Device and method

Abstract

The present invention provides a device and a method that can accurately provide an appropriate text to a user.　A device 100 comprises: an acquisition unit 101 that acquires a first text, user information including attribute information about an attribute of a user who may read the first text, and feature information indicating a feature of a text generated on the basis of the first text; a text generation unit 102 that generates a plurality of second texts on the basis of the first text and the feature information using a generative AI 300; and a selection unit 103 that selects, from the plurality of second texts, a second text to be provided to the user who may read the first text, on the basis of the attribute information.

Description

Device and Method 【0001】 The present invention relates to a device and a method. 【0002】 Patent Document 1 describes a device that provides minutes of a meeting. In this device, the content to be included in the minutes is determined for each attribute of the users who use the minutes. Thereby, the minutes showing the optimal content suitable for the user's position are provided to the user. 【0003】 Japanese Unexamined Patent Application Publication No. 2021-163214 【0004】 In the device as described above, in order to provide an appropriate text to a user who can read the text, the content of the text is corrected according to the attributes of the user. Here, it is conceivable to use a generation AI to provide an appropriate text to a user who can read the text. However, in this case, an appropriate text could not be accurately provided to the user. 【0005】 Therefore, an object of the present invention is to provide a device and a method capable of accurately providing an appropriate text to a user. 【0006】 The device of the present invention includes an acquisition unit that acquires a first text, user information including attribute information regarding the attributes of a user who can read the first text, and feature information indicating the features of the text generated based on the first text, a text generation unit that generates a plurality of second texts based on the first text and the feature information using a generation AI model, and a selection unit that selects, from the plurality of second texts, the second text to be provided to the user based on the attribute information. 【0007】 According to the present invention, an appropriate text can be accurately provided to a user who can read the text. 【0008】Figure 1 is a diagram showing a system configuration including the device of this disclosure. Figure 2 is a schematic diagram showing the prompt generation process of this disclosure. Figure 3 is a diagram showing the input screen of a user terminal and the response instruction prompt generated therefrom. Figure 4 is a diagram showing a specific example of a prompt for text generation. Figure 5 is a block diagram showing the functional configuration of the device of this disclosure. Figure 6 is a flowchart showing the operation of the device for causing the prompt generation AI and the generation AI to generate content. Figure 7 is a diagram showing the configuration of a user terminal on which the device or generation AI is located. Figure 8 is a diagram showing an example of the hardware configuration of the device according to one embodiment of this disclosure. 【0009】 Embodiments of the apparatus and method according to the present invention will be described in detail below with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant explanations are omitted. 【0010】 Figure 1 shows a system configuration including the apparatus 100 of this disclosure. As shown in the figure, this system includes the apparatus 100, a prompt generation AI 200, and a generation AI 300. The user terminal 400 is a terminal operated by the user. In this disclosure, the prompt generation AI 200 and the generation AI 300 for content generation are arranged separately, but they may be the same generation AI. 【0011】 Based on the information entered at the user terminal 400, the device 100 selects a prompt generation AI 200 and requests the prompt generation AI 200 to generate a prompt (response instruction prompt) for giving a response instruction to the generation AI 300. 【0012】 Device 100 obtains a response instruction prompt from the prompt generation AI 200. Device 100 sends the obtained response instruction prompt to the selected generation AI 300 and obtains the response result. Device 100 sends the response result to the user terminal 400. At the user terminal 400, the user confirms the response result and evaluates it. 【0013】With this system, the user can use prompts (response instruction prompts) appropriately generated in response to the information entered in the user terminal 400 to have the generating AI 300 generate a response result. 【0014】 Figure 2 is a schematic diagram illustrating the prompt generation process of this disclosure. As shown in the figure, input N1 is the following: "Manually created article (URL or article text): http: / / XXXX.YYY Characteristics of the newly created article: - Designed to be of interest to first-year employees... Customer attributes of the reader: - First to third-year employees..." Based on this input N1, etc., the prompt generation AI 200 generates a prompt. 【0015】 In Figure 2, the text-specific prompt generation AI 200a is selected, and the text-specific prompt generation AI 200a generates a text generation prompt P1 (corresponding to an answer instruction prompt) based on the generation instruction prompt generated based on the input N1. The text-specific generation AI 300a takes the text generation prompt P1 as input and generates the answer result K1. 【0016】 Figure 3 shows the input screen S1 of the user terminal 400 when input N1 is entered, and the response instruction prompt generated based on it. As shown in the figure, in the user terminal 400, the input screen S1 for input N1 accepts input of a manually created article (URL or article text), the characteristics of the new article to be created, and the customer attributes of the reader. 【0017】 The characteristics of manually created articles, newly created articles, and the customer attributes of the readers are all strings entered by the user. A "Start Generation" button is displayed on this input screen, and when the user selects (clicks, taps, etc.) this button, the user terminal 400 transmits this information to the device 100. 【0018】In addition, this input screen S1 also includes Back, Home, Search Past Cases, and Help buttons, and the user can execute the respective function by tapping each button. Back returns to the previous screen, Home returns to the home screen, Search Past Cases proceeds to the past cases search screen, and Help proceeds to the help screen. 【0019】 Figure 4 shows a specific example of a text generation prompt P1 (answer instruction prompt) generated based on input N1. As shown in the figure, the text generation prompt P1 includes a predefined phrase. This predefined phrase is: "You are a writer for a major web media company. Based on the following conditions and the customer's web browsing history, please create an article targeting users of ... based on "...". ###Conditions: ... ###Customer's web browsing history: ..." The predefined phrase may be stored in the prompt generation AI 200, or it may be specified as a predefined phrase in the generation instruction prompt. 【0020】 In the text generation prompt P1, section P11 is set to the "manually created article" entered on the input screen. Section P11 is the part that says "https: / / XXXX.YYY". In the text generation prompt P1, section P12 is set to the "reader's customer attributes" entered on the input screen. Section P12 is the part that says "first year working professional". 【0021】As a condition, part P13 of the text generation prompt P1 contains the following description: "Approximately 400 characters, polite style ("desu" and "masu"), line breaks every 2-3 lines, and the assumption that the reader has basic financial knowledge." This part P13 is text generated by the prompt generation AI 200 and is information generated according to information indicating the characteristics of the newly created article. In this disclosure, conditions regarding characters are generated. In addition, the prompt generation AI 200 generates conditions that the text should be approximately 400 characters, use polite style ("desu" and "masu"), have line breaks every 2-3 lines, and that the intended reader has basic financial knowledge. Furthermore, part P14 contains information indicating the customer's web page browsing history. This information indicates the date and time the customer viewed the web page, and the URL or content of the web page. This information is pre-stored by the device 100 and output from the device 100 to the prompt generation AI 200. 【0022】 The generated text generation prompt P1 (answer instruction prompt) is input to the generation AI 300, and the answer result is generated. Here, a new article based on a manually created article is generated by the generation AI 300 according to the specified conditions. 【0023】 In this disclosure, the device 100 generates prompts according to the prompt description method selected by the generation AI selection model. Figure 4 shows an example. Multiple prompt description methods are known, such as the Fukatsu method and the Junsuke method, depending on the purpose. Figure 4 shows a prompt generated using the Fukatsu method. 【0024】 Figure 5 is a block diagram showing the functional configuration of the apparatus 100 of this disclosure. As shown in the figure, the apparatus 100 is composed of an acquisition unit 101, a text generation unit 102, a selection unit 103, an output unit 104, an evaluation acquisition unit 105, and a history storage unit 106. The history storage unit 106 may be provided outside the apparatus 100. 【0025】The browsing history storage unit 500 is connected to the device 100 via the network NW shown in Figure 1. The browsing history storage unit 500 stores information indicating the browsing history of web pages transmitted from, for example, the user terminal 400. 【0026】 The acquisition unit 101 acquires the first text, feature information, and user information. The first text is a document intended to convey some content to the reader, for example, the manually created article mentioned above. The feature information is information that indicates the characteristics of the document generated based on the first text. For example, the feature information is information that indicates the characteristics of the newly created article mentioned above. The feature information is set by the user holding the user terminal 400. For example, the acquisition unit 101 acquires the first text and feature information input to the user terminal 400 from the user terminal 400. Note that the feature information may be generated by the generation AI 300 or the like based on the reader's customer attributes. 【0027】 User information is information about a user who can read the first document. User information includes attribute information about the attributes of the user who can read the first document (the reader described above), and history information showing the user's document browsing history. For example, the acquisition unit 101 acquires attribute information entered into the user terminal 400. The acquisition unit 101 acquires history information from the browsing history storage unit 500. Attribute information is, for example, information showing the customer attributes of the reader described above, and one example is demographic information. History information is, for example, information showing the browsing history of the reader described above, and one example is a log showing articles the user has viewed in the past. In this case, although the acquisition unit 101 acquired history information from the browsing history storage unit 500, it may also acquire history information entered into the user terminal 400 (for example, a CSV file). For example, the input screen S1 for input N1 shown in Figure 3 may accept input of information showing the reader's browsing history of web pages. 【0028】The text generation unit 102 generates multiple second sentences based on the first sentence and feature information using a generation AI model. Specifically, the text generation unit 102 generates multiple second sentences based on the first sentence, feature information, attribute information, and history information using a generation AI model. For example, the text generation unit 102 generates prompts for generating multiple second sentences using a prompt generation AI 200, and inputs the generated prompts to the generation AI 300 to obtain multiple second sentences. As an example, the text generation unit 102 executes a generation process to generate one second sentence using the method described below. 【0029】 The text generation unit 102 transmits the first text, feature information, attribute information, and history information to the prompt generation AI 200. The prompt generation AI 200 uses the first text, feature information, attribute information, and history information to generate a text generation prompt P1 shown in Figure 4 and transmits it to the text generation unit 102. The text generation unit 102 generates a second text by inputting the text generation prompt P1 to the generation AI 300. The second text is a modified version of the first text based on the feature information. 【0030】 For example, the prompt generation AI 200 generates the text generation prompt P1 by inputting information corresponding to the first sentence into part P11 of the text generation prompt P1, information corresponding to attribute information into part P12, information corresponding to feature information into part P13, and information corresponding to history information into part P14. The prompt generation AI 200 may also generate information on the user's proficiency in knowledge about the first sentence, the kanji characters the user can read, and the user's preferred article features based on the history information, and input information indicating the generated features into part P13. 【0031】 In this way, the text generation unit 102 generates one second text (the answer result K1 described above) by executing the generation process. The text generation unit 102 generates multiple second texts by executing the generation process described above multiple times. For example, the text generation unit 102 creates multiple patterns of articles from one article created manually. 【0032】The selection unit 103 selects a second sentence to provide to the user from a plurality of second sentences based on attribute information. Specifically, the selection unit 103 first inputs information and attribute information based on each of the plurality of second sentences into a learning model to generate relevance information that indicates the degree of relevance of each of the plurality of second sentences to a user who can read the first sentence. The relevance information is, for example, a score that indicates the degree of relevance of each of the plurality of second sentences to a user who can read the first sentence. 【0033】 For example, the selection unit 103 generates goodness-of-fit information by inputting information, attribute information, and history information based on each of the multiple second sentences into the learning model. The information based on each of the multiple second sentences is similarity information that shows the similarity between each of the multiple second sentences and the history information. The selection unit 103 calculates the dot product of multiple first vector information obtained by vectorizing each of the multiple second sentences and second vector information obtained by vectorizing the sentences included in the history information. The selection unit 103 uses the calculated dot product as similarity information. Note that the generation of similarity information may be achieved by methods other than those described above, and may be achieved by various known methods. 【0034】 The selection unit 103 pre-constructs a learning model used to generate goodness-of-fit information. Specifically, the selection unit 103 constructs a learning model by machine learning using training data that takes information based on a predetermined article, as well as attribute information and history information about the user, as input, and outputs information indicating whether or not the user has read the predetermined article. The information indicating whether or not the user has read the predetermined article is, for example, information indicating either label "1" indicating that the user has read the predetermined article, or label "0" indicating that the user has not read the predetermined article. In this case, the score indicated by the goodness-of-fit information output from the learning model is a numerical value between 0.0 and 1.0. 【0035】 Next, the selection unit 103 selects the second sentence that is most suitable for users who can read the first sentence, based on the suitability information. Specifically, the selection unit 103 selects the second sentence with the highest suitability. 【0036】The output unit 104 outputs the second sentence selected by the selection unit 103 to the user terminal 400. The user terminal 400 presents the second sentence to the user by displaying it on its own display. In this way, the user can read a second sentence that is suitable for them. 【0037】 The output unit 104 sends the second text along with an evaluation request for the second text to the user terminal 400. This evaluation request is screen information that allows the user to rate the text using the number of star marks. 【0038】 The evaluation acquisition unit 105 acquires the user's evaluation result for the second text transmitted to the user terminal 400. The user evaluates the second text displayed on the user terminal 400 by inputting a numerical value (for example, specifying the number of stars or clicking the star mark displayed on the screen of the user terminal 400). The evaluation acquisition unit 105 acquires that numerical value (number of stars) as the evaluation result. The evaluation acquisition unit 105 stores the acquired evaluation result together with the second text in the history storage unit 106. 【0039】 The history storage unit 106 stores the second sentence selected by the selection unit 103 of the device 100, and the evaluation result acquired by the evaluation acquisition unit 105. This history storage unit 106 does not need to be included in the device 100, and may be an external device. The history storage unit 106 stores the second sentence and the evaluation result in association. 【0040】 Next, the operation of the apparatus 100 according to this embodiment will be explained using the flowchart in Figure 6. Figure 6 is a flowchart showing the operation of the apparatus 100 for causing the prompt generation AI 200 and the generation AI 300 to perform content generation. First, the acquisition unit 101 acquires the first sentence, user information, and feature information (S01). 【0041】 Next, the text generation unit 102 generates a prompt (text generation prompt P1) for generating multiple second sentences using the prompt generation AI 200 (S02). The text generation unit 102 inputs the text generation prompt P1 to the generation AI 300 to generate multiple second sentences (S03). 【0042】 Subsequently, the selection unit 103 calculates the degree of suitability for the user for each of the plurality of second sentences (S04). The selection unit 103 selects the second sentence with the highest degree of suitability (S05). The output unit 104 outputs the second sentence selected by the selection unit 103 to the user terminal 400, and the user terminal 400 presents the output second sentence to the user (S06). The evaluation acquisition unit 105 acquires the evaluation result and stores the acquired evaluation result together with the second sentence in the history storage unit 106 (S07). 【0043】 Subsequently, the operation and effect of the apparatus 100 and the method according to the present embodiment will be described. In the apparatus 100 and the method of the present embodiment, the sentence generation unit 102 generates a plurality of second sentences based on the first sentence and the feature information using the generation AI 300. Then, the selection unit 103 selects, from the plurality of second sentences, the second sentence to be provided to the user who can read the first sentence based on the attribute information. Thereby, an appropriate second sentence can be selected according to the user's attribute and presented to the user. As a result, for example, compared with the case of generating a second sentence for each user, an appropriate sentence can be provided to the user with high accuracy. 【0044】 Further, in the present disclosure, the sentence generation unit 102 generates a plurality of second sentences based on the attribute information using the generation AI 300. Thereby, a plurality of second sentences corresponding to the user's attribute can be generated. As a result, a more appropriate second sentence can be presented to the user. In addition, compared with the case of generating and presenting one second sentence according to the user's attribute, the number of trials of the second sentence generation process by the generation AI 300 is large, so the possibility that an appropriate second sentence for the user is included in the plurality of second sentences can be increased. 【0045】Furthermore, in this disclosure, user information includes history information indicating the user's browsing history of the first text, and the text generation unit 102 generates multiple second texts based on the history information using the generation AI 300. This makes it possible to generate multiple second texts according to the user's browsing history. For example, multiple second texts can be generated considering the user's level of knowledge regarding the first text, the kanji characters the user can read, and the characteristics of articles the user prefers. This further increases the likelihood that a second text appropriate for the user will be included among the multiple second texts. 【0046】 For example, when a human modifies the first text to provide an appropriate text to a user who can read the first text, it takes time for the human to consider how to convey the content of the first text to that user, and then the effort to perform the work based on the result of that consideration. However, with the device 100 of this disclosure, it is possible to provide an appropriate text to a user who can read the first text while eliminating such time and effort. This makes it possible to change the way the content of the first text is conveyed for each user. 【0047】As an example, since the appropriate words (language) for each user are different and the upper limit of the number of characters in one article is determined in advance, the effort required for a person creating an article has been increasing. Specifically, when comparing an article for adults with an article for children, the words used in each article are different. In addition, in an article for children, the words to be used are selected in consideration of the fact that there are Chinese characters that the user cannot read depending on the user's age. Furthermore, when comparing an article for experts with an article for beginners, the amount of prerequisite knowledge required to read each article is different. And the words used also differ depending on the style of the article (a polite style or a frank (light) style). Performing such selection or use of appropriate words for each user for each user is difficult from the perspective of manual labor and cost. Also, it has been difficult for a person to determine which article is suitable for each user. On the other hand, in the device 100 of the present disclosure, for each user, while considering the words and language suitable for the user, the atmosphere of the user, and the prerequisite knowledge (readable Chinese characters or specialized knowledge, etc.) that the user has, a plurality of patterns of the second article (article) can be automatically generated, and it is possible to select the second article suitable for each user. As a result, it is possible to reduce the manual labor for creating and selecting the second article suitable for each user, and it is possible to improve the degree of understanding when the user reads the second article. 【0048】 Also, in the present disclosure, the selection unit 103 inputs information and attribute information based on each of the plurality of second articles into the learning model, thereby generating fitness information indicating the fitness of each of the plurality of second articles for a user who can read the first article, and selects the second article that most suits the user who can read the first article based on the fitness information. Thereby, it is possible to accurately present an appropriate second article to the user. 【0049】Furthermore, in this disclosure, user information includes history information indicating the user's browsing history of the first text. The selection unit 103 generates relevance information by further inputting the history information into the learning model. This makes it possible to more reliably present the user with an appropriate second text. For example, based on the trends of articles the user has previously viewed, it is possible to select which of several article patterns is most suitable. 【0050】 Furthermore, in this disclosure, the information based on each of the multiple second sentences is similarity information indicating the similarity between each of the multiple second sentences and the historical information. This makes it possible to present the user with an even greater degree of accuracy in finding the appropriate second sentence. 【0051】 Furthermore, in this disclosure, the text generation unit 102 generates a text generation prompt P1 for generating multiple second sentences using the prompt generation AI 200, and inputs the generated text generation prompt P1 to the generation AI 300 to obtain multiple second sentences. This makes it possible to easily generate a suitable text generation prompt P1 by having the generation AI 300 generate multiple second sentences. 【0052】 In the above embodiment, the feature information may also be information indicating the characteristics of a text directed to multiple virtual users having different attributes, and the text generation unit 102 may generate multiple second texts directed to multiple virtual users. In this case, multiple second texts suitable for each of the multiple virtual users will be generated. This further increases the possibility that a second text appropriate for the user will be included among the multiple second texts. 【0053】 Furthermore, in the above embodiment, the text generation unit 102 generated a plurality of second texts based on the first text, feature information, attribute information, and history information using the generation AI 300. However, it is sufficient if the plurality of second texts are generated based on at least the first text and feature information. For example, the text generation unit 102 may generate a plurality of second texts based on the first text, feature information, and attribute information using the generation AI 300. 【0054】Furthermore, in the above embodiment, the selection unit 103 selected and presented a second sentence to one user, but it may also select a second sentence for each of multiple users. In this case, the selection unit 103 may acquire information indicating the combination of each second sentence and the group of users for which each second sentence was selected, and output the acquired information to the history storage unit 106. 【0055】 Furthermore, although the second text was evaluated by the user in the above embodiment, the embodiment is not limited to this. For example, the evaluation acquisition unit 105 may acquire browsing information and the second text, and perform an evaluation of the second text based on the browsing information and the second text. 【0056】 [About this disclosure] The apparatus 100 and method of this disclosure have the following configuration. 【0057】 [1] An apparatus comprising: an acquisition unit that acquires a first sentence, user information including attribute information relating to the attributes of a user who can read the first sentence, and feature information indicating the characteristics of a sentence generated based on the first sentence; a sentence generation unit that generates a plurality of second sentences based on the first sentence and the feature information using a generation AI model; and a selection unit that selects a second sentence to be provided to a user who can read the first sentence from the plurality of second sentences based on the attribute information. 【0058】 [2] The apparatus according to [1], wherein the text generation unit generates a plurality of second texts based on the attribute information using the generation AI model. 【0059】 [3] The apparatus according to [2], wherein the user information includes history information indicating the browsing history of the user who can read the first text, and the text generation unit generates a plurality of second texts based on the history information using the generation AI model. 【0060】[4] The apparatus according to any one of [1] to [3], wherein the selection unit inputs information based on each of the plurality of second sentences and attribute information into a learning model to generate relevance information indicating the degree of relevance of each of the plurality of second sentences to a user who can read the first sentence, and selects the second sentence that is most suitable for a user who can read the first sentence based on the relevance information. 【0061】 [5] The apparatus according to [4], wherein the user information includes history information indicating the browsing history of the first text of a user who can read the text, and the selection unit generates the fitness information by further inputting the history information into the learning model. 【0062】 [6] The apparatus according to [5], wherein the information based on each of the plurality of second sentences is similarity information indicating the similarity between each of the plurality of second sentences and the history information. 【0063】 [7] The apparatus according to any one of [1] to [6], wherein the text generation unit generates prompts for generating the plurality of second sentences using the generation AI model, and inputs the generated prompts to the generation AI model to obtain the plurality of second sentences. 【0064】 [8] The apparatus according to any one of [1] to [7], wherein the characteristic information is information indicating the characteristics of a document addressed to a plurality of virtual users having different attributes from each other, and the document generation unit generates the plurality of second documents addressed to the plurality of virtual users. 【0065】 [9] A method for selecting text in a device, comprising: an acquisition step of acquiring a first text, user information including attribute information relating to the attributes of a user who can read the first text, and feature information indicating the characteristics of a text generated based on the first text; a text generation step of generating a plurality of second texts based on the first text and the feature information using a generation AI model; and a selection step of selecting a second text to be provided to a user who can read the first text from the plurality of second texts based on the attribute information. 【0066】Furthermore, all or some of the prompt generation AI 200, generation AI 300, and browsing history storage unit 500 may be located in the device 100 or the user terminal 400. The user terminal 400 may also have the functions of the device 100 and function as the device 100. Some generation AI models, like Tsuzumi, have the generation AI model located within the user terminal 400. In this type, the RAG application is also provided on the user terminal 400. However, the information (knowledge database) accessed by the RAG may be located within the user terminal 400 or on the network. There are also types, like ChatGPT, where the generation AI model is located on the network. In this type, the RAG application is provided on the user terminal 400. However, the information (knowledge database) accessed by the RAG is on the network. 【0067】 The specific configuration will now be explained. Figure 7(a) shows an example configuration when the user terminal 400 has the functions of the device 100. In this case, the user terminal 400 generates a prompt, sends it to the prompt generation AI 200 or generation AI 300, and obtains the result. Figure 7(b) shows an example configuration when the user terminal 400 has the device 100 and the prompt generation AI 200 or generation AI 300. As shown in the figure, the user terminal 400 generates a prompt, outputs it to the built-in prompt generation AI 200 or generation AI 300, and obtains the result. 【0068】 [Definitions of Terms, etc.] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired, wireless, etc.). A functional block may be realized by combining the above one device or the above multiple devices with software. 【0069】Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited. 【0070】 For example, the apparatus 100 in one embodiment of the present disclosure may function as a computer that processes the method of the present disclosure. Figure 8 shows an example of the hardware configuration of the apparatus 100 of the present disclosure. The apparatus 100 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc. 【0071】 In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of device 100 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices. 【0072】 Each function in the device 100 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003. 【0073】The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the document generation unit 102 described above may be implemented by the processor 1001. 【0074】 Furthermore, the processor 1001 reads 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 accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the text generation unit 102 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line. 【0075】 The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out the methods of this disclosure. 【0076】The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003. 【0077】 The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the acquisition unit 101 described above may be implemented by the communication device 1004. The communication device 1004 may be implemented with physically or logically separated transmitting and receiving units. 【0078】 The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel). 【0079】Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device. 【0080】 Furthermore, the device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components. 【0081】 Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc. 【0082】The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented. 【0083】 Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices. 【0084】 The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value). 【0085】 Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification). 【0086】 Although the present disclosure has been described in detail above, it will be 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 intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way. 【0087】Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. 【0088】 Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium. 【0089】 The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. 【0090】 In addition, terms used 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 the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc. 【0091】Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index. 【0092】 The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way. 【0093】 In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably. 【0094】 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 appropriate term. 【0095】As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering." 【0096】The terms “connected,” “coupled,” or any variation thereof, mean 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” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain. 【0097】 In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on." 【0098】 Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way. 【0099】 Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR. 【0100】In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural. 【0101】 In this 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 "combine" may be interpreted similarly to "different." 【0102】 100...Device, 101...Acquisition unit, 102...Text generation unit, 103...Selection unit, 200...Prompt generation AI, 300...Generation AI, 1001...Processor, 1002...Memory, 1003...Storage, 1004...Communication device, 1005...Input device, 1006...Output device.

Claims

1. An apparatus comprising: an acquisition unit that acquires a first sentence, user information including attribute information relating to the attributes of a user who can read the first sentence, and feature information indicating the characteristics of a sentence generated based on the first sentence; a sentence generation unit that generates a plurality of second sentences based on the first sentence and the feature information using a generation AI model; and a selection unit that selects a second sentence to be provided to a user who can read the first sentence from the plurality of second sentences based on the attribute information.

2. The apparatus according to claim 1, wherein the text generation unit generates a plurality of second texts based on the attribute information using the generation AI model.

3. The apparatus according to claim 2, wherein the user information includes history information indicating the browsing history of the user who can read the first text, and the text generation unit generates a plurality of second texts based on the history information using the generation AI model.

4. The apparatus according to claim 1, wherein the selection unit inputs information based on each of the plurality of second sentences and attribute information into a learning model to generate relevance information indicating the degree of relevance of each of the plurality of second sentences to a user who can read the first sentence, and selects the second sentence that is most suitable for a user who can read the first sentence based on the relevance information.

5. The apparatus according to claim 4, wherein the user information includes history information indicating the browsing history of the first text of a user who is able to read the text, and the selection unit generates the fitness information by further inputting the history information into a learning model.

6. The apparatus according to claim 5, wherein the information based on each of the plurality of second sentences is similarity information indicating the similarity between each of the plurality of second sentences and the history information.

7. The apparatus according to claim 1, wherein the text generation unit generates prompts for generating the plurality of second sentences using the generation AI model, and inputs the generated prompts to the generation AI model to obtain the plurality of second sentences.

8. The apparatus according to claim 1, wherein the feature information is information indicating the characteristics of a document addressed to a plurality of virtual users having different attributes from each other, and the document generation unit generates the plurality of second documents addressed to the plurality of virtual users.

9. A method for selecting text in a device, comprising: an acquisition step of acquiring a first text, user information including attribute information relating to the attributes of a user who can read the first text, and feature information indicating the characteristics of a text generated based on the first text; a text generation step of generating a plurality of second texts based on the first text and the feature information using a generation AI model; and a selection step of selecting a second text to be provided to a user who can read the first text from the plurality of second texts based on the attribute information.

Images