Information processor

Abstract

To appropriately distribute a storage destination of information on the basis of the confidentiality level required for the information.SOLUTION: An information processor 10 includes: a reception section 11 that receives generation request information input from a user; an extraction section 12 that extracts a predetermined keyword from the received generation request information; a determination section 13 that determines, from a plurality of databases 21 and 22 associated in advance with confidentiality levels of data to be stored, one or more storage destinations of data related to the generation request information on the basis of the extracted keyword; and a storage section 14 that stores, in one or more databases determined as the storage destinations, the data related to the generation request information of the confidentiality levels associated with the databases.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device. [Background technology]

[0002] In recent years, various types of content have been generated using generative artificial intelligence (AI) models. A generative AI model is a model that can generate generated results (content) in response to various input generation request information, based on the instructions, context, questions, and output format indicated in the generation request information, and return the generated results as response information. Large language models (hereinafter referred to as "LLMs") are known as generative AI models used in the technical field of natural language processing. In fact, LLMs require a great deal of effort and time for pre-training, and it is difficult to get them to provide completely accurate answers. Therefore, a technology called a Retrieval Augmented Generation system (hereinafter referred to as "RAG system") is known, which aims to reduce the effort and time required for pre-training and provide more accurate answers by providing the LLM with information to be referenced when making an inquiry to the LLM. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2017-085378 Summary of the Invention [Problem to be solved by the invention]

[0004] As LLM becomes more widely used in the future, it is expected that software agents equipped with LLM will be used to exchange information between different organizations, family members, and so on.

[0005] On the other hand, while there is a variety of information, some may be freely disclosed between different organizations or among family members, and other information should be kept secret from other organizations or other members. Therefore, in the RAG system, the storage destination of information provided to the LLM (i.e., information to be referenced by the LLM) must be allocated according to the above circumstances. Furthermore, although the technology for allocating information storage destinations is disclosed in Patent Document 1, allocation of information storage destinations based on the confidentiality level required for the information has not been considered.

[0006] Therefore, an object of the present disclosure is to appropriately allocate storage destinations for information based on the confidentiality level required for the information. [Means for solving the problem]

[0007] The information processing device according to the present disclosure includes a receiving unit that receives generation request information input by a user, an extraction unit that extracts predetermined keywords from the received generation request information, a determination unit that determines one or more storage destinations for data related to the generation request information based on the extracted keywords from a plurality of databases that are pre-associated with the confidentiality level of the data to be stored, and a storage unit that stores data related to the generation request information of the confidentiality level associated with the database in the one or more databases determined as the storage destination. [Effects of the Invention]

[0008] According to the present disclosure, it is possible to appropriately allocate storage destinations for information based on the confidentiality level required for the information. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a functional block diagram showing a configuration of an information processing device. [Figure 2] FIG. 10 is a flowchart showing a process of a recording phase executed in the information processing apparatus. [Figure 3] FIG. 10 is a flowchart showing a process of an answer phase executed in the information processing device. [Figure 4] FIG. 10 is a diagram illustrating a modified example of the configuration of an information processing device. [Figure 5] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0010] An embodiment of an information processing device according to the present disclosure will be described below with reference to the drawings. In the following embodiment, a form will be described in which a large language model (LLM) that is mainly used for text generation is used as an example of a generative AI model.

[0011] [Configuration of information processing device] FIG. 1 shows a configuration diagram of an information processing device 10 according to the present disclosure. As shown in FIG. 1, the information processing device 10 includes a receiving unit 11, an extracting unit 12, a determining unit 13, a storing unit 14, a reading unit 15, an output unit 16, a reference database (reference DB) 20, and an LLM 30 in order to perform the functions according to the present disclosure. The information processing device 10 is a device that constitutes the RAG system described above. The RAG system is a system that, when issuing a generation request to an LLM based on an instruction statement (generation request information), searches in advance for reference data to be referenced by the LLM, outputs the obtained reference data to the LLM together with the instruction statement, and then obtains the generation results from the LLM and outputs them to the user.

[0012] Furthermore, various information processing devices (desktop computers, notebook computers, servers, smartphones, mobile phones, smart watches, wearable devices, etc.) can be used as hardware for the information processing device 10. The functions of each unit will be described below.

[0013] The reference DB 20 is a database for storing various reference data to be referenced by the LLM 30. The reference DB 20 includes multiple databases that are pre-associated with the confidentiality levels of the reference data to be stored. In this embodiment, an example is described in which the reference DB 20 includes two types of DBs: a private DB 21 that stores reference data with a high confidentiality level and an open DB 22 that stores reference data with a low confidentiality level. However, the reference DB 20 may include three or more databases for storing data grouped into three or more confidentiality levels. The private DB 21 stores reference data with the highest confidentiality level, i.e., reference data that can only be used by the user who executed the storage process. On the other hand, the open DB 22 stores reference data with the lowest confidentiality level, i.e., reference data that can be used by anyone other than the user who executed the storage process.

[0014] The LLM 30 is also included in the information processing device 10. This configuration can be realized, for example, by installing an application that executes the functions of the LLM 30 in the information processing device 10. Note that a configuration may be adopted in which the information processing device 10 does not include the LLM 30 and instead interacts with an external LLM 30 (for example, on a network cloud), and this configuration will be described later with reference to FIG. 4.

[0015] The receiving unit 11 is a functional unit that receives generation request information input by a user (that is, information requesting the generation of some content (including, for example, various questions requesting the generation of answer documents)).

[0016] The extraction unit 12 is a functional unit that extracts predetermined keywords from the received generation request information. The "keywords" here are assumed to be of two types: (a) keywords that directly indicate secrecy, and (b) keywords related to content that is generally considered to be sensitive information. Examples of (a) include keywords such as surprise, secret, confidential, secret, classified, confidential, code, and private, which directly indicate that the words themselves are secret. Examples of (b) include keywords related to content that is generally not considered to be disclosed to others, such as keywords related to financial problems, family problems, health problems (mental and physical problems), romantic relationship problems, and workplace problems.

[0017] The determination unit 13 is a functional unit that determines one or more storage destinations for data related to the generation request information based on extracted keywords from multiple databases that are pre-associated with the confidentiality levels of the data to be stored (i.e., multiple databases for storing each of the data grouped according to the confidentiality levels of the data to be stored).

[0018] The storage unit 14 is a functional unit that stores reference data of confidentiality levels associated with one or more databases determined as storage destinations. The storage unit 14 also stores reference data, with information granularity set according to the confidentiality levels associated with the determined databases, in the determined databases. Specific examples of the functions of the determination unit 13 and the storage unit 14 are described below.

[0019] For example, if a user inputs generation request information to the LLM 30, "Please find a store where I can buy a surprise present tomorrow (March 8th)," and obtains a generation result (answer) from the LLM 30, "I recommend Department Store B as a store for buying a present," the keyword "surprise" is extracted from the generation request information, and the determination unit 13 determines that the user's planned behavior information, "Purchase a present at Department Store B on March 8th," obtained from the above exchange, has a confidentiality level of "high" based on the keyword "surprise," and determines the private DB 21, which corresponds to the confidentiality level "high," as the storage destination. However, for information with a lower information granularity (generalized information) of the planned behavior information, "Purchase a present at Department Store B on March 8th," the open DB 22, which corresponds to the confidentiality level "low," is determined as the further storage destination. Based on this determination, the storage unit 14 (1) Detailed action plan information, such as "Purchase a gift at department store B on March 8th," is stored in private DB21, which corresponds to the "high" confidentiality level. (2) The action plan information (simplified information) with a lower level of granularity than the detailed action plan information described above, "I will go out on March 8th (no details)", is stored in the open DB22 corresponding to the confidentiality level "low".

[0020] The reading unit 15 is a functional unit that, when new generation request information related to the saved reference data is received from a requester other than the user, reads data related to the new generation request information from a database corresponding to the confidentiality level that can be disclosed to the requester based on the relationship between the requester and the user. For example, if the requester is a family member of the user, although they are closely related to the user, they are not the user himself / herself. Therefore, reading from the private DB 21 corresponding to the confidentiality level "high" is avoided, and only reading from the open DB 22 corresponding to the confidentiality level "low" is performed, and the generalized information "going out on March 8th (no details)" is acquired.

[0021] The reading unit 15 also reads data related to the new generation request information from a database according to a confidentiality level determined based on information about the requester (e.g., whether the requester is a paid user or a free user). For example, if the requester is a paid user, data on home medical books can be used as RAG, and the requester can receive professional medical advice from an agent. This will be described in more detail later.

[0022] The output unit 16 is a functional unit that outputs reference data related to the read new generation request information together with the generation request information to the LLM 30 and outputs the generation result acquired from the LLM 30 to the requester. For example, when a question (new generation request information) such as "I want to return something that Mr. A left behind, where is Mr. A now?" is received from a family member of the above user (Mr. A), the output unit 16 outputs "Mr. A will be out on March 8th (no details)", which is information (simplified information) read only from the open DB 22 corresponding to the confidentiality level "low", as reference data together with the question to the LLM 30, and outputs the answer (generation result) acquired from the LLM 30, "Mr. A is out, but his current location is unknown", to the requester (Mr. A's family member).

[0023] [Regarding processing executed in information processing device 10] Below, we will explain the processes executed by the information processing device 10 in order: the recording phase process (Figure 2) in which new reference data is recorded in the reference DB 20 at the instruction of the user, and the answer phase process (Figure 3) in which a new question (generation request information) from a requester other than the user is output to the LLM 30, and an answer (generation result) is obtained and output from the LLM 30.

[0024] 2, first, the accepting unit 11 accepts generation request information input by a user (step S1). Next, the extracting unit 12 extracts keywords from the generation request information (step S2). Next, the determining unit 13 determines one or more DBs to be used as storage destinations for reference data related to the generation request information, based on the keywords (step S3).

[0025] Furthermore, the storage unit 14 stores, in the determined destination DB, reference data of the confidentiality level associated with the DB (step S4). At this time, the storage unit 14 stores, in the determined database, reference data with information granularity set according to the confidentiality level associated with the database. As in the example described above, the storage unit 14 stores detailed planned activity information, such as "Purchase a present at department store B on March 8th," in the private DB 21 corresponding to the confidentiality level "high," and also stores planned activity information (simplified information) with information granularity lowered from the detailed planned activity information, such as "Go out on March 8th (no details)," in the open DB 22 corresponding to the confidentiality level "low."

[0026] Through the above-described processing in the recording phase, reference data is stored in each of the private DB 21 and the open DB 22, with the granularity of information set according to the confidentiality level associated with each DB, as described above.

[0027] The following describes the process of the response phase shown in Fig. 3. Here, it is assumed that new generation request information regarding saved reference data is received from a requester other than the user.

[0028] First, the reading unit 15 reads data related to new generation request information from a database corresponding to the confidentiality level that can be disclosed to the requester based on the relationship between the requester and the user (step S11). Next, the output unit 16 outputs the reference data together with the generation request information to the LLM 30 (step S12). Then, when a response (generation result) is obtained from the LLM 30, the output unit 16 outputs the obtained response (generation result) to the requester (step S13). A specific example will be described below.

[0029] For example, if the requester is a family member of the user, although they are closely related to the user, they are not the user himself / herself, and therefore reading from the private DB 21 corresponding to the confidentiality level "high" is avoided, and only the open DB 22 corresponding to the confidentiality level "low" is read, and the generalized information "will be out on March 8th (no details)" is acquired. Thereafter, if a question (new generation request information) is received from the family of the user (Mr. A) on March 8th, such as "I want to return my forgotten item, where is Mr. A now?", the generalized information "will be out on March 8th (no details)" read only from the open DB 22 corresponding to the confidentiality level "low" is output as reference data along with the question to the LLM 30, and the answer (generation result) acquired from the LLM 30, "Mr. A is out, but his / her current location is unknown," is output to the requester (Mr. A's family).

[0030] According to the embodiment described above, detailed planned activity information, such as "Purchase a gift at department store B on March 8," is stored in private DB 21 corresponding to a confidentiality level of "high," while generalized information with reduced information granularity, such as "Go out on March 8 (no details)," is stored in open DB 22 corresponding to a confidentiality level of "low." Therefore, information storage destinations can be appropriately allocated based on the confidentiality level required for the information. Thus, when a question (generation request information) is input by a requester other than the user, reading from private DB 21 corresponding to a confidentiality level of "high" is avoided, and reference data is read only from open DB 22 corresponding to a confidentiality level of "low" and provided to LLM 30. As a result, the requester is provided with a response such as "Mr. A is out, but his current location is unknown," thereby fulfilling the user's (Mr. A's) desire for a "surprise."

[0031] Here, an example will be described in which the reading unit 15 reads data related to new generation request information from a database corresponding to a level determined based on information about the requester (e.g., whether the requester is a paid user or a free user). For example, if the requester inputs a question about medicine, if the requester is a paid user, the reading unit 15 reads the book data for "Home Medicine," which contains a lot of specialized medical information, from a database that has the book data pre-stored, and uses the book data as reference data for the LLM 30. This allows the paid user to obtain answers based on specialized medical advice from the LLM 30.

[0032] In addition to the above, the following methods can be used to allocate the databases from which reference data is read as described above. (a) There is a method of allocating based on the usage status of users of a certain service, such as whether it is their first access (first use), whether they have used the service more than N times in total, or whether they have used the service for more than N hours in total. (b) There is a method of allocating users of a service according to their skills or achievements. For example, there is a method of allocating users according to their karate rank (blue belt or black belt) or according to their past scores on an English proficiency test. (c) A method of allocating traffic based on whether or not a specific registration action related to a certain service has been performed, such as a method of allocating traffic based on whether or not the official SNS (Social Networking Service) account of a certain service has been followed. (d) There is a method of sorting according to the attributes (age, gender, etc.) of users of a certain service. For example, if a user is determined to be an elementary school student based on their age, they may be sorted into a database that does not use difficult expressions or does not include information on alcohol, tobacco, etc. (e) A method of allocating data according to the "character preferences" customized by a user of a certain service is exemplified. For example, a method of allocating data according to customized preferences is exemplified.

[0033] As described above, by sorting the database from which reference data is read into a database according to a level determined based on various information about the user (requester), data suitable for the user (requester) can be used as reference data for the LLM30 to refer to, and as a result, it becomes possible to obtain an answer from the LLM30 that is suitable for the user (requester).

[0034] The configuration of the information processing device 10 is not limited to the configuration shown in Fig. 1. For example, as shown in Fig. 4, the LLM 30 (generative AI model) may exist outside the information processing device 10 (for example, on a network cloud).

[0035] The gist of the present disclosure lies in the following [1] to [4]. [1] a reception unit that receives generation request information input by a user; an extraction unit that extracts predetermined keywords from the received generation request information; a determination unit that determines one or more destinations for storing data related to the generation request information based on keywords extracted from a plurality of databases that are previously associated with confidentiality levels of the data to be stored; a storage unit for storing data related to the generation request information having a confidentiality level associated with one or more databases determined as storage destinations; An information processing device comprising: [2] a reading unit that, when new generation request information related to the stored data is received from a requester other than the user, reads data related to the new generation request information from the database according to the confidentiality level that can be disclosed to the requester based on the relationship between the requester and the user; an output unit that outputs data related to the read new generation request information together with the generation request information to a generation AI model, and outputs a generation result obtained from the generation AI model to the requester; The information processing device according to [1], further comprising: [3] The reading unit The information processing device according to [2], wherein data relating to the new generation request information is read from the database according to the confidentiality level determined based on information about the requester. [4] The storage unit is The information processing device according to any one of [1] to [3], wherein the data is stored in the determined database with the granularity of information set according to the confidentiality level associated with the database.

[0036] [Explanation of terms, explanation of hardware configuration (Figure 5), etc.] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0037] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocation, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0038] For example, an apparatus according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 5 is a diagram illustrating an example of a hardware configuration of an information processing apparatus 10 according to an embodiment of the present disclosure. The information processing apparatus 10 described above may be physically configured as a computer apparatus including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0039] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0040] Each function of the information processing device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 1001, memory 1002, etc., so that the processor 1001 performs calculations, controls communication via the communication device 1004, and controls at least one of reading and writing data in the memory 1002 and storage 1003.

[0041] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0042] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-mentioned embodiments. Although the various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0043] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0044] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0045] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD).

[0046] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel).

[0047] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0048] Furthermore, the information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0049] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0050] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0051] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0052] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, notification of predetermined information (e.g., notification that "X is true") is not limited to being done explicitly, but may be done implicitly (e.g., by not notifying the predetermined information).

[0053] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0054] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0055] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0056] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0057] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0058] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0059] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0060] 10...information processing device, 11...reception unit, 12...extraction unit, 13...determination unit, 14...storage unit, 15...reading unit, 16...output unit, 20...reference DB, 21...private DB, 22...open DB, 30...LLM, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. a reception unit that receives generation request information input by a user; an extraction unit that extracts predetermined keywords from the received generation request information; a determination unit that determines one or more destinations for storing data related to the generation request information based on keywords extracted from a plurality of databases that are previously associated with confidentiality levels of the data to be stored; a storage unit for storing data related to the generation request information having a confidentiality level associated with one or more databases determined as storage destinations; An information processing device comprising:

2. a reading unit that, when new generation request information relating to the stored data is received from a requester other than the user, reads data relating to the new generation request information from the database according to the confidentiality level that can be disclosed to the requester in relation to the requester and the user; an output unit that outputs data related to the read new generation request information together with the generation request information to a generation AI model, and outputs a generation result obtained from the generation AI model to the requester; The information processing device according to claim 1 , further comprising:

3. The reading unit reading data relating to the new generation request information from the database according to the confidentiality level determined based on information about the requester; The information processing device according to claim 2 .

4. The storage unit storing the data in the determined database, the data having a granularity of information set in accordance with the confidentiality level associated with the database; The information processing device according to claim 1 .

Images