Sentence creating system using confidentiality protection prompt

Abstract

To provide a sentence creation system using confidentiality protection prompt for preventing leakage of confidentiality.SOLUTION: In the system according to the present invention, a sentence generation support apparatus connected through a communication network to a user terminal and a generative AI server has an input screen generating unit for generating an input screen to send it to the terminal, a screen input reception unit for receiving text data of an instruction sentence input on the input screen, a confidential information conversion unit for converting the text data of words input from the terminal and designated as confidential information into data subjected to hashing, a prompt generating unit for generating a prompt for input of large scale language model in which the designated words were replaced with hashed character strings, a sentence generation instruction unit for instructing generation of a sentence by transmitting the generated prompt to the server, a confidential information restoring unit for receiving the sentence generated from the server and restoring the hashed character strings to the words before hashing, a generated document output unit for transmitting the an output screen on which the restored sentence is displayed to the terminal, and a control unit for controlling the sentence generating apparatus generally.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a sentence generation system using secure prompts, and more particularly to a sentence generation system using secure prompts that prevents security leaks from prompts input to a large language model. [Background technology]

[0002] In recent years, the use of generative artificial intelligence (AI) that uses large-scale language models (LLM) to respond to user questions and inquiries has been rapidly spreading. A large-scale language model is a natural language processing model trained using large amounts of text data, and when a question or instruction is input into a generative AI equipped with a large-scale language model, an answer is output from the large-scale language model. The text input into a large-scale language model is called a "prompt."

[0003] When using a generative AI that supports text processing, a user sends question text data to a server computer that constitutes a text generation system consisting of a trained large-scale language model provided by the company that operates the generative AI, via the Internet or a mobile communication network, etc., and receives answer text data generated by the server via the Internet or a mobile communication network, etc. The sending and receiving of text data is performed using an API (Application Programming Interface) provided by the company that operates the generative AI, or can also be performed using general communication protocols such as HTTP and HTTPS, and can also be performed via a web browser.

[0004] However, when sending text containing confidential information (for example, personal information including names and addresses, or confidential corporate information) to a server computer of a text generation system outside of one's control, the leakage of confidential information becomes an issue.

[0005] In generative AI released to the public as described above, there is a risk that input information will be used as training data. To avoid this, some businesses allow users to select a setting that prevents input text data from being used in training, but the input text data itself is stored on the server computer that provides the generative AI, and confidentiality cannot be guaranteed.

[0006] In addition, when sending and receiving text containing confidential information to and from a server computer that provides the generation AI, there is a risk that the confidential information in the text may be leaked or stolen on the communication path. As a method for safely processing such text containing confidential information using external computer resources, Patent Document 1 discloses a method of encrypting the text by replacing part of the highly confidential text with a character string that is difficult to decipher.

[0007] However, the method of Patent Document 1 requires the user to select the term to be encrypted in advance, associate this term with a specific code (character string), and register it in a database, forcing the user to incur the effort and expense of registering and confirming the word. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] JP 2020-77134 A Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention has been made in consideration of the above-mentioned problems in the conventional technology, and an object of the present invention is to provide a sentence generation system that uses security prompts to prevent the leakage of confidential information from prompts input to an external computer equipped with a large-scale language model. [Means for solving the problem]

[0010] In order to achieve the above object, one aspect of the present invention provides a text generation system using a confidentiality prompt, which generates a prompt for inputting a large-scale language model in which confidential information contained in an input instruction is concealed, the text generation system comprising a text generation support device connected to a user terminal and a generative artificial intelligence (AI) server via a communication network, the text generation support device including an input screen generation unit that generates an input screen on which a template form for inputting the instruction is displayed and transmits the generated input screen to the user terminal, a screen input acceptance unit that receives character data of the instruction input from the user terminal into the template form on the input screen, a confidential information conversion unit that converts character data of a wording designated as confidential information input from the user terminal via the screen input acceptance unit into a hashed string, and a confidential information conversion unit that converts character data of the instruction input into the template form that corresponds to the wording designated as confidential information into a hashed string. The device is characterized by including a prompt generation unit that generates a prompt for inputting a large-scale language model replaced with a hashed character string, a sentence generation instruction unit that sends the generated prompt for inputting the large-scale language model to the generation AI server to instruct sentence generation, a confidential information restoration unit that receives the generated sentence from the generation AI server, detects the hashed character string contained in the received sentence, and restores the detected hashed character string to character data before hashing, a generated document output unit that sends an output screen to the user terminal displaying the generated sentence with the hashed character string restored, and a control unit that controls the sentence generation device in general.

[0011] The confidential information conversion unit stores the hashed character string in a memory unit in association with character data of the wording specified in the confidential information before hashing, and the confidential information restoration unit can obtain from the memory unit and restore the character data of the wording specified in the confidential information before hashing that corresponds to the detected hashed character string. The wording designated as confidential information can be inputted in a confidential information designation field displayed on the input screen transmitted to the user terminal. The standard form displayed on the input screen includes a plurality of input fields with different items, and the prompt generation unit combines character data entered into each of the plurality of input fields of the standard form to dynamically generate a prompt for inputting a large-scale language model, generates the input screen on which the generated prompt for inputting a large-scale language model is displayed, and transmits the input screen to the user terminal. The standard form includes an input field for specifying the genre of the text to be generated, and the input screen generation unit can generate a prompt confirmation screen including a prompt template associated with the genre name entered into the input field for specifying the genre, and send it to the user terminal. The control unit can generate a usage history for each user, the usage history including a prompt for inputting the generated large-scale language model and character data corresponding to the wording specified as the confidential information, and store the usage history in a memory unit. Effect of the Invention

[0012] According to the present invention, it is possible to easily generate prompts for inputting a large-scale language model in which confidential information is concealed, thereby preventing the leakage of confidential information that may occur when using a generation AI. Furthermore, since prompts for inputting a large-scale language model can be dynamically generated using templated input forms, users can easily obtain highly accurate sentence generation results. [Brief description of the drawings]

[0013] [Figure 1] 1 is a diagram for explaining the overall configuration of a sentence generation system using security prompts according to an embodiment of the present invention; [Diagram 2] 1 is a block diagram showing an example of the hardware configuration of a writing generation assistance device and a generation AI server according to the present embodiment. FIG. [Diagram 3] 1 is a block diagram showing an example of a functional configuration of a writing production assistance device according to an embodiment of the present invention; [Figure 4] A block diagram showing an example of the functional configuration of a generation AI server according to this embodiment. [Diagram 5] FIG. 2 is a diagram showing a document generation process procedure of the writing generation system according to the embodiment of the present invention. [Figure 6] FIG. 2 is a diagram showing an example of an input screen on which a template form for creating a prompt generated by the writing assistance device according to the present embodiment is displayed. [Figure 7] FIG. 11 is a diagram showing an example of a prompt confirmation screen generated by the writing assistance device according to the present embodiment. [Figure 8] 1 is a diagram showing an example of an original prompt generated by the writing support device according to the present embodiment; [Figure 9] FIG. 2 is a diagram showing an example of a generated result (answer sentence) generated by the writing support device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, specific examples of the embodiments of the present invention will be described in detail with reference to the drawings.

[0015] 1 is a diagram for explaining the overall configuration of a text generation system using confidentiality prompts according to one embodiment of the present invention. The text generation system 1 using confidentiality prompts according to this embodiment is configured to include a user terminal 10, a text generation support device 20, and a generation AI server 30. The text generation support device 20 is communicatively connected to the user terminal 10 and the generation AI server 30 via a communication network. The communication network is, for example, the Internet, and is constructed by a public telephone line network, a mobile communication network, a wireless communication path, Ethernet (registered trademark), etc.

[0016] The user terminal 10 is a computer terminal operated by a user who wishes to create a sentence using a generation AI (sentence generation AI) equipped with a large-scale language model, and includes, for example, a smartphone, a tablet computer, a personal computer, etc.

[0017] A Web browser runs on the user terminal 10, allowing access to the writing assistance device 20. A user who uses the writing generation system 1 using the confidentiality prompt according to the present invention registers in advance and obtains a user account, a user ID (identification number), and the like. A method for user registration can be a common method for using Web services, and a detailed description thereof will be omitted. Users can be registered not only as individuals, but also as a company, and the members of the company can use the system as a group. In the case of group use, a user ID is assigned to each member of the company, and the system can also be configured to manage the usage status of the group.

[0018] The writing generation support device 20 is a computer that exchanges data with the user terminal 10. The writing generation support device 20 and the generation AI server 30 may be configured to be regarded as one virtual computer when viewed from the user terminal 10. The writing generation support device 20 functions as a Web server, and provides the user terminal 10 with a screen (Web page) written in HTML, and can input and output text related to the writing generation procedure. However, the method of cooperation between the writing generation support device 20 and the user terminal 10 is not limited to this, and processing may be executed via a pre-implemented application.

[0019] The generation AI server 30 is a computer that has a large-scale language model, receives a prompt that is an input sentence to the large-scale language model, and generates a new sentence in response to the received prompt. As an API server, the generation AI server 30 receives a prompt specified by the user via the sentence generation support device 20, and generates a new sentence (answer sentence) in response to the prompt.

[0020] The writing assistance device 20 and the generation AI server 30 may be configured as a general-purpose computer such as a workstation or a personal computer. However, they are not limited to this and may be realized by cloud computing.

[0021] 2 is a block diagram showing an example of the hardware configuration of the writing assistance device and the generation AI server according to the present embodiment. However, the illustrated configuration is only an example and is not limiting. The user terminal 10 may also have a hardware configuration similar to that shown in FIG.

[0022] As shown in FIG. 2, the writing support device 20 according to the present embodiment is configured by a general-purpose computer, and includes a CPU (Central Processing Unit) 101, a memory 102, a storage device 103, a communication interface 104, an input device 105, and an output device 106. The storage device 103 stores various data and programs, and is, for example, a hard disk drive, a solid state drive, or a flash memory. The communication interface 104 is an interface for connecting to a communication network, and is, for example, an adapter for Ethernet (registered trademark) connection, a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector for serial communication. The input device 105 is a device for inputting data, and is, for example, a keyboard, a mouse, a touch panel, a button, or a microphone. The output device 106 is a device for outputting data, and is, for example, a display, a printer, or a speaker.

[0023] The generation AI server 30 may also have the hardware configuration shown in FIG. 2, but in order to realize higher data processing capabilities, it may be configured as a dedicated computer equipped with multiple GPUs (Graphics Processing Units) in addition to or instead of a CPU.

[0024] The functional configuration of the writing generation support device 20 and the generation AI server 30 according to this embodiment will be described below.

[0025] FIG. 3 is a block diagram showing an example of a functional configuration of the writing assistance device according to the present embodiment.

[0026] The writing assistance device 20 according to this embodiment has the hardware configuration shown in FIG. 3, writing generation assistance device 20 according to this embodiment includes control unit 200 including CPU 101 and memory 102, storage unit 280 including storage device 103, and communication unit 290 including communication interface 104. Furthermore, as functional units realized by control unit 200 executing a predetermined program, there are provided input screen generation unit 210, screen input acceptance unit 220, confidential information conversion unit 230, prompt generation unit 240, writing generation instruction unit 250, confidential information restoration unit 260, and generated document output unit 270.

[0027] In response to an access request from the user terminal 10, the input screen generation unit 210 generates an input screen displaying a standard form into which an instruction sentence for creating an input sentence (prompt) to the generation AI is input, and transmits the generated input screen to the user terminal 10. The standard form can include input fields for multiple items.

[0028] The screen input receiving unit 220 receives instructions entered into a standard form on the input screen displayed on the user terminal 10, i.e., character data (text data) for creating a prompt, and transmits the received character data (instructions) for creating a prompt to the prompt generating unit 240 for each input field of the standard form.

[0029] The confidential information conversion unit 230 hashes the character data of the wording designated as confidential information, which is input for each item (field) designated as confidential information from the input screen displayed on the user terminal 10. The hashing can be performed using a general hash function. The hashed character string is associated with the original character data before hashing and stored in the storage unit 280, for example, in the form of a correspondence table. The wording designated as confidential information is input from a predetermined confidential information designation field (details will be described later) displayed on the input screen transmitted to the user terminal 10.

[0030] The prompt generation unit 240 combines (integrates) the character data for creating prompts for each input field of the received standard form to create the original text of the prompt, and replaces character data that corresponds to wording designated as confidential information (proper nouns, addresses, wording that constitutes confidential matters, etc.) contained in the original text of the created prompt with a hashed string to generate a prompt for inputting into a large-scale language model.

[0031] The sentence generation instruction unit 250 transmits a prompt for inputting the generated large-scale language model to the generation AI server 30 to instruct sentence generation.

[0032] The confidential information restoration unit 260 detects hashed character strings contained in the sentence (answer sentence) generated by the generation AI server 30, and restores the detected hashed character string to character data corresponding to the wording before hashing, based on a correspondence table stored in the memory unit 280.

[0033] The generated document output unit 270 generates an output screen on which the generated text (answer text) is displayed, in which the hashed character string is restored, and transmits the output screen to the user terminal 10.

[0034] The storage unit 280 stores data and programs for image display and input / output control, including standard forms to be displayed on the input screen, and items to specify confidential information, etc. Also, character data of instruction statements input by users, and a correspondence table between character data of phrases specified as confidential information and character strings obtained by hashing the character data are stored for each user (for example, in association with a user account or a user ID).

[0035] The communication unit 290 controls communication with the user terminal 10 and the generation AI server 30.

[0036] FIG. 4 is a block diagram showing an example of the functional configuration of the generation AI server according to this embodiment.

[0037] The generation AI server 30 according to this embodiment is an API server computer equipped with a trained large-scale language model provided by a business operator that operates the generation AI, and has the hardware configuration shown in Fig. 2. It is desirable that the generation AI server 30 has enhanced functions and performance compatible with the large-scale language model.

[0038] As shown in FIG. 4, the generation AI server 30 according to this embodiment includes a control unit 300 including a CPU (GPU) 101 and a memory 102, a model storage unit 340 including a storage device 103, and a data communication unit 350 including a communication interface 104. In addition, as functional units realized by executing a predetermined program in the control unit 300, a generation request receiving unit 310, a sentence generation unit 320, and a generation result output unit 330 are provided. For example, ChatGPT-3.5 or ChatGPT-4 provided by OpenAI OPCO, LLC in the United States, or Bard provided by Google LLC in the United States can be used as a large-scale language model used for sentence generation, and the generation AI server 30 according to this embodiment can also use API servers provided by these companies.

[0039] The generation request receiving unit 310 receives an API usage request for the large-scale language model. In this embodiment, the API usage from the writing support device 20 is performed by sending a prompt for inputting the large-scale language model, and the prompt for inputting the large-scale language model sent from the writing instruction unit 250 of the writing support device 20 is received by the generation request receiving unit 310.

[0040] The sentence generation unit 320 is provided with a predetermined large-scale language model, and generates a response sentence to the sentence included in the prompt by providing the large-scale language model with a prompt for inputting the large-scale language model received by the generation request receiving unit 310.

[0041] The generation result output unit 330 outputs (transmits) the sentence (answer sentence) generated by the sentence generation unit 320 to the request source (transmission source) of the writing generation assistance device 20.

[0042] The model storage unit 340 stores large-scale language models, parameters, and the like.

[0043] The data communication unit 350 controls communication with the writing assistance device 20 .

[0044] Next, the operation of the sentence generation system using secure prompts according to one embodiment of the present invention will be described.

[0045] 5 is a diagram showing a document generation process procedure of the writing system according to an embodiment of the present invention. Hereinafter, the procedure in which the user terminal 10, the writing support device 20, and the generation AI server 30 work together will be described with reference to FIG.

[0046] When the user terminal 10 transmits an access request to the writing generation support device 20 (step S100), the control unit 200 of the writing generation support device 20 authenticates the user terminal 10. If the authentication based on the user ID or the like is successful, the control unit 200 causes the input screen generating unit 210 to generate an input screen (see FIG. 6) on which a template form for creating an input sentence (prompt) to the generation AI is displayed, and transmits display data of the generated input screen to the user terminal 10 (step S200). When the input screen is displayed on the user terminal 10 that has received the display data (step S110), the user inputs the genre and confidential information items of the prompt to be created on the displayed input screen (step S120).

[0047] Fig. 6 is a diagram showing an example of an input screen on which a template form for creating a prompt generated by the writing support device according to this embodiment is displayed. An input screen 400 shown in Fig. 6 displays a template form having a title input field 410 for specifying the genre of the prompt to be created, a confidential information item selection field 420, and an additional information specification field 430.

[0048] In the title input field 410, the genre of the prompt to be created may be input as free text, or preset genres may be pulled down and selected from. In the confidential information item selection field 420, a list box in which preset target items are written as field names may be placed so that the user can select from the list box. In the additional information specification field 430, a sentence or phrase describing information to further supplement the instructions for creating the prompt may be input as text.

[0049] On the input screen 400, after completing input into each field 410, 420, 430, when the “Execute” button 440 is pressed, prompt creation data consisting of the genre name, confidential information item, and additional information entered respectively into the title input field 410, confidential information item selection field 420, and additional information specification field 430 from the user terminal 10 is sent to the writing generation support device 20.

[0050] The screen input receiving unit 220 of the writing support device 20 transmits the prompt creation data received from the user terminal 10 to the input screen generating unit 210, and the input screen generating unit 210 reads out a prompt template (hereinafter simply referred to as a template sentence) associated with the genre based on the genre name specified in the prompt creation data from the storage unit 280, generates a prompt confirmation screen (see FIG. 7) including the read template sentence, and transmits it to the user terminal 10 (step S220). The template sentence is a fixed phrase configured as an instruction sentence including standard contents used in each genre, and is stored in the storage unit 280 in advance. Specifiable genres include specifications, inquiries, replies to inquiries, translations, minutes, requests, summaries, notices regarding employment and sales, and the like. The template sentences include template sentences of common general specifications and template sentences dedicated to users (including corporate users) themselves, and the right to use the template sentences dedicated to users can be set only for the users (including group use by corporate users) who created them.

[0051] 7 is a diagram showing an example of a prompt confirmation screen generated by the writing support device according to this embodiment. The prompt confirmation screen 500 includes a title field 510 showing the name of the selected genre, an original text confirmation field 520 showing a template text corresponding to the selected genre, an additional information confirmation field 530 showing an additional text to be combined with the template text, and a confidential information specification field 540 for specifying the actual wording of the selected confidential information item.

[0052] The original text confirmation field 520 and the additional information confirmation field 530 are provided with a function that enables text correction such as modification, addition, and deletion of the displayed template sentence, and the changes made (input) by the user to these fields are sequentially transmitted to the screen input receiving unit 220 of the writing production assistance device 20, and the prompt generating unit 240 dynamically (for each change input) reflects the changes received by the screen input receiving unit 220 in the template sentence currently being confirmed, creates or updates the original text of the prompt, and redisplays it on the user terminal 10 via the input screen generating unit 210. The prompt generating unit 240 may temporarily store the original text of the created prompt in the storage unit 280.

[0053] The additional information confirmation field 530 displays the context of the additional information corresponding to the information item input in the additional information specification field 430 of the input screen 400 of FIG. 6. The context includes role settings, conditions, prior information, and knowledge. The confidential information specification field 540 displays input fields 541 and 542 for each field of the target item specified in the confidential information item selection field 420 of the input screen 400 of FIG. 6, and the user may be able to input specific confidential information (for example, a proper noun of an individual or company, corporate internal information related to research and development or new business, personal information, etc.) in text form in each input field. The context of the additional information may be stored in the storage unit 280 in advance in association with a keyword used to specify the information item.

[0054] After the specific confidential information wording is entered as text in the confidential information designation field 540, when the "Update" button 550 is pressed on the prompt confirmation screen 500, the confidential information wording (character data) entered in the confidential information designation field 540 is sent to the prompt generation unit 240 via the screen input acceptance unit 220 of the text generation support device 20, and the prompt generation unit 240 operates the confidential information conversion unit 230 to hash the character data corresponding to the wording designated as the confidential information, and associates the hashed character string (hash value) with the original character data (wording) before hashing, and stores the hashed character string (hash value) in the memory unit 280 for each user.

[0055] Furthermore, the prompt generating unit 240 detects a word specified as confidential information included in the original text of the prompt, and performs a process of replacing the word corresponding to the detected confidential information with a hashed character string. After that, the input screen generating unit 210 generates an input screen (described later) on which the original text of the prompt after the replacement process is displayed, transmits the screen to the user terminal 10, and causes the user terminal 10 to redisplay the screen (step S230). The prompt generating unit 240 also updates the original text of the prompt temporarily stored in the storage unit 280 to the original text of the prompt after the replacement process.

[0056] Fig. 8 is a diagram showing an example of an original text of a prompt generated by the writing support device according to this embodiment, where (a) of Fig. 8 shows an example of the original text of the prompt before confidential information is hashed (prompt before hashing), and (b) of Fig. 8 shows an example of the original text of the prompt in which confidential information has been replaced with a hashed character string (prompt after hashing). Note that there is no particular limitation on the display format of the input screen on which the original text of the prompt shown in Fig. 8 is displayed, and therefore Fig. 8 shows only a display field for the original text of the prompt.

[0057] An example of the original prompt text shown in FIG. 8 illustrates a notification text for a job interview. The pre-hashed prompt shown in FIG. 8(a) is created by combining a template text (a fixed text instructing the creation of an interview notification) corresponding to the interview notification with an additional text that defines a prerequisite. The template text has fields (e.g., 601 to 604) in which any word or phrase can be placed in the text, and the user can complete the input text (original prompt text) simply by rewriting the field parts with the desired phrase, which is highly convenient and greatly improves work efficiency.

[0058] The hashed prompt shown in (b) of Fig. 8 shows an example in which the wording of fields (601, 603, 604) designated as confidential information items among any fields placed in the template text is hashed. In this way, confidential information is concealed in the hashed prompt.

[0059] When the user checks the original text of the prompt redisplayed on the user terminal 10 and determines that the necessary requirements are satisfied, the "Confirm" button 560 is pressed on the prompt confirmation screen 500 of the user terminal 10. As a result, an instruction to send the confirmed original text of the prompt to the generation AI server 30 is transmitted to the writing generation instruction unit 250 via the screen input acceptance unit 220 of the writing support device 20 (step S140).

[0060] When the writing generation instruction unit 250 of the writing generation support device 20 receives an instruction from the user terminal 10 to send the original text of the prompt to the generation AI server 30, it sends the original text of the prompt after the replacement process temporarily stored in the storage unit 280 to the generation AI server 30 as a prompt for inputting the large-scale language model (step S240). At the same time, the writing generation instruction unit 250 saves information including the title of the sent prompt, the content (wording) of the confidential information, the user ID, etc., together with the transmission log, in the storage unit 280 as a usage history for each user.

[0061] By storing the usage history for each user in the memory unit 280, users of the system (including corporate users) can centrally manage data to know when, who, and what kind of generating AI was used, and what confidential information was included, thereby enabling data management to be carried out safely.

[0062] When the generation AI server 30 receives a prompt for inputting a large-scale language model from the text generation support device 20 at the generation request receiving unit 310, it transmits the received prompt for inputting the large-scale language model to the text generation unit 320, and the text generation unit 320 generates a new text (called an answer text) in accordance with the received prompt for inputting the large-scale language model.

[0063] The prompt for inputting the large-scale language model received by the generation AI server 30 does not contain confidential information in plain text, so the confidential information is concealed from the generation AI side, and confidentiality can be maintained even if it is used as learning data. In addition, since the wording corresponding to confidential information is replaced with a character string consisting of a hash value, the large-scale language model recognizes the character string consisting of the hash value as a single word (proper noun), which has the advantage that a highly accurate generation result (answer sentence) can be output without affecting the understanding of the context.

[0064] When the answer sentence is generated by the sentence generation unit 320, the generation result output unit 330 outputs (transmits) the generated answer sentence to the requesting writing assistance device 20 (step S300).

[0065] When the control unit 200 of the text generation assistance device 20 receives the generated answer sentence from the generation AI server 30, it activates the confidential information restoration unit 260 to detect the hashed character string included in the generated answer sentence and restore the detected hashed character string to the character data before hashing. A correspondence table stored in the storage unit 280 is used to detect and restore the hashed character string.

[0066] When the generated document output unit 270 of the writing generation assistance device 20 has completed restoring the hashed character string included in the answer sentence, the generated document output unit 270 generates an output screen displaying the restored answer sentence and transmits the output screen to the user terminal 10 (Step S250).

[0067] The user terminal 10 displays the output screen received from the writing assistance device 20 on the display means of the user terminal (step S150). Note that the user terminal 10 can also obtain the answer sentence as text data from the output screen.

[0068] FIG. 9 is a diagram showing an example of a generation result (answer sentence) generated by the writing generation support device according to this embodiment, where (a) of FIG. 9 shows an example of the generation result (answer sentence) before the hashed confidential information is restored, and (b) of FIG. 9 is a diagram showing an example of the generation result (answer sentence) after the hashed confidential information is restored.

[0069] In the generation result (answer text) before restoration shown in Figure 9(a), the wording corresponding to the confidential information is displayed as a hash value, and it can be seen that the confidential information was concealed during the text generation process, and the text was generated without affecting the interpretation of the text.In addition, in the generation result (answer text) after restoration shown in Figure 9(b), it can be seen that the concealed confidential information has been properly restored to the original wording.

[0070] As described above, the sentence generation system using the confidentiality prompt according to the present invention can easily generate a prompt for inputting a large-scale language model in which confidential information is concealed, and can generate sentences with high accuracy. In addition, since the user does not need to directly send the generated prompt for inputting a large-scale language model to the generation AI, and the usage history is also saved, the user can easily obtain the sentences generated by the generation AI and can safely manage data.

[0071] Although the embodiments of the present invention have been described in detail above with reference to the drawings, the present invention is not limited to the above-described embodiments and can be modified in various ways without departing from the technical scope of the present invention. [Explanation of symbols]

[0072] 1. A text generation system using confidential prompts 10 User terminal 20 Sentence generation support device 30 Generating AI Server 101 CPU 102 Memory 103 Storage device 104 Communication Interface 105 Input Device 106 Output Device 200, 300 Control section 210 Input screen generation unit 220 Screen input reception section 230 Confidential Information Conversion Department 240 Prompt Generation Unit 250 Sentence generation instruction section 260 Confidential Information Recovery Department 270 Generated Document Output Unit 280 Storage section 290 Communications Department 310 Creation request reception unit 320 Sentence generation section 330 Generation result output section 340 Model Memory Unit 350 Data Communications Department

Claims

1. A sentence generation system that generates a prompt for inputting a large-scale language model in which confidential information included in an input instruction sentence is concealed, the system comprising: The writing system includes a writing support device connected to a user terminal and a generation AI (Generative Artificial Intelligence) server via a communication network, The sentence generation assistance device comprises: an input screen generating unit that generates an input screen on which a standard form for inputting the instruction text is displayed and transmits the input screen to the user terminal; a screen input receiving unit that receives character data of the instruction statement inputted into the template form of the input screen from the user terminal; a confidential information conversion unit that converts character data of a phrase designated as the confidential information input from the user terminal via the screen input acceptance unit into a hashed character string; a prompt generating unit that generates a prompt for inputting a large-scale language model by replacing character data corresponding to a word designated as confidential information, among character data of the instruction sentence inputted into the template form, with the hashed character string; a sentence generation instruction unit that transmits a prompt for inputting the generated large-scale language model to the generation AI server to instruct the generation of sentences; a confidential information restoration unit that receives a text generated from the generation AI server, detects the hashed character string included in the received text, and restores the detected hashed character string to character data before hashing; a generated document output unit that transmits to the user terminal an output screen on which the generated text in which the hashed character string is restored is displayed; a control unit for controlling the entirety of the writing assistance device.

2. the confidential information conversion unit stores the hashed character string in a storage unit in association with character data of a word specified in the confidential information before hashing; The sentence generation system using a confidentiality prompt as described in claim 1, characterized in that the confidential information restoration unit retrieves and restores character data of a phrase specified in the confidential information before hashing that corresponds to the detected hashed string from the memory unit.

3. 2. A text generation system using a confidentiality prompt as described in claim 1, wherein the text to be designated as confidential information is input from a confidential information designation field displayed on the input screen transmitted to the user terminal.

4. The template form displayed on the input screen includes a plurality of input fields with different items, The text generation system using a confidentiality prompt as described in claim 1, characterized in that the prompt generation unit dynamically generates a prompt for inputting a large-scale language model by combining character data entered into each of the multiple input fields of the template form, generates the input screen displaying the generated prompt for inputting a large-scale language model, and transmits it to the user terminal.

5. The template form includes an input field for specifying a genre of text to be generated, The text generation system using a confidentiality prompt as described in claim 4, characterized in that the input screen generation unit generates a prompt confirmation screen including a prompt template corresponding to the genre name entered in the input field specifying the genre, and transmits the screen to the user terminal.

6. The sentence generation system using a confidentiality prompt as described in claim 1, characterized in that the control unit generates a usage history for each user, the usage history including the generated prompt for inputting the large-scale language model and character data corresponding to the wording specified as the confidential information, and stores the usage history in a memory unit.

Images