The song information may include any of the song title, composer name, singer name, performer name, instrument name, music genre, etc. The song information may also include specific information that identifies a portion of the song. The specific information that identifies a portion of the song may be represented, for example, by a time span from the start of the song's performance, a bar number, etc. Furthermore, the song information may be the song itself (song data itself). In this case, the song information may include song data for only a portion of the song, rather than the entire song.

[0018] For example, if the target to be verbalized is food or drink, the target information received by the receiving unit 110 includes food or drink information related to the target to be verbalized. The food or drink information may include any of the food or drink genre, food or drink name, product name, ingredient name, cooking method, and eating method.

[0019] For example, if the target to be verbalized is a picture, the target information received by the receiving unit 110 includes picture information about the picture to be verbalized designated by the user. The picture information may include any of the genre of the picture, the title of the work, the name of the artist, the name of the photographer, etc. Furthermore, the picture information may be the picture itself (the picture data itself).

[0020] The prompt generation unit 120 generates a prompt that instructs the LLM 200 to generate a sentence that verbalizes the verbalization target based on the target information of the verbalization target acquired by the reception unit 110. This prompt includes a task, which is the instruction content, and the acquired target information. The prompt generation unit 120 can instruct the LLM 200 on which information source to use to verbalize the verbalization target. For example, the prompt generation unit 120 can include in the prompt an instruction to generate a sentence based on a review article about the verbalization target. In this case, the prompt generation unit 120 can include in the prompt an instruction to generate a sentence based on the usefulness of the review article.

[0021] The review article may be, for example, information available on the Internet (including social networking sites), information stored in a storage unit that stores multiple review articles, or information previously held by the LLM 200. The prompt generation unit 120 may generate a prompt that specifies a reference destination for the review article depending on the subject to be verbalized. For example, the reference destination for the review article may be predetermined depending on the genre of the subject to be verbalized or the content of the subject information.

[0022] The usefulness of a review article is information that serves as an index for determining which of a plurality of review articles should be referenced when generating a sentence. For example, the usefulness of a review article may be determined based on the number of times the review article has been viewed. In this case, the more times the review article has been viewed, the more useful the review article may be considered to be. For example, if a review article has been assigned a rating (e.g., a rating of whether it was helpful or not, a rating of whether the article was good or bad, etc.), the usefulness may be determined based on this rating. For example, the prompt generation unit 120 may include in the prompt an instruction to generate a sentence by preferentially referring to review articles with high usefulness.

[0023] When the target to be verbalized is a piece of music, the prompt generation unit 120 can include in the prompt an instruction to generate a sentence based on the results of music analysis, such as rhythm and sound expression techniques. The receiving unit 110 receives music information about the piece of music to be verbalized as target information. The prompt generation unit 120 includes in the prompt an instruction to generate a sentence based on the results of music analysis of the piece of music to be verbalized. The music information may include specific information that identifies a portion of the music. The specific information that identifies a portion of the music is information for identifying a portion in the music specified by the user, such as a portion containing a rhythm that the user prefers. In this case, the prompt generation unit 120 can include in the prompt an instruction to generate a sentence based on the results of music analysis of the portion of the music identified by this specific information.

[0024] For example, music analysis results such as rhythm and sound expression techniques may be learned (stored) in advance in the LLM 200. Furthermore, for example, the LLM 200 may acquire the music analysis results of the music from an analysis device or the like when generating sentences for the music to be verbalized.

[0025] In addition to an instruction to generate a sentence verbalizing the target for verbalization, the prompt generation unit 120 may also include an instruction to request related object information about related objects related to the target for verbalization. Related objects are, for example, things similar to the target for verbalization, things that have many things in common with the target for verbalization, or things that have the same characteristics as the target for verbalization. Related object information about related objects is information that represents the related objects, similar to the target information about the target for verbalization. Thus, if a user inputs information about a favorite song as target information about the target for verbalization, the LLM 200 outputs information about songs (related objects) related to this song (related object information).

[0026] For example, the prompt generation unit 120 may extract points about the target to be verbalized from the review article and include in the prompt an instruction to output related target information about a related target that satisfies or is similar to the extracted points. Also, if the target to be verbalized is a song, the prompt generation unit 120 may extract points from the music analysis results and include in the prompt an instruction to output related target information about a related target that satisfies or is similar to the extracted points.

[0027] The prompt generator 120 transmits the generated prompt to the LLM 200 and acquires an answer corresponding to the prompt from the LLM 200. The prompt generator 120 transmits the answer acquired from the LLM 200 to the user terminal 300.

[0028] A specific example of a prompt generated by the prompt generating unit 120 and an output from the LLM 200 will be described below. First, an example will be described in which the object to be verbalized is a piece of music, and a user verbalizes a piece of music that the user likes.

[0029] 3, the prompt generation unit 120 generates a prompt including the following instruction as an example of a task: "By utilizing online review articles and music analysis results, infer why the user likes the following and generate an explanation for it. Also, please generate the explanation while paying attention to the following points: - If the favorite part is not "the whole" (if the favorite part is specified), explain the musical techniques and rhythm used in that part. - When referring to review articles, give priority to those that are highly useful, such as those with a high number of views. - If there is a song that meets the points extracted from the above two points, present it."

[0030] The prompt generation unit 120 also includes the following target information received by the reception unit 110 in the prompt as "what the user likes." Here, an example is shown in which the prompt generation unit 120 generates a prompt by including two pieces of target information (music information) in one prompt: "Type: Music Favorite song: Song A1 by singer A Favorite part: Whole" "Type: Music Favorite song: Song B1 by singer B Favorite part: 2 minutes 30 seconds to 3 minutes 00 seconds"

[0031] In this example prompt, the content of the task column instructs the user to generate a sentence that verbalizes the target song. The task column states, "Utilize online reviews and music analysis results to infer why users like the following and generate an explanatory sentence." This corresponds to an instruction to generate a sentence based on reviews of the target song and an instruction to generate a sentence based on the music analysis results of the target song. The task column states, "If the favorite part is not 'the whole song' (if a favorite part is specified), explain the musical techniques and rhythm used in that part." This corresponds to an instruction to generate a sentence based on the music analysis results of the target song. The task column states, "Give priority to review articles that are highly useful, such as those with a high number of views." This corresponds to an instruction to generate a sentence based on the usefulness of the review article. The task column states, "If there is a song that meets the points extracted from the above two points, present it." This corresponds to an instruction to request information (related object information) about songs related to the target song (related objects). The content of "Favorite Song" in the "User's Preferences" column corresponds to song information (target information) about the song to be verbalized. The content of "Favorite Part" in the "User's Preferences" column corresponds to specific information that identifies a part of the song.

[0032] The prompt generation unit 120 transmits the generated prompt shown in Fig. 3 to the LLM 200. Based on this prompt, the LLM 200 generates a sentence that serves as a response, for example, by creating a summary by referring to the corresponding review article or by creating an explanatory sentence based on the music analysis results.

[0033] As shown in Figure 4, the LLM 200 generates the following answer as an example: "Your favorite song A1 by singer A is characterized by AAA and BBB. The part you like in singer B's song B1 uses a musical technique called CCC. This technique seems to often give the impression of DDD. An example of a song that uses a similar technique is song E."

[0034] In this way, the prompt generation device 100 and the LLM 200 can generate a sentence that verbalizes a user's favorite song based on, for example, song information about the favorite song input by the user. The prompt generation device 100 and the LLM 200 can also present other songs that satisfy the user's preferences. By checking the sentence generated by the LLM 200, the user can understand, for example, why the user likes a particular song. Furthermore, by checking the songs suggested by the LLM 200, the user can find other songs that satisfy the user's preferences.

[0035] Next, an example will be described in which the object to be verbalized is alcohol, and the user verbalizes their favorite alcohol. As shown in FIG. 5 , the prompt generation unit 120 generates a prompt including the following instruction as an example of a task: "By utilizing online review articles, infer the reasons why the user likes the following items and generate an explanation for them. Also, please generate the explanation while paying attention to the following points: - When referencing review articles, give priority to those that are highly useful, such as those with a high number of views. - If there is an alcohol that meets the above points, present it."

[0036] The prompt generation unit 120 also includes the following target information received by the reception unit 110 in the prompt as "what the user likes." Here, an example is shown in which the prompt generation unit 120 generates a prompt that includes two pieces of target information: "Type: Alcohol Favorite Alcohol: Japanese Sake Name F Junmai Daiginjo Favorite Way to Drink: Cold" "Type: Alcohol Favorite Alcohol: Japanese Sake Name G Junmai Daiginjo Favorite Way to Drink: Cold"

[0037] In this example prompt, the content of the task column instructs the user to generate a sentence that verbalizes the target alcoholic beverage. The task column states, "Utilize online review articles to infer why the user likes the following and generate an explanatory sentence." This corresponds to the instruction to generate a sentence based on the review articles about the target alcoholic beverage. The task column states, "Priority review articles based on usefulness, such as those with the most number of views." This corresponds to the instruction to generate a sentence based on the usefulness of the review articles. The task column states, "If there is an alcoholic beverage that meets the points extracted from the above, present it." This corresponds to the instruction to request information (related target information) about alcoholic beverages related to the target alcoholic beverage (related target). The content of "Favorite alcoholic beverages" and "Favorite drinking style" in the "User's preferences" column corresponds to information (target information) about the target alcoholic beverage.

[0038] As shown in FIG. 6, the LLM 200 generates the following answer as an example: "Your favorite sake name F, Junmai Daiginjo, is characterized by HHH and JJJ. Your favorite sake name G, Junmai Daiginjo, is characterized by KKK and LLL. A common feature of the above is MMM. A sake with similar characteristics is sake name N."

[0039] In this way, the prompt generation device 100 and the LLM 200 can generate a sentence that verbalizes a user's favorite alcoholic beverage based on, for example, information about the user's favorite alcoholic beverage (target information) input by the user. The prompt generation device 100 and the LLM 200 can also present other alcoholic beverages that satisfy the user's preferences. By checking the sentence generated by the LLM 200, the user can understand, for example, why the user likes a particular alcoholic beverage. Furthermore, by checking the alcoholic beverages suggested by the LLM 200, the user can find other alcoholic beverages that satisfy the user's preferences.

[0040] Next, the flow of processing of the method for verbalizing a verbalization target performed in the prompt generation device 100 will be described. FIG. 7 is a flowchart showing the flow of processing of the method for verbalizing a verbalization target performed in the prompt generation device. As shown in FIG. 7, the reception unit 110 receives object information related to the verbalization target from the user terminal 300 (S101: reception step). The prompt generation unit 120 generates a prompt that instructs the generation of a sentence verbalizing the verbalization target based on the acquired object information (S102: prompt generation step). The prompt generation unit 120 transmits the generated prompt to the LLM 200 (S103: prompt transmission step).

[0041] The prompt generation unit 120 acquires an answer to the sent prompt from the LLM 200 (S104: answer acquisition step). The prompt generation unit 120 transmits the acquired answer to the user terminal 300 (S105: answer transmission step). The user terminal 300 acquires the answer from the prompt generation device 100 and displays the answer on a display unit or the like. This allows the user to acquire a sentence that verbalizes the verbalization target.

[0042] As described above, the receiving unit 110 of the prompt generation device 100 receives object information related to the verbalization target. Based on the received object information, the prompt generation unit 120 generates a prompt that instructs the user to generate a sentence that verbalizes the verbalization target. Based on this prompt, the LLM 200 generates a sentence that verbalizes the verbalization target. In this way, the prompt generation device 100 can generate a sentence that verbalizes the verbalization target. This allows the user to recognize, as a language, a verbalization target, such as a piece of music, which is difficult to express in words, using the prompt generation device 100. For example, the user can verbalize a favorite piece of music as the verbalization target. In this case, the user can refer to the sentence in which the favorite piece of music is verbalized to find a new favorite piece of music.

[0043] The receiving unit 110 receives information about non-verbal objects as the object to be verbalized. This allows the prompt generation device 100 to generate verbalized sentences about non-verbal objects such as music, food, drink, and pictures. This allows the user to verbalize things that are difficult for the user to express in words by using the prompt generation device 100.

[0044] The prompt generation unit 120 generates a prompt including an instruction to generate a sentence based on a review article about the target to be verbalized, thereby enabling the prompt generation device 100 to obtain the sentence generated based on the review article as a sentence obtained by verbalizing the target to be verbalized.

[0045] Review articles contain a mixture of appropriate and inappropriate content. For this reason, the prompt generation unit 120 generates a prompt that includes an instruction to generate a sentence based on the usefulness of the review article. This allows the prompt generation device 100 to obtain a sentence with more appropriate content as the sentence that verbalizes the target.

[0046] When the target to be verbalized is a song, the receiving unit 110 acquires song information (e.g., song title) related to the song to be verbalized. The prompt generating unit 120 generates a prompt based on the acquired song information such as the song title. This allows the user to input the song information into the user terminal 300 and acquire a sentence that verbalizes the song corresponding to the song information.

[0047] When the target to be verbalized is a piece of music, the prompt generation unit 120 generates a prompt including an instruction to generate a sentence based on the music analysis results. This allows the prompt generation device 100 to obtain a sentence that includes the music analysis results as a verbalized version of the music. For example, the user can recognize the analysis results, such as the rhythm or tempo of the music.

[0048] The receiving unit 110 can acquire music information that includes specification information that identifies a portion of a music piece. In this case, the prompt generation unit 120 includes in the prompt an instruction to generate a sentence based on the music analysis results of the portion of the music piece identified by the specification information. This allows the prompt generation device 100 to acquire a sentence that includes the music analysis results of the portion indicated by the user. The user can then recognize the music analysis results for the portion they specified.

[0049] The prompt generation unit 120 includes in the prompt an instruction to request related object information about a related object related to the verbalization object. In this case, the prompt generation device 100 can acquire related object information about the related object by adding the verbalization object to a verbalized sentence. This allows the user to find, for example, a new song related to a favorite song.

[0050] The prompt generation unit 120 generates a prompt that instructs the generation of a sentence that verbalizes the verbalization target. The prompt generation unit 120 transmits the generated prompt to the LLM 200 and obtains an answer (sentence) generated by the LLM 200. This allows the prompt generation unit 120 to verbalize the verbalization target using the LLM 200.

[0051] The method for generating a sentence verbalizing the target for verbalization performed by the prompt generation device 100 includes a receiving step for receiving target information related to the target for verbalization, and a prompt generation step for generating a prompt that instructs the generation of a sentence verbalizing the target for verbalization. In this way, this method can generate a sentence verbalizing the target for verbalization.

[0052] The above description is an example of the present disclosure and is not limited to these descriptions. For example, the verbalization target described in the present disclosure is not limited to music, food, drink, or pictures. The verbalization target is non-verbal, but may be expressed in language. The prompts and their responses described above are provided for illustrative purposes and are not limited to these examples. The instructions included in the prompts may be changed as appropriate.

[0053] The device and method of the present disclosure have the following configuration.

[0054] [1] A device comprising: a receiving unit that receives object information related to a target for verbalization; and a prompt generating unit that generates a prompt that instructs the user to generate a sentence that verbalizes the target for verbalization based on the object information. [2] The device described in [1] above, wherein the target for verbalization is non-verbal. [3] The device described in [1] or [2] above, wherein the prompt includes an instruction to generate the sentence based on a review article related to the target for verbalization. [4] The device described in [3] above, wherein the prompt includes an instruction to generate the sentence based on the usefulness of the review article. [5] The device described in any one of [1] to [4] above, wherein the target for verbalization is a piece of music, and the target information includes music information related to the piece of music to be verbalized. [6] The device described in [5] above, wherein the prompt includes an instruction to generate the sentence based on a music analysis result of the piece of music to be verbalized. [7] The device described in [6] above, wherein the music information includes specification information that specifies a portion of the music, and the prompt includes an instruction to generate the sentence based on a musical analysis result of the portion of the music to be verbalized that is specified by the specification information. [8] The device described in any one of [1] to [7] above, wherein the prompt includes an instruction to request related object information about a related object related to the target to be verbalized. [9] The device described in any one of [1] to [8] above, wherein the prompt generation unit sends the prompt to a generative AI model and obtains an answer corresponding to the prompt from the generative AI model.

[10] A method including: a receiving step of receiving object information about a target to be verbalized; and a prompt generation step of generating a prompt that instructs the generation of a sentence verbalizing the target to be verbalized based on the object information.

[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, judgment, 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 method for generating a sentence that verbalizes a verbalization target according to the present disclosure. Fig. 8 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, for example, runs an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 110 and prompt generation unit 120 may be realized by the processor 1001.

[0061] The processor 1001 also loads programs (program code), 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 reception unit 110 and the prompt generation unit 120 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used 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 be configured to 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). The communication device 1004 may be implemented with a transmitter and a receiver 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, the 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 the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware. 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 using 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, such as an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0068] 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.

[0069] 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.

[0070] 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).

[0071] 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).

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0078] 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.

[0079] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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."

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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."

[0088] 100...prompt generation device (device), 110...reception unit, 120...prompt generation unit, 200...LLM (generation AI model), 300...user terminal.

Claims

1. A device comprising: a receiving unit that receives target information regarding a target to be verbalized; and a prompt generating unit that generates a prompt that instructs the generation of a sentence that verbalizes the target to be verbalized based on the target information.

2. The device according to claim 1, wherein the object to be verbalized is non-verbal.

3. The device of claim 1, wherein the prompt includes an instruction to generate the sentence based on a review article about the subject to be verbalized.

4. The device of claim 3, wherein the prompt includes instructions to generate the sentence based on the helpfulness of the review article.

5. The device according to claim 1, wherein the object to be verbalized is a piece of music, and the object information includes music information about the piece of music to be verbalized.

6. The device of claim 5, wherein the prompt includes instructions to generate the sentence based on a musical analysis result of the song to be verbalized.

7. The device described in claim 6, wherein the music information includes specific information that identifies a portion of the music, and the prompt includes instructions to generate the sentence based on musical analysis results of the portion of the music to be verbalized that is identified by the specific information.

8. The device of claim 1, wherein the prompt includes an instruction requesting related object information about a related object related to the verbalized object.

9. The device of claim 1, wherein the prompt generator transmits the prompt to a generative AI model and obtains an answer corresponding to the prompt from the generative AI model.

10. A method comprising: a receiving step of receiving target information regarding a target to be verbalized; and a prompt generating step of generating a prompt that instructs the generation of a sentence verbalizing the target to be verbalized based on the target information.

Images