Information providing device, information providing method, and information providing program

Abstract

To effectively utilize a language model specialized in a specific field.SOLUTION: An information providing device according to an embodiment comprises a discussion unit and a proposal unit. The discussion unit holds a discussion on a policy guidance by a plurality of chairpersons set in a language model generated by learning data stored in a database on a policy and for generating an answer for an input prompt. The proposal unit judges the discussion results of the discussion unit by a judging account set in the language model, and proposes a policy guideline.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The disclosed embodiments relate to an information providing device, an information providing method, and an information providing program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there is known a system that uses a language model to generate an answer to a question input by a user (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2022-503838 Summary of the Invention [Problem to be solved by the invention]

[0004] While conventional technology generates answers based on news articles, it does not take into account the use of language models specialized for specific domains.

[0005] The present invention has been made in view of the above, and has an object to effectively utilize a language model specialized for a specific field. [Means for solving the problem]

[0006] According to an embodiment, an information providing device includes a discussion unit and a proposal unit. The discussion unit is a language model generated by learning data stored in a database related to policies, and holds discussions on policy guidelines using multiple chairperson accounts set in the language model that generates answers to input prompts. The proposal unit judges the results of the discussion by the discussion unit using judge accounts set in the language model, and proposes policy guidelines. Effect of the Invention

[0007] According to one aspect of the embodiment, a language model specialized for a specific field can be effectively utilized. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overview of an information providing device according to an embodiment. [Diagram 2] FIG. 2 is a functional block diagram illustrating an example of the configuration of an information providing device according to the embodiment. [Diagram 3] FIG. 3 is a flowchart illustrating a processing procedure executed by the information providing device according to the embodiment. [Figure 4] FIG. 4 is a flowchart illustrating a processing procedure executed by the information providing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a computer hardware configuration that functions as an information providing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will be described below through embodiments, but the following embodiments do not limit the scope of the invention according to the claims. In addition, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0010] A process flow of the information providing device according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an overview of the information providing device according to the embodiment. Fig. 1 shows a configuration of an information providing system 1 including an information providing device 10 according to the embodiment.

[0011] 1, the information providing system 1 includes an information providing device 10 and a policy information database 20. The policy information database 20 is a database that stores various data related to various policies of the country, each local government, and the like.

[0012] The information providing device 10 is a device to which various devices, including a policy information database 20, are plugged in. In the information providing system 1, in which the various devices include various types of servers, vehicles, smartphones, and other devices, the information providing device 10 realizes the highest level of artificial intelligence by being plugged in to each device.

[0013] For example, in the information provision system 1, the information provision device 10 and each device including the policy information database 20 incorporate semiconductor chips manufactured by the same manufacturer. Each of these semiconductor chips may perform machine learning or deep learning by itself.

[0014] In addition, the semiconductor chips used in the information providing device 10 and the policy information database 20 are chips of a size suitable for each housing. For example, assuming that the chip size of the information providing device 10 is XL size, L size is used for servers and vehicles, and S or M size is used for user terminals. For terminals with housing sizes even smaller than the user terminals, SS size is used and is put into a SoC (System on a chip) to form a single chip. Note that the number of tiles for each size is only an example and is not limited to the above. If it is desired to attach accessories such as a camera or a microphone to the user terminal, a chip dedicated to accessories other than the semiconductor chip may be set in an empty space near the semiconductor chip in the SoC.

[0015] In this way, in the information providing system 1, the use of semiconductor chips made by the same manufacturer in various devices connected to the information providing device 10 makes it possible to keep the information providing system 1 secure. In other words, in the information providing system 1, hacking, virus infection, and deep fakes can be avoided with a high degree of accuracy, and privacy between the information providing device 10 and data source providers including the policy information database 20 can be ensured.

[0016] In this embodiment, the information providing device 10 learns a model based on a data source acquired from the policy information database 20. The model is a language model. As a language model, for example, ChatGPT by OpenAI Inc. is known (Reference: https: / / openai.com / blog / chatgpt). The language model may be a language model such as GAN (Generative Adversarial Networks) using a neural network, VAE (Variational Autoencoder), etc.

[0017] In this embodiment, the language model generates a text response to a text of a query (hereinafter, a prompt) input by a user. The language model is trained in advance using a data source. The language model may be trained by known machine learning techniques.

[0018] This enables the language model to generate an answer based on the data source. In this embodiment, the information providing device 10 plugs in the policy information database 20 (step S1), and learns the language model based on the data stored in the policy information database 20 (step S2).

[0019] In this way, the information providing device 10 trains the language model on various data stored in the policy information database 20. As a result, the language model generates a response to an input prompt based on the learned policy-related data. In other words, the information providing device 10 can generate a language model specialized for a policy field.

[0020] In this embodiment, a language model specialized in the policy field is used to provide advice regarding the policies of the nation or each local government. Specifically, in this embodiment, accounts (roles) of "Chairpersons A to C," "Experts A to C," and "Judge System" are set in advance by system prompts of the language model.

[0021] "Chairpersons A to C" are accounts corresponding to the heads of the nation or local governments. That is, Chairpersons A to C are accounts corresponding to the prime minister, prefectural governors, city mayors, town mayors, village mayors, etc. In this embodiment, Chairperson A holds discussions through multiple accounts such as Chairperson A-1, Chairperson A-2, and Chairperson A-3, and Chairperson B holds discussions through multiple accounts such as Chairperson B-1, Chairperson B-2, and Chairperson B-3, and derives policy guidelines as Chairperson A and Chairperson B.

[0022] "Experts A to C" are expert accounts in various fields involved in the management of the nation or local governments.

[0023] Specific examples of expert accounts include the fields of finance, security, government, energy, and healthcare. The "Judge System" is an account that judges the results of discussions by each account. For example, the judge system judges the merits of each account's arguments and proposes their content. Expert Account A holds discussions with multiple accounts, such as Expert Account A-1, Expert Account A-2, and Expert Account A-3, and Expert Account B holds discussions with multiple accounts, such as Expert Account B-1, Expert Account B-2, and Expert Account B-3, and draws conclusions on policy directions for each field.

[0024] In this embodiment, the assertions made by each of the multiple chairperson accounts are input as prompts to the language model, and the input prompts are set as system prompts so that the other chairperson accounts can debate on the input prompts.

[0025] Such a setting enables each chairperson account to hold a spontaneous discussion using the language model. As shown in Fig. 1, the information providing device 10 uses the language model to hold a discussion on politics through each account (step S3).

[0026] For example, Chair Accounts A to C are accounts with different political ideologies, such as conservative, reformist, right-wing, and left-wing, and each of them debates using language models. The virtual experts debate billions of times per second. This makes it possible to verify and solve problems from all angles, and to instantly propose policies, etc.

[0027] Similarly, each expert account holds discussions with multiple accounts for each field and draws a conclusion on the policy direction for that field. Then, chairperson accounts A to C hold discussions on the policy direction based on the discussions in each field. Note that the final discussion may be held by all accounts including each account.

[0028] For example, the chairperson account holds a discussion on policy, and the "judging system" makes a judgment based on the content of the discussion (step S4). For example, the "judging system" is composed of multiple accounts. The multiple accounts that make up the judging system discuss the content of the discussion by the chairperson account, etc., and judge the final policy. For example, when a predetermined termination condition is met, such as when the discussion reaches a deadlock, the judging system compares the arguments of each account with the data stored in the policy information database 20 to determine the most appropriate policy direction.

[0029] The "judge system" then proposes the determined policy direction to the actual chairman. In other words, the information provision system 1 uses a language model to simulate a large-scale discussion on policies.

[0030] In this manner, the information providing device 10 according to the embodiment generates a language model based on various knowledge registered in the policy information database 20, and after holding a discussion using the language model, makes a proposal regarding a policy direction.

[0031] Therefore, the information providing device 10 according to the embodiment can effectively utilize a language model specialized for a specific field.

[0032] The configuration of the information providing device 10 will be described with reference to Fig. 2. Fig. 2 is a functional block diagram showing an example of the configuration of the information providing device according to the embodiment.

[0033] As shown in FIG. 2, the information providing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0034] The communication unit 11 transmits and receives information to and from the policy information database 20 and the like via the network.

[0035] The storage unit 12 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 12 stores various programs and various data. The storage unit 12 stores language model information 121.

[0036] The language model information 121 is information about a language model. For example, the language model information 121 is information about parameters for constructing a language model. Such parameters are, for example, weights and biases of a neural network.

[0037] The control unit 13 is a controller, and includes, for example, a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM, an input / output port, and various other circuits. The control unit 13 may also be configured with hardware such as an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 13 includes an acquisition unit 31, a generation unit 32, a discussion unit 33, and a proposal unit 34.

[0038] The acquiring unit 31 acquires data from a data source provider. For example, the acquiring unit 31 acquires data related to politics from the policy information database 20 (see FIG. 1). For example, the acquiring unit 31 acquires data every time the policy information database 20 is updated.

[0039] The generation unit 32 generates a language model. Specifically, the generation unit 32 learns the language model based on a data source related to politics. The generation unit 32 also updates the parameters of the model through learning. The generation unit 32 may regenerate the model at each learning timing, or may reflect in the model a data source that is a difference from the previous learning.

[0040] The discussion unit 33 is a language model generated by learning data stored in a political database, and uses the language model to generate answers to input prompts, and holds a discussion between multiple chairman accounts, each with different arguments.

[0041] First, the discussion unit 33 sets accounts for each field according to the system prompts of the language model. For example, the discussion unit 33 sets a chairperson account, expert A to C accounts, and a judge system account.

[0042] After setting these accounts, the discussion unit 33 starts a discussion using the language model. For example, the discussion unit 33 holds a discussion for each field, and then holds a discussion using the chairperson's account based on the discussion results of each field. Specifically, the discussion unit 33 holds a discussion using the language model by the following steps 1 to 5.

[0043] Step 1: Set up a multi-functional virtual expert There are hundreds of sets of virtual experts in different policy fields. For example, politics has specific characters such as "Political Science Expert A", "Political Science Expert B", and "Political Science Expert C", while economics has specific characters such as "Economics Expert A", "Economics Expert B", and "Economics Expert C".

[0044] Step 2: Speed ​​up information exchange These experts exchange information based on each data and debate billions of times per second, enabling them to instantly make decisions on optimal policies and economic measures.

[0045] Step 3: Handling data The virtual experts share and debate various types of information, such as stock prices and birth rates, allowing them to quickly arrive at optimal solutions from multiple perspectives.

[0046] Step 4: Self-study and update If new knowledge or information is discovered during the discussion, it will be immediately reflected in the database and used in future discussions, allowing doctors to provide diagnoses and treatments based on the most up-to-date policy information.

[0047] Step 5: Building consensus Debate involves the clash of different opinions and perspectives, leading to the formation of a final "consensus." This allows information and knowledge from multiple sources to be comprehensively incorporated when policy proposals are made.

[0048] The above has been explained about the chairman account, but each of the Expert A to C accounts is also assigned a character, and each account is further divided into various characters. Each account holds a discussion and forms a consensus as Experts A to C.

[0049] The proposal unit 34 judges the results of the discussion by the discussion unit 33 using a judge account set in the language model, and proposes a policy guideline. For example, the proposal unit 34 makes a judgment when a predetermined end condition is met, such as when the discussion by the discussion unit 33 reaches a deadlock.

[0050] For example, the proposing unit 34 refers to various data registered in the policy information database 20, judges the policy that is estimated to be the most appropriate among the policy guidelines discussed by each chairperson account, and proposes that policy guideline. Alternatively, a policy guideline may be proposed by adding various consensuses, such as the consensus of Expert A, to the consensus result of the chairperson account.

[0051] Next, a process procedure executed by the information providing device 10 according to the embodiment will be described with reference to Fig. 3 and Fig. 4. Fig. 3 and Fig. 4 are flowcharts showing a process procedure executed by the information providing device 10 according to the embodiment.

[0052] First, the procedure for generating a language model will be described with reference to Fig. 3. As shown in Fig. 3, the information providing device 10 first acquires data related to politics from the policy information database 20 (step S101). Next, the information providing device 10 generates a language model based on the data acquired from the policy information database 20 (step S102), and ends the process.

[0053] Next, the discussion process using the language model will be described with reference to Fig. 4. As shown in Fig. 4, the information providing device 10 first holds a discussion on a policy in each field (step S111). Then, the information providing device 10 holds a discussion on a policy between fields (step S112).

[0054] Next, the information providing device 10 judges the results of the discussion (step S113), and then proposes a policy (step S114), and ends the process.

[0055] According to this embodiment, a language model trained based on data stored in the policy information database 20 can be used to discuss policies and then propose policy guidelines, making it possible to effectively utilize language models specialized for specific fields.

[0056] 5 is a diagram showing an example of a computer hardware configuration functioning as an information providing device. A program installed in the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the device according to the present embodiment, and / or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0057] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphic controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive, a solid state drive, etc. The computer 1200 also includes input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0058] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

[0059] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0060] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0061] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing operations or processing of information according to the use of the computer 1200.

[0062] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0063] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0064] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0065] The above-mentioned programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0066] The blocks in the flowcharts and block diagrams in the present embodiment may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable storage medium, and / or a processor provided with computer readable instructions stored on a computer readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as, for example, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like, including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0067] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

[0068] The computer readable instructions may include either assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0069] Computer readable instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., to cause the processor of the general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, to execute the computer readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0070] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications or improvements can be made to the above embodiments. It is clear from the claims that such modifications or improvements can also be included in the technical scope of the present invention.

[0071] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and may be realized in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is essential to perform the process in this order. [Explanation of symbols]

[0072] 1 Information provision system 10 Information provision device 11 Communications Department 12 Storage section 13 Control section 20 Policy Information Database 31 Acquisition Department 32 Generation part 33 Discussion Department 34 Proposal Department 121 Language Model Information

Claims

1. a discussion section for holding discussions on policy policies using multiple chairperson accounts set in a language model that is generated by learning data stored in a database related to politics and that generates answers to input prompts; a proposal unit that judges a result of the discussion by the discussion unit using a judge account set in the language model and proposes the policy direction; An information providing device comprising:

2. The discussion section: Discussions will be held including expert accounts from various fields related to politics set in the language model.

2. The information providing device according to claim 1.

3. The discussion section: Discussions will be held in the respective expert accounts for each field, and discussions will be held in the chairperson account based on the results of the discussions in each field.

3. The information providing device according to claim 2.

4. An information providing method executed by an information providing device, comprising: a discussion process in which a language model is generated by learning data stored in a database related to politics, and a discussion process is performed on policy guidelines using a plurality of chairperson accounts set in the language model that generates answers to input prompts; a proposal step of judging a result of the discussion by the discussion step using a judge account set in the language model and proposing the policy direction; Methods of providing information, including:

5. a discussion step in which a discussion on policy policies is held by a plurality of chairperson accounts set in a language model that is generated by learning data stored in a database related to politics and that generates answers to input prompts; a proposal step of judging a result of the discussion by the discussion step using a judge account set in the language model and proposing the policy direction; An information providing program that causes a computer to execute the above.

Images