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

Abstract

To improve the satisfaction level of a user for the information to be provided.SOLUTION: An information processing device according to an embodiment comprises a generation unit and a provision unit. The generation unit generates an answer for the prompt input by a user using any of a plurality of language models whose provision sources of a data source used for training differ for each other. The provision unit provides the user with the answer generated by the generation unit together with information indicative of a provision source of data source used for training the language model used to generate the answer.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 generative 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] In conventional techniques, answer sentences are generated using the same generation model, so there is room for improvement in terms of improving user satisfaction with the answer sentences.

[0005] The present invention has been made in view of the above, and has an object to improve user satisfaction with the information provided. [Means for solving the problem]

[0006] An information providing device according to one aspect of an embodiment includes a generation unit that generates an answer to a prompt input by a user using one of a plurality of language models having different sources of data sources used for training, and a provision unit that provides the answer generated by the generation unit to the user together with information indicating the source of the data source used for training the language model used to generate the answer. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to improve user satisfaction with the information provided. [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 diagram for explaining changes in the amount of data. [Figure 4] FIG. 4 is a diagram showing an example of the information provision screen. [Diagram 5] FIG. 5 is a diagram showing an example of the information provision screen. [Figure 6] FIG. 6 is a diagram showing an example of the information provision screen. [Figure 7] FIG. 7 is a flowchart illustrating the flow of the pre-training process. [Figure 8] FIG. 8 is a flowchart illustrating the flow of the information provision process. [Figure 9] FIG. 9 is a diagram showing an example of the information provision screen. [Figure 10] FIG. 10 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] The flow of processing of the information providing device 10 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 10 according to the embodiment.

[0011] 1, the information providing device 10 acquires a data source from a data source provider that is a provider of the data source (step S1). For example, the entity of the data source provider is a plurality of servers (server 20_1, server 20_2, server 20_3) for distributing information.

[0012] The data source provider distributes information on the Internet via a website or a social networking service (SNS). The data source is data in the form of text, audio, image, etc., distributed by the data source provider.

[0013] Data source providers include, for example, newspapers, news agencies, broadcasting companies, publishers, and online news providers.

[0014] The information providing device 10 trains a model (learning process) based on the acquired data source. The model is a language model. For example, ChatGPT by OpenAI is known as a language model (Reference: https: / / openai.com / blog / chatgpt). The language model may be a generative model such as GAN (Generative Adversarial Networks) or VAE (Variational Autoencoder) using a neural network.

[0015] In this embodiment, the model generates a text response to a prompt input by a user. The model is pre-trained using a data source. The model may be trained by known machine learning techniques.

[0016] This allows the model to generate answers based on the data source. For example, if the prompt contains the keyword "electric car," the model can generate answers based on news articles related to that keyword. In other words, the training allows the content of the news articles to influence the answer generation by the model.

[0017] In step S1, the information providing device 10 continuously acquires data sources. Therefore, the amount of data sources acquired by the information providing device 10 increases over time.

[0018] The information providing device 10 has two models that are different from each other in terms of the data source providers of the data sources used for training: a standard model and an advanced model.

[0019] The information providing device 10 trains a standard model based on the data source of the first data source provider (step S2), and trains an advanced model based on the data source of the second data source provider (step S3).

[0020] The second data source provider includes more data source providers than the first data source provider. For example, the first data source provider includes "C News" and "D Sports Flash." The second data source provider includes "A Economic Newspaper," "B Journal," "C News," and "D Sports Flash."

[0021] The standard model is trained on a historical data source provided by a first data source, and the advanced model is trained on a current data source provided by a second data source.

[0022] In addition, the standard model may be trained based on the current data source provided by the first data source.

[0023] Here, the past data source is a data source acquired up to a certain time point in the past before the timing of model training. For example, if the certain time period is two years, when training is performed on "2023 / 6 / 22 16:05", the past data source is a data source acquired from the start of data source acquisition to "2021 / 6 / 22 16:05".

[0024] On the other hand, the current data source is the data source acquired up to the time when the model training is performed. For example, if training is performed on "2023 / 6 / 22 16:05", the current data source is the data source acquired from the start of data source acquisition to "2023 / 6 / 22 16:05".

[0025] The model may be trained every second, or even shorter (e.g., every nanosecond).

[0026] Here, the information providing device 10 accepts an inquiry from a user (step S4).Then, the information providing device 10 generates a response to the inquiry by using a model according to the user's plan (step S5).

[0027] In addition, an inquiry from a user is transmitted to the information providing device 10 via the terminal 30. In addition, the information providing device 10 transmits a response to the terminal 30. The terminal 30 is, for example, a personal computer, a smartphone, or the like. In addition, the terminal 30 is connected to the information providing device 10 via the Internet.

[0028] The information providing device 10 provides an answer as a service. The service includes a higher-level premium plan (second plan) and a lower-level freemium plan (first plan). The premium plan is a subscription plan in which a fixed fee is charged for a certain period (e.g., yearly or monthly), or a pay-as-you-go plan in which the fee is determined according to the usage fee. The freemium plan is a free plan. The freemium plan may be replaced with a plan (e.g., a basic plan) that charges less than the premium plan.

[0029] The information providing device 10 realizes differentiation of service quality for each plan depending on the difference in the data source provider that provides the data source used to train the model to be used. When the user subscribes to the premium plan, the information providing device 10 generates an answer using an advanced model. On the other hand, when the user subscribes to the freemium plan, the information providing device 10 generates an answer using a standard model. That is, when the user subscribes to the premium plan, the information providing device 10 generates an answer sentence using an advanced model trained based on the data source of the second data source provider. Also, when the user subscribes to the freemium plan, the information providing device 10 generates an answer using a standard model trained based on the data source of the first data source provider.

[0030] The information providing device 10 provides the generated answer to the user (step S6). The information providing device 10 may accept the prompt and provide the answer via a chat-style UI.

[0031] Here, if the user has subscribed to a premium plan, the information providing device 10 updates the advanced model based on the latest data source and further generates an answer (step S7). The model updated in step S7 is called a real-time model. The information providing device 10 provides an additional answer generated using the real-time model (step S8).

[0032] The information providing device 10 continuously acquires data sources during the period from generating an answer to providing the generated answer (steps S5 to S6). The information providing device 10 can generate an answer that reflects a difference that occurs during this period by using a real-time model.

[0033] 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 10 according to the embodiment.

[0034] As shown in FIG. 2, the information providing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0035] The communication unit 11 transmits and receives information to and from each server or terminal 30 that provides a data source via the network.

[0036] 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. Various programs and various data are stored in the storage unit 12. The storage unit 12 has user information 121, standard model information 122, advanced model information 123, and real-time model information 124.

[0037] The user information 121 is information on the plan to which each user subscribes. For example, the user information 121 is information in which the user ID is associated with a premium plan or a freemium plan.

[0038] Standard model information 122, advanced model information 123, and real-time model information 124 are information such as parameters for constructing a standard model, an advanced model, and a real-time model, respectively. The parameters for constructing a model are, for example, weights and biases of a neural network. In training a model, these parameters are updated.

[0039] 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 131, an update unit 132, a determination unit 133, a generation unit 134, and a provision unit 135.

[0040] The acquisition unit 131 acquires a data source from a data source provider. The acquisition unit 131 accumulates the acquired data source in the storage unit 12. The acquisition unit 131 also continuously acquires the data source asynchronously with the operation of other processing units. That is, the acquisition unit 131 continues to acquire the data source asynchronously with processing such as training a model and generating and providing an answer.

[0041] The amount of data accumulated in the storage unit 12 by the acquisition unit 131 changes over time as shown in Fig. 3. Fig. 3 is a diagram for explaining the change in the amount of data.

[0042] The horizontal axis in Fig. 3 is time (hours). The vertical axis in Fig. 3 is the amount of data. The amount of data at the current time t2 is v2. The amount of data at time t1, which is a period T in the past from time t2, is v1. Also, v1 is smaller than v2.

[0043] In addition, the advanced model is trained at time t2, and the time when an answer is generated using the trained advanced model is t2+Δt. Since the acquisition unit 131 continues to acquire data, the amount of data increases by Δv during the period Δt.

[0044] The update unit 132 updates the parameters of the model through training. The update unit 132 may regenerate the model at each training timing, or may reflect a data source of the difference from the previous training in the model.

[0045] The determination unit 133 determines the plan of the user by referring to the user information 121. The determination unit 133 determines whether the user has subscribed to a premium plan or a freemium plan.

[0046] The generator 134 inputs a prompt to the model and generates an answer. The generator 134 generates an answer to the prompt input by the user using one of a plurality of language models provided by different data sources used in training. For example, the generator 134 generates an answer using one of a standard model and an advanced model.

[0047] The providing unit 135 provides the answer generated by the generating unit 134 to the user together with information indicating the data source provider used in training the language model used to generate the answer. For example, the providing unit 135 causes the terminal 30 to display an information providing screen 500. FIGS. 4, 5, and 6 are diagrams showing examples of the information providing screen 500.

[0048] Fig. 4 shows an information provision screen 500 in the case where the user subscribes to a freemium plan. As shown in Fig. 4, the providing unit 135 displays the data source provider in an area 501 of the information provision screen 500. Fig. 4 shows that the data source providers are "C News" and "D Sports Breaking News".

[0049] The name of the company that provided the data source may be displayed in area 501, or the name of the content (such as a news program, newspaper, book, website, or service) provided by the company may be displayed. The name of the company that provided the data source is an example of information indicating the provider of the data source used to train the language model used to generate the answer.

[0050] The providing unit 135 displays the prompt input by the user and the answer provided by the information providing device 10 by using a chat UI. The user's plan and the chat UI are displayed in an area 502. An area 503 is an area for the user to input a prompt.

[0051] FIG. 4 shows that the user's plan is "Freemium." FIG. 4 also shows that the prompt entered by the user is "What about electric cars?". FIG. 4 also shows that the answer provided by the information providing device 10 is "The EU has set a goal of transitioning to 100% electric cars by 2035."

[0052] Fig. 5 shows an information provision screen 500 when the user subscribes to a premium plan. Fig. 5 shows that the user's plan is "Premium". Fig. 5 shows that the data source providers are "A Keizai Shimbun", "B Journal", "C News", and "D Sports Breaking News".

[0053] In this way, by showing the data source providers to the user, the user can understand the reliability of the information provided. For example, if a company that the user strongly trusts is included in the data source providers, the user can assume that the answer is highly reliable. Also, by displaying many data source providers, the user can assume that the answer is highly reliable.

[0054] 5 shows that the prompt entered by the user is "What about electric cars?". Also, FIG. 5 shows that the answer provided by the information providing device 10 is "The EU has set a goal of shifting to 100% electric cars by 2035, but recently there has been a movement to reconsider that goal."

[0055] In this way, even if the prompt is the same, the answers are different between the freemium plan (FIG. 4) and the premium plan (FIG. 5). In this way, when the fee plan associated with the user is a premium plan that is more expensive than the freemium plan, the generation unit 134 generates an answer using the advanced model, and when the fee plan associated with the user is a freemium plan that is less expensive than the premium plan, the generation unit 134 generates an answer using the standard model that is trained using data sources from fewer data source providers than the advanced model.

[0056] More specifically, when the fee plan associated with the user is a premium plan, the generation unit 134 generates an answer using an advanced model trained with data sources acquired up to a first time (e.g., t2 in FIG. 3), and when the fee plan associated with the user is a freemium plan, the generation unit 134 generates an answer using a standard model trained with data sources acquired up to a second time (e.g., t1 in FIG. 3) that is a certain period of time (e.g., T in FIG. 3) in the past than the first time.

[0057] Further, an additional answer generated by the real-time model will be described with reference to FIG. 6. FIG. 6 shows that the user's plan is "Premium". FIG. 6 also shows that the prompt entered by the user is "How is the pro baseball game going for Team X?". FIG. 6 also shows that the answer is "Current situation. [Top of the 5th inning] Team X 1-2 Team Y".

[0058] The above answer was given at "16:05:33". After that, at "16:05:35", the information providing device 10 provides an additional answer, "Team X turns the game around with a home run! [Top of the 5th inning] Team X 3-2 Team Y". This indicates that the information providing device 10 updated the real-time model and generated an answer during the two seconds between "16:05:33" and "16:05:35".

[0059] FIG. 6 also suggests that between “16:05:33” and “16:05:35”, the acquisition unit 131 acquired a data source indicating that in a professional baseball game, Team X won the game against Team Y with a home run.

[0060] In this manner, the update unit 132 trains and updates the language model using a data source acquired during the period from when the generation unit 134 starts generating a first answer using the language model (advanced model) until the first answer generated by the generation unit 134 is presented. The generation unit 134 generates a second answer to the prompt using the language model (real-time model) updated by the update unit 132. The provision unit 135 provides the second answer to the user.

[0061] This enables tuning of the model in real time, making it possible to provide users with more accurate information.

[0062] Furthermore, the update unit 132 may select the data source to be used for training in accordance with the contents of the prompt.

[0063] The flow of the pre-training process will be described with reference to Fig. 7. Fig. 7 is a flowchart illustrating the flow of the pre-training process.

[0064] 7, the information providing device 10 continuously acquires data sources (step S101). Next, the information providing device 10 determines whether it is time to generate a model (step S102).

[0065] If it is not the model generation timing (step S102, No), the information providing device 10 returns to step S101 and continues to acquire data sources. On the other hand, if it is the model generation timing (step S102, Yes), the information providing device 10 proceeds to step S103.

[0066] The information providing device 10 trains the standard model using the data source of the first data source provider (step S103). For example, the information providing device 10 trains the standard model using the past data source of the first data source provider.

[0067] In addition, the information providing device 10 trains the advanced model using the data source of the second data source provider (step S104). For example, the information providing device 10 trains the advanced model using the data source of the second data source provider up to the present.

[0068] The flow of the information provision process will be described with reference to Fig. 8. Fig. 8 is a flowchart illustrating the flow of the information provision process. The information provision device 10 can execute the pre-training process and the information provision process in parallel.

[0069] 8, the information providing device 10 continuously acquires a data source (step S201). The information providing device 10 determines whether or not there is an inquiry from the user (step S202).

[0070] If there is no inquiry from the user (step S202, No), the information providing device 10 returns to step S201 and continues to acquire data sources. On the other hand, if there is an inquiry from the user (step S202, Yes), the information providing device 10 determines the user's plan (step S203).

[0071] If the user's plan is a freemium plan (step S203, freemium), the information providing device 10 proceeds to step S204. On the other hand, if the user's plan is a premium plan (step S203, premium), the information providing device 10 proceeds to step S206.

[0072] In step S204, the information providing device 10 inputs the inquiry content into the standard model and generates a response, and then provides the generated response to the user (step S205).

[0073] In step S206, the information providing device 10 inputs the inquiry content to the advanced model and generates a response, and then provides the generated response to the user (step S207).

[0074] Furthermore, the information providing device 10 updates the advanced model using the latest data source (step S208). The information providing device 10 inputs the inquiry content into the updated advanced model (real-time model) and generates a response (step S209). The information providing device 10 provides the generated response to the user (step S210).

[0075] According to this embodiment, by partnering with companies that are generally recognized as reputable companies and using such companies as data source providers, it is possible to increase the reliability of a service that provides answers using a language model.

[0076] Furthermore, according to this embodiment, general answers can be provided to individual free members through a freemium plan, and highly accurate answers can be provided to individual paid members, companies, government and other public institutions through a premium plan.

[0077] In addition, when the user's plan is a freemium plan, the information providing device 10 may display a data source provider that is the second data source provider and is not the first data source provider. In other words, when the fee plan is a freemium plan, the information providing device 10 may notify the user of the second data source provider that is used in training the advanced model and the first data source provider that is not used in training the standard model.

[0078] For example, when the data source providers of the data sources used in training the standard model are "C News" and "D Sports Flash", the data source providers of the data sources used in training the advanced model are "A Economic Newspaper", "B Journal", "C News", and "D Sports Flash", and the user's plan is a freemium plan, the data source providers are displayed as shown in Fig. 9. Fig. 9 is a diagram showing an example of an information provision screen 500.

[0079] In Figure 9, "A Keizai Shimbun," "B Journal," "C News," and "D Sports News" are displayed as data source providers, but "A Keizai Shimbun" and "B Journal," which are data source providers for data sources that are not used in training for the standard plan, are displayed separately from "C News" and "D Sports News."

[0080] For example, "A Keizai Shimbun" and "B Journal" are crossed out to indicate that they are not used as data source providers. Note that "A Keizai Shimbun" and "B Journal" may be displayed in a lighter color than "C News" and "D Sports Breaking News", as long as they are distinguishable from "C News" and "D Sports Breaking News".

[0081] In this way, the information providing device 10 can generate interest in the answers of the premium plan in the user by displaying the data source provider of the data source that is not used in training the standard model of the freemium plan. Therefore, the information providing device 10 can encourage the user to subscribe to the premium plan.

[0082] The information providing device 10 includes a generating unit 134 and a providing unit 135. The generating unit 134 generates an answer to a prompt input by a user using either a standard model or an advanced model, the data source providers used in training being different from each other. The providing unit 135 provides the answer generated by the generating unit 134 to the user together with the training of the standard model used to generate the answer and the data source provider used in training the advanced model.

[0083] This allows the information providing device 10 to display an answer generated using a standard model or an advanced model, which are different language models, together with the data source provider. This allows the user to check the answer together with the data source provider used to train the model. This allows the information providing device 10 to improve satisfaction with the answer.

[0084] If the fee plan associated with the user is a freemium plan, the generation unit 134 generates an answer using a standard model, and if the fee plan associated with the user is a premium plan, the generation unit 134 generates an answer using an advanced model that has more data source providers for the data sources used in training than the standard model.

[0085] As a result, when the fee plan is the premium plan, the information providing device 10 can generate an answer using an advanced model that uses more data sources from more data source providers for training than the freemium plan. Therefore, the information providing device 10 can provide a more detailed answer to a user with a premium plan.

[0086] If the fee plan is a freemium plan, the provider 135 notifies the user of the data source providers of the data sources used in training the advanced model and the data source providers of the data sources not used in training the standard model.

[0087] In this way, the information providing device 10 can inform the user of the existence of a data source provider that has not been used in training the standard model in response to a response in the freemium plan. Therefore, the information providing device 10 can encourage the user to subscribe to the premium plan.

[0088] 10 is a diagram illustrating an example of a computer hardware configuration that functions as the information providing device 10. 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 associated with the device according to the present embodiment or one or more "parts" thereof, and / or cause the computer 1200 to execute a process according to the present embodiment or steps of the process. 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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]

[0104] 10 Information provision device 11 Communications Department 12 Storage section 13 Control section 121 User Information 122 Standard Model Information 123 Advanced Model Information 124 Real-time model information 131 Acquisition Department 132 Update Department 133 Judgment section 134 Generation part 135 Provision Department 500 Information provision screen 501, 502, 503 areas

Claims

1. A generation unit that generates an answer to a prompt input by a user using one of a plurality of language models each of which is trained using a data source provided by different sources; a providing unit that provides the answer generated by the generating unit to the user together with information indicating a provider of a data source used in training the language model used to generate the answer; An information providing device having the above configuration.

2. The generation unit generates an answer using a first language model when a fee plan associated with the user is a first plan, and generates an answer using a second language model that is trained using more data sources than the first language model when a fee plan associated with the user is a second plan that is more expensive than the first plan.

2. The information providing device according to claim 1.

3. 3. The information providing device of claim 2, wherein when the fee plan is the first plan, the providing unit notifies the user of a provider of a data source that was used in training the second language model and was not used in training the first language model.

4. An information providing method executed by an information providing device, comprising: A generating step of generating an answer to a prompt input by a user using one of a plurality of language models each having a different data source used for training; a providing step of providing the answer generated by the generating step to the user together with information indicating the provider of a data source used in training the language model used to generate the answer; Methods of providing information, including:

5. A generating step of generating an answer to a prompt input by a user using one of a plurality of language models each having a different data source used for training; a providing step of providing the answer generated by the generating step to the user together with information indicating a provider of a data source used in training the language model used to generate the answer; An information providing program that causes a computer to execute the above.

Images