Programs, methods, information processing devices, and systems

Abstract

The goal is to reduce security risks associated with the use of generative AI. [Solution] This is a program for operating a computer equipped with a processor and memory. The program performs the following steps: receiving input information for using a generated AI from a terminal operated by a member of the organization; determining whether the received input information matches pre-stored conditions for the member's use of the generated AI; and if the input information matches the conditions, continuing to use the generated AI; otherwise, informing the terminal that the generated AI cannot be used.

Description

Technical Field

[0001] The present disclosure relates to programs, methods, information processing apparatuses, and systems.

Background Art

[0002] In recent years, the technology of generative AI has developed significantly, and the opportunities for its use are increasing for the purpose of improving work efficiency.

[0003] Patent Document 1 describes a technique for assisting in text generation using a language model. In this technique, a new prompt is generated by replacing variables in a template prompt with specific answers, and text data is obtained by inputting this into the language model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] [[ID=३९]]As the use of generative AI within an organization increases, managing its use by the organization's members has become important from the perspective of security measures such as preventing information leakage. In an environment where members can freely use generative AI, there is a risk that prompts containing confidential information may be input, or that high-cost AI usage may occur frequently.

[0006] An object of the present disclosure is to reduce security risks associated with the use of generative AI.

Means for Solving the Problems

[0007] To solve the above problems, a program according to one aspect of the present disclosure is a program for operating a computer comprising a processor and memory, which performs the following steps: receiving input information for using a generated AI from a terminal operated by a member of an organization; determining whether the received input information matches pre-stored conditions for the member's use of the generated AI; and, if the input information matches the conditions, continuing to use the generated AI, and if it does not match, informing the terminal that the generated AI cannot be used. [Effects of the Invention]

[0008] According to this disclosure, the security risks associated with the use of generative AI can be reduced. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing an example of the overall configuration of System 1. [Figure 2] This figure shows an example of the functional configuration of terminal device 10. [Figure 3] This is a block diagram showing an example of the functional configuration of server 20. [Figure 4] This diagram shows the data structure of User Table 2021. [Figure 5] This diagram shows the data structure of template table 2022. [Figure 6] This diagram shows the data structure of the cache table 2023. [Figure 7] This figure shows an example of the processing flow in System 1. [Figure 8] This figure shows an example of the processing flow in System 1. [Figure 9] This figure shows an example of the screen in this disclosure. [Figure 10] A block diagram showing the basic hardware configuration of Computer 90. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0011] Furthermore, in the following description, "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0012] Furthermore, at least one processor may be a broad-sense processor, such as a hardware circuit that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)).

[0013] Furthermore, in the following explanation, we may use expressions such as "xxx table" to describe information that yields an output for a given input. This information can be data with any structure, or it can be a learning model such as a neural network that generates an output for a given input. Therefore, "xxx table" can be referred to as "xxx information."

[0014] Furthermore, in the following explanation, the structure of each table is just an example; one table may be divided into two or more tables, or all or part of two or more tables may constitute a single table.

[0015] In the following description, the "program" may be used as the subject to describe the processing. However, since the program performs the defined processing by being executed by a processor, appropriately using a storage unit and / or an interface unit, etc., the subject of the processing may be the processor (or a device such as a controller having the processor).

[0016] The program may be installed in a device such as a computer, or may be in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Also, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0017] Also, in the following description, an identification number is used as identification information for various objects, but other types of identification information (e.g., an identifier including letters and symbols) may be adopted.

[0018] Also, in the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type separately, the identification numbers (or reference signs) of the elements may be used.

[0019] Also, in the following description, the control lines and information lines show those considered necessary for the description, and not necessarily all the control lines and information lines on the product are shown. All the components may be interconnected.

[0020] Each information processing device is composed of a computer having an arithmetic unit and a storage unit. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10 and the server 20, descriptions overlapping with the basic hardware configuration of the computer and the basic functional configuration of the computer described later are omitted.

[0021] <Overview> The system according to this embodiment mediates the use of generative AI within an organization. The system receives prompts for input to the generative AI from terminal devices operated by members of the organization, and determines whether the received prompts match pre-stored conditions for the use of generative AI by members. If the prompt matches the conditions, the system inputs the prompt into the generative AI; otherwise, it displays to the terminal device that the generative AI cannot be used. This promotes the safe use of generative AI while ensuring the security of the entire organization.

[0022] <1. Overall System Configuration> Figure 1 is a block diagram showing an example of the overall configuration of the prompt management system 1 according to this embodiment. System 1 is, for example, a system for managing and mediating the use of generative AI within an organization. As shown in Figure 1, System 1 includes terminal devices 10, a server 20, and a generative AI system 30. These devices are connected to each other so as to be able to communicate with each other via a network 80, such as the Internet or a LAN (Local Area Network).

[0023] In Figure 1, for the sake of illustration simplicity, System 1 is shown as an example including one terminal device 10, but it is not limited to this, and in reality, it may include multiple terminal devices 10 for use by multiple members belonging to the organization. Similarly, the server 20 and the generation AI system 30 may each consist of a single device or may be configured as a collection of multiple devices. For example, the multiple functions required to realize the server 20 may be distributed to one or more physical servers according to the processing capacity of each hardware, etc.

[0024] Terminal device 10 is an information processing device operated by members of the organization. Members can freely input prompts to the generation AI system 30 via this terminal, or select prompt templates prepared in advance on server 20. Terminal device 10 can be implemented as, for example, a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer), laptop PC, etc. Terminal device 10 includes hardware such as a communication interface, input device, output device, memory, storage, and processor.

[0025] Server 20 is the core information processing device of this disclosure, and centrally manages and controls the use of the generation AI system 30 within the organization. Server 20 may be, for example, an API (Application Programming Interface) server. Server 20 is implemented by a computer equipped with hardware such as a communication interface, input / output interfaces, memory, storage, and a processor.

[0026] The generation AI system 30 is, for example, a cloud server with an LLM. The generation AI system 30 may be provided as an external cloud service, or it may be an on-premise AI model running on a server within the organization. Also, although Figure 1 shows an example where the generation AI system 30 is independent of the server 20, the server 20 may be configured to contain the functions of the generation AI system 30 (e.g., LLM). The number of LLMs included in the generation AI system 30 may be one or more.

[0027] LLM (Language Modeling) is a single-modal natural language model built by training on large amounts of text data, and is used for many NLG (Natural Language Generation) tasks, such as generating responses to specific questions, automatically generating sentences, and summarizing text. LLM is an example of a generative AI model. Examples of LLMs include the following: • OpenAI: GPT-4 Google: Gemini 1.5 Flash Anthropic:Claude 3.5 Sonnet

[0028] The generation AI system 30 inputs text data sent from the server 20 into the LLM and causes the LLM to output a response to the input prompt. The generation AI system 30 then sends the response output from the LLM back to the server 20.

[0029] <2. Configuration of terminal equipment> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10. As shown in Figure 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a camera 160, a location information sensor 150, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus.

[0030] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from an external source and outputs it to the control unit 190.

[0031] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 can be implemented, for example, by a touch-sensitive device 131 on which instructions are input by touching the operating surface. If the terminal device 10 is a PC, the input device 13 may be implemented by a reader, keyboard, mouse, etc. The input device 13 converts the instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0032] The output device 14 is a device for presenting information to the user operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is implemented, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0033] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of the audio signal. The audio processing unit 17 converts the signal received from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is implemented, for example, by an audio processing processor. The microphone 171 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 17. The speaker 172 converts the audio signal received from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0034] Camera 160 is a device that receives light using a photodetector and outputs it as a shooting signal.

[0035] The location information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. A GPS module is a receiving device used in a satellite positioning system. In a satellite positioning system, signals are received from at least three or four satellites, and the current position of the terminal device 10, which is equipped with a GPS module, is detected based on the received signals. The location information sensor 150 may also detect the current position of the terminal device 10 from the position of the wireless base station to which the terminal device 10 is connected.

[0036] The storage unit 180 is implemented by, for example, memory 15 and storage 16, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, user information 181.

[0037] User information 181 includes, for example, information about the user who uses the terminal device 10. User information includes, for example, the user's name, age, address, date of birth, contact information, etc.

[0038] The control unit 190 is realized when the processor 19 reads a program stored in the memory unit 180 and executes instructions contained in the program. The control unit 190 controls the operation of the terminal device 10. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193.

[0039] The operation reception unit 191 processes instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives instructions or information such as queries input from the touch-sensitive device 131, etc.

[0040] Furthermore, the operation reception unit 191 receives voice commands input from the microphone 171. Specifically, for example, the operation reception unit 191 receives voice signals input from the microphone 171 and converted into digital signals by the voice processing unit 17.

[0041] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 sends information input by the user or instructions from the user to the server 20. The transmitting / receiving unit 192 also receives information provided by the server 20.

[0042] The presentation control unit 193 controls the output device 14 to present information provided by the server 20 to the user. Specifically, for example, the presentation control unit 193 displays information such as answers to queries sent from the server 20 on the display 141. The presentation control unit 193 also outputs information sent from the server 20 through the speaker 172.

[0043] <3. Functional Configuration of the Server> Figure 3 shows an example of the functional configuration of server 20. As shown in Figure 3, server 20 performs the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0044] The communication unit 201 performs processing to enable the server 20 to communicate with an external device such as a terminal device 10 or a generation AI system 30 via the network 80.

[0045] The memory unit 202 stores, for example, various conditions or data related to the use of the generated AI. Specifically, the memory unit 202 stores a user table 2021 that defines the permissions or terminals that members are allowed to use, a template table 2022 that is a prompt template and can have conditions such as prohibited words or usage limits set on it, and a cache table 2023 that stores past usage history for reuse. These tables store various usage conditions based on the organization's security guidelines.

[0046] The control unit 203 is implemented by the processor executing a program stored in the memory unit 202, and controls the operation of the entire server 20. By operating according to the program, the control unit 203 functions as a reception module 2031, a decision module 2032, an output control module 2033, and a cache management module 2034.

[0047] The reception module 2031 receives information from the terminal device 10 as input information for the generation AI system 30, including prompts (freely entered text or selected templates) which are instructions for the generation AI, or information about the members (authority, identification information of the user terminal, etc.).

[0048] The decision module 2032 determines whether the input information received by the reception module 2031 matches the usage conditions defined in the user table 2021.

[0049] The output control module 2033 branches the processing based on the judgment result from the judgment module 2032. If the input information matches the conditions, it sends the input information to the generation AI system 30. If it does not match, it generates a notification indicating that the generation AI is unavailable and the reason for this, and sends it to the terminal device 10.

[0050] The cache management module 2034 stores pairs of previously entered prompts and the corresponding responses of the generating AI system 30 in the cache table 2023 to improve the efficiency and reduce costs of using the generating AI system 30. Furthermore, when a new prompt is entered, it searches the cache table 2023 for similar prompts, and if found, returns the response from the cache without querying the generating AI system 30.

[0051] <4. Data Structure> Figure 4 shows the data structure of User Table 2021. User Table 2021 is a data structure for comprehensively managing information about members belonging to an organization and the usage conditions for generating AI that apply to each member. This table may consist of items (columns) such as "User ID" as the primary key, "Permissions," "Device Restrictions," and "Template Usage Log." "Permissions" stores the permission level of the member, such as whether free input of prompts is allowed or the types of generating AI that can be used. "Device Restrictions" is for identifying devices that are permitted to use the system and stores a list of permitted / denied MAC addresses or IP addresses. "Template Usage Log" records historical information such as which templates each member used and when, and can be used for analyzing usage status. In addition to these items, User Table 2021 may also hold information on data restrictions, AI restrictions, and usage limits that apply to each user. This information is referenced by Decision Module 2032 to determine whether the received prompt contains prohibited data information and whether it meets the conditions for using generating AI. For example, data restriction information could include a list of keywords such as "personal information" or "confidential" that are prohibited from being entered into prompts, or specific files (data sources) that are prohibited from being accessed. AI restriction information could include the types of available generating AIs, and usage restriction information could include limits on the number of times each template can be used. Furthermore, this table may store different usage conditions associated with each generating AI that is permitted to be used. For example, it is possible to set stricter prohibited word lists or lower usage limits for certain generating AIs (e.g., external AIs), while applying relatively lenient conditions to other generating AIs (e.g., internal AIs). Of course, it is also possible to set conditions that are common to all generating AIs.

[0052] Figure 5 shows the data structure of template table 2022. Template table 2022 is a data structure for managing multiple prompt templates useful when using the generation AI. This table consists of items such as "service category," "instruction text," and "usage status," with "template ID" as a unique identifier. "Service category" indicates a specific task or purpose performed using the generation AI (e.g., "chatbot response," "email draft creation," "information summarization," etc.). "Instruction text" stores the text body of the template, which is a prompt template. This instruction text may include not only simple sentences, but also structured instructions to obtain high-quality answers, such as role instructions that instruct the generation AI system 30 to assume a specific role (e.g., "You are an expert familiar with XX tasks"), output format instructions to output answers in a specific format, or reference information specifications that specify information sources to refer to. It may also include variable parts (placeholders) for members to add specific information. The "Usage Status" section records the number of times a template has been used or the evaluation (satisfaction level) from members, and may be used to present popular templates in a ranking format. Each template is created by an administrator to ensure security in accordance with the organization's security guidelines, such as not containing words related to specified sensitive information or referencing specific files.

[0053] Figure 6 shows the data structure of the cache table 2023. The cache table 2023 is a data structure for recording past interactions in order to reuse the results of queries to the generating AI system 30. This table consists of items such as "cache ID," "past prompt," "answer," and "usage date and time." "Past prompt" stores the text of the prompt that was actually sent to the generating AI system 30, and "answer" stores the answer returned by the generating AI system 30 in response to it. This makes it possible to return a response without querying the generating AI system 30 again when a similar prompt is entered.

[0054] <5. Operation> Next, using the flowchart in Figure 7, a basic example of the prompt management process of the server 20 in this embodiment will be explained in detail. This flow mainly assumes a case where members freely input prompts.

[0055] First, in step S1, when a member accesses the service page of server 20 from terminal device 10, server 20 begins accepting input information to start using the generated AI. Members can use the generated AI permitted for use within the organization through this system. The type of input information is determined based on the member's authority; for example, members with certain authority can freely input prompts, while members with other authority are only allowed to select from pre-prepared prompt templates. The reception module 2031 receives the input information entered or selected by the member in this way from terminal device 10. This input information may include prompts, which are instructions for the generated AI, as well as information about the member (authority, identification information of the user's terminal, etc.).

[0056] Next, in step S2, the server 20 determines whether the received input information matches the usage conditions stored in advance. The determination module 2032 refers to the user table 2021 and verifies several conditions, such as whether the terminal identification information included in the input information is permitted, whether the prompt body does not contain prohibited words, and whether the input method is permitted by the member's authority.

[0057] Finally, in step S3, the server 20, based on the result of the decision in step S2, indicates that if the input information meets the conditions, it will continue to use the generation AI, and if it does not, it will not be able to use it. Specifically, if all usage conditions are met, the output control module 2033 sends the input information to the generation AI system 30 and presents the obtained response to the terminal device 10, thereby continuing to use the generation AI. On the other hand, if even one usage condition is not met, the output control module 2033 blocks the transmission of the input information and notifies the terminal device 10 that it cannot be used and the reason why.

[0058] <6.Summary> As described above, the server 20, acting as a prompt management device in this disclosure, receives input information from a terminal device 10 operated by a member of the organization to be input to the generation AI system 30 (reception step). The server 20 then determines whether the received input information matches the conditions for the member's use of the generation AI, which are stored in the storage unit 202 beforehand (determination step). Finally, based on the result of the determination step, the server 20 outputs the input information to the generation AI system 30 if it matches the conditions, and informs the terminal device 10 that the generation AI cannot be used if it does not match (output control step). In this way, the server 20 receives all input information transmitted from the terminal device 10 and determines its appropriateness by comparing it with the usage conditions stored in advance. Then, it blocks inappropriate input information that does not match the conditions without sending it to the generation AI system 30. This series of operations prevents use that violates the organization's security policy and reduces serious security risks such as information leakage.

[0059] <7. Variation> (Variations of the judgment method) In the above embodiment, an example was described in which the decision module 2032 makes conditional decisions based on rules. This rule-based decision includes, for example, matching keywords between the text included in the prompt and the prohibited word list, comparing terminal identification information included in the input information with the allowed list, determining whether or not to allow use based on the member's authority level, and verifying the usage limit set for each template. However, this method may have difficulty detecting inappropriate requests that depend on context. Therefore, in this modified example, a different generative AI is used as the decision method to achieve more flexible security control.

[0060] In this configuration, when input information is transmitted from the terminal device 10, the server 20 receives it and processes it using two stages of generation AI with different roles. First, the server 20 does not directly send the prompt contained in the received input information to the main generation AI system 30, which is responsible for content generation, but rather sends it to a first generation AI specialized in security checks. This first generation AI is a relatively small, fast-operating model that has learned, for example, the organization's security policies or past incident cases, and it is desirable to run it in a secure environment within the organization (such as an on-premises environment). The first generation AI understands the context of the prompt and determines whether it may contain confidential information, whether there is an intention to request disclosure of information outside the company, and whether there are other security risks.

[0061] If the first generating AI determines that the prompt is "safe," the server 20 forwards the prompt to a second generating AI (corresponding to the main generating AI system 30), whose primary purpose is content generation. This second generating AI may be an external cloud AI service. On the other hand, if the first generating AI determines that the prompt is "dangerous" or "requires verification," the server 20 blocks its transmission and notifies the administrator as necessary. In this way, by setting up a dedicated AI for security checks as a gatekeeper, it becomes possible to capture risks that include nuances that cannot be detected by rule-based methods.

[0062] (Variations of operation using templates and caching) In this modified example, the terminal device 10 and the server 20 work together, utilizing prompt templates and caching functions to achieve further operational efficiency and cost reduction while ensuring security. This operation will be explained with reference to the flowchart in Figure 8.

[0063] First, in step S11, the server 20 displays a list of prompt templates when a member accesses it from the terminal device 10. In the following step S12, the server 20 determines whether each template is usable. Based on this determination, for example, templates that have reached their usage limit may be displayed as unavailable, or even if selected, they may be controlled so that they are not input to the generation AI system 30.

[0064] In the following step S13, the output control module 2033 of the server 20 accesses the generation AI system 30 using an available template. Then, in step S14, the reception module 2031 of the server 20 receives the prompt selected by the member.

[0065] Next, in step S15, the cache management module 2034 of the server 20 searches the cache table 2023 for past prompts similar to the received prompt and extracts them. If similar prompts are extracted, in step S16, the server 20 presents the extracted past prompts and their answers to the terminal device 10.

[0066] Subsequently, in step S17, it is determined whether the user has consented to the use of the presented cache. If the user consents, the server 20 presents the cached answer as the formal response and terminates the process. On the other hand, if the user does not consent, or if no similar prompt is extracted, the response obtained from the generating AI system 30 is presented in step S13. Through this series of processes, organizations can ensure the security of prompts while simultaneously achieving cost reduction through the use of caches and business standardization through the use of templates.

[0067] (Modifications regarding data linkage function and automated patrolling) In this embodiment, the server 20 may have a function to collaborate with data sources inside and outside the organization and extend the prompts.

[0068] For example, server 20 interacts with an internal file server or with electronic documents (e.g., Word documents or PDF files) stored in cloud storage such as SharePoint® or Box®. If the prompt included in the input information received from terminal device 10 contains a specific instruction intended to refer to internal company information, server 20 searches the linked documents using keywords related to the prompt and extracts highly relevant information. It then attaches the extracted information as supplementary information to the original prompt and sends it to the generating AI system 30. This series of processes is called Retrieval-Augmented Generation (RAG). As a result, the generating AI system 30 can generate answers based not only on publicly available information but also on the organization's own up-to-date information or expertise, improving the accuracy of the answers and its ability to provide evidence.

[0069] Furthermore, the server 20 may have settings to connect to other external data sources, such as customer relationship management (CRM) systems like Salesforce®, schedulers, or proprietary customer databases. Members can select the data source they want to reference when executing prompts, depending on the task they are performing. For example, if a sales representative instructs the creation of an email draft for a specific customer, the system can retrieve the customer's past transaction history or inquiry details from the CRM system and provide them to the AI ​​generation system 30 as the prompt context. This enables the generation of more personalized and flexible content tailored to the individual customer's situation.

[0070] (Modified example of automatic generation of terms of use) In the above embodiment, an example was described in which the administrator manually sets the usage conditions. However, an organization's security policy may be frequently updated in response to changes in the business environment, and manually reflecting these updates in the system settings would be a significant burden on the administrator. Therefore, in this modified example, the server 20 automatically generates and updates the usage conditions based on the security guidelines.

[0071] In this configuration, server 20 analyzes the security guideline document uploaded by the administrator using natural language processing technology. It then extracts rules such as prohibited words like "confidential" or data patterns that constitute personal information, and automatically updates the usage conditions (e.g., the list of prohibited words) stored in user table 2021 based on these rules.

[0072] According to this modified version, administrators can reflect specific usage conditions in the system simply by uploading guideline documents. This reduces the burden on administrators and minimizes configuration errors, ensuring that the user environment always complies with the latest security policies.

[0073] <8. Screen example> Figure 9 shows an example of a user interface screen displayed on the terminal device 10. This screen is displayed, for example, on a web browser and provides various functions for members to use the generated AI safely and efficiently. The main area of ​​the screen displays a list of prompt templates 801. This list is organized by service category, such as "chatbot response" or "email reply creation." Each template may display a popularity ranking based on its usage count or evaluation from other members. Also, templates that have reached their usage limit are displayed in gray so that they cannot be selected, and only available templates are presented in an identifiable manner. Members can easily create safe prompts by selecting a template that suits their purpose from this list.

[0074] The screen also includes a free-form prompt input field 802. However, the display, hiding, and input capability of this input field are controlled according to the member's privileges. For example, it is possible to hide the field from members with general privileges and only allow them to select templates, while allowing members with administrator privileges to freely input prompts.

[0075] If, after a member sends a prompt, the server 20 determines that any terms of use have been violated, a notification message 803 will be displayed on the screen. This message will clearly state that the use has been blocked and the specific reason, such as "This connection is from an unauthorized device" or "The prompt contains the prohibited word 'Confidential'." This allows the member to understand what was wrong with their actions and learn how to use the system properly.

[0076] <Basic Computer Hardware Configuration> Figure 10 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 comprises at least a processor 901, main memory 902, auxiliary storage 903, and a communication interface IF991. These are electrically connected to each other by a communication bus.

[0077] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0078] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0079] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0080] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0081] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0082] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 10) is described below. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0083] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0084] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0085] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0086] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0087] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0088] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0089] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0090] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0091] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0092] The functions realized by the components described herein may be implemented in a circuit or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor is considered to be a circuit or processing circuitry, including transistors and other circuits. A processor may be a programmed processor that executes a program stored in memory. In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0093] While several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications are permitted without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0094] (Note) The details described in each of the above embodiments are noted below.

[0095] (Note 1) A program for operating a computer that includes a processor and memory, The program is provided to the processor: The steps include receiving input information for using the generated AI from a terminal operated by a member of the organization, The steps include determining whether the received input information matches the conditions for the use of the generated AI by the member, which are stored in advance, If the input information matches the conditions, the use of the generation AI is continued; if it does not match, a message is displayed to the terminal indicating that the generation AI cannot be used. A program that executes the command. (Note 2) The input information is a prompt, which is an instruction to the generating AI, and is the program described in <Appendix 1>. (Note 3) The aforementioned conditions include terminal identification information for identifying terminals that are permitted to use the generated AI, The program described in <Note 1> determines, in the step of making the determination, whether the terminal identification information of the terminal included in the input information matches the terminal identification information stored in advance. (Note 4) The aforementioned conditions include prohibited data information that is prohibited from being included in the prompt, The program described in Appendix 2, which includes determining whether or not the received prompt contains the prohibited data information in the aforementioned determination step. (Note 5) Multiple prompt templates are stored, The aforementioned conditions include the maximum number of uses within a predetermined period set for each prompt template, The program described in Appendix 2, wherein in the step of making the determination, if the prompt received in the step of receiving matches one of the multiple prompt templates, the program determines whether the number of times the prompt has been used has not reached the upper limit. (Note 6) The aforementioned multiple prompt templates are programs described in Appendix 5, created in accordance with security guidelines that specify certain words or files that are prohibited from being included in the prompt templates. (Note 7) The conditions further include restricting the member's prompt input to selection only from the multiple prompt templates stored, The program described in <Appendix 5> or <Appendix 6> accepts, in the aforementioned acceptance step, one prompt template selected from the plurality of prompt templates as the prompt. (Note 8) The prompts previously output to the generating AI and the responses from the generating AI to those prompts are stored in a cache in association with each other. The program described in Appendix 2, which, prior to the determination step, causes the processor to further perform the step of searching whether a prompt similar to the received prompt is stored in the cache, and if a similar prompt is stored, presents the response associated with the similar prompt to the terminal. (Note 9) A program described in any of <Appendix 1> to <Appendix 8> that causes the processor to further perform a step of automatically generating the conditions based on pre-configured security guidelines. (Note 10) The aforementioned conditions include information that identifies the generating AI that is permitted to be used according to the authority of the member, The program described in Appendix 1 to Appendix 9 includes determining whether the input information is to be input to the generating AI which is authorized to be used according to the authority. (Note 11) The aforementioned determination step involves causing the first generating AI to determine whether the received prompt matches the conditions. The output step is a program as described in any of <Appendix 2>, <Appendix 4>, <Appendix 5>, or <Appendix 10>, wherein the first generating AI determines that the conditions are met, and outputs the prompt to the second generating AI, which is the generating AI. (Note 12) The program described in any of Appendix 2, Appendix 3, Appendix 4, Appendix 5, or Appendix 10 includes determining whether the received prompt meets the conditions based on a rule base that conforms to pre-configured security guidelines. (Note 13) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all steps in any of the programs described in <Appendix 1> to <Appendix 12>. (Note 14) A method to be executed on a computer comprising a processor and memory, wherein the processor executes all steps in any of the programs described in Appendix 1 to Appendix 12. (Note 15) A system that provides means for executing all steps in the program described in any of the appendices 1 through 12. [Explanation of symbols]

[0096] 1... System 10…Terminal device 12…Communication IF 13…Input device 14…Output device 15…Memory 16…Storage 19… Processor 20... Server 22...Communication IF 23…Input / Output Interface 25…Memory 2 hours… storage 29… Processor 30…Generating AI system

Claims

1. A program for operating a computer that includes a processor and memory, The program is provided to the processor: The steps include receiving input information for using the generated AI from a terminal operated by a member of the organization, The steps include determining whether the received input information matches the conditions for the use of the generated AI by the member, which are stored in advance, If the input information matches the conditions, the use of the generating AI is continued; if it does not match, a message is sent to the terminal indicating that the generating AI cannot be used. Make it run, The aforementioned conditions include the types of input information that can be entered according to the authority of the member, A program that, in the aforementioned receiving step, causes the terminal to display an input screen for entering the input information according to the authority of the member.

2. The program according to claim 1, wherein the input information is a prompt which is an instruction to the generating AI.

3. The aforementioned conditions include terminal identification information for identifying terminals that are permitted to use the generated AI, The program according to claim 1, wherein in the step of making the determination, it is determined whether the terminal identification information of the terminal included in the input information matches the terminal identification information stored in advance.

4. The aforementioned conditions include prohibited data information that is prohibited from being included in the prompt, The program according to claim 2, further comprising determining in the aforementioned determination step whether or not the received prompt contains the prohibited data information.

5. Multiple prompt templates are stored, The aforementioned conditions include the maximum number of uses within a predetermined period set for each prompt template, The program according to claim 2, wherein in the determination step, if the prompt received in the acceptance step matches any one of the plurality of prompt templates, the program determines whether the number of times the prompt has been used has not reached the upper limit.

6. The program according to claim 5, wherein the plurality of prompt templates are created in accordance with security guidelines that specify certain words or files that are prohibited from being included in the prompt templates.

7. The conditions further include restricting the member's prompt input to selection only from the multiple prompt templates stored, The program according to claim 5, wherein in the receiving step, one prompt template selected from the plurality of prompt templates is received as the prompt.

8. The prompts previously output to the generating AI and the responses from the generating AI to those prompts are stored in a cache in association with each other. The program according to claim 2, wherein, prior to the step of making the determination, the processor further causes the processor to perform the step of searching whether a prompt similar to the received prompt is stored in the cache, and if a similar prompt is stored, presents the answer associated with the similar prompt to the terminal.

9. The program according to claim 1, further comprising causing the processor to perform a step of automatically generating the conditions based on pre-set security guidelines.

10. The aforementioned conditions include information that identifies the generating AI that is permitted to be used according to the authority of the member, The program according to claim 1, wherein the step of determining whether the input information is to be input to the generating AI which is authorized to use according to the authority.

11. The aforementioned determination step involves causing the first generating AI to determine whether the received prompt matches the conditions. The program according to claim 2, wherein when the first generating AI determines that the conditions are met, it forwards the prompt for use by the second generating AI, which is the first generating AI.

12. The program according to claim 2, wherein the determination step includes determining whether the received prompt meets the conditions based on a rule base that conforms to pre-configured security guidelines.

13. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all steps in the program described in any one of claims 1 to 12.

14. A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps of a program according to any one of claims 1 to 12.

15. A system comprising means for executing all steps in the program described in any one of claims 1 to 12.

Images