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

Abstract

To learn a model with high reliability while reducing the amount of learning.SOLUTION: An information providing device according to an embodiment comprises: a collection unit which collects data sources provided from a provision source meeting conditions on reliability; a determination unit which determines the reliability of the collected data sources; and a generation unit which generates a language model generated by learning data sources where reliability meets prescribed conditions and for generating an answer to the prompt input by a user.SELECTED DRAWING: Figure 2

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] BACKGROUND ART Conventionally, a system is known 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] Furthermore, when training a generative model, training may be performed using the latest data source and training using a data source from a time before a certain point in the past. However, when training is performed using the latest data source, if the amount of training is large, there is a risk that the provision of an answer to a user who inputs a prompt will be delayed.

[0005] The present invention has been made in view of the above, and has as its object to learn a highly reliable model while reducing the amount of learning. [Means for solving the problem]

[0006] An information providing device according to one aspect of the embodiment includes a collection unit that collects data sources provided by sources that satisfy reliability conditions, a determination unit that determines the reliability of the collected data sources, and a generation unit that generates a language model that generates an answer to a prompt entered by a user, the language model being generated by learning the data sources whose reliability satisfies predetermined conditions. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to learn a highly reliable model while reducing the amount of learning. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overview of an information providing device according to an embodiment. [Figure 2] FIG. 2 is a functional block diagram illustrating an example of the configuration of the information providing device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating changes in the amount of data. [Figure 4] FIG. 4 is a flowchart illustrating the flow of the reliability determination process. [Figure 5] FIG. 5 is a flowchart illustrating the flow of the pre-training process. [Figure 6] FIG. 6 is a flowchart illustrating the flow of the information provision process. [Figure 7] FIG. 7 is a diagram illustrating an example of a computer hardware configuration that functions as an information providing device. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0011] As shown in FIG. 1, the information providing system 1 includes an information providing device 10, a data source provider 20, and a response destination 30. The data source provider 20 is embodied as a server 20-1 for distributing information, a user terminal 20-2 owned by a user, a vehicle 20-3 with an autonomous driving function, etc. The server 20-1 is a server managed by, for example, a newspaper company, a news agency, a broadcasting company, a publisher, an online news provider, etc. The server 20-1 distributes information via a website or a social networking service (SNS) on the Internet.

[0012] The answer destination 30 is a destination to which an answer to a user's question is provided using a language model included in the information providing device 10. The answer destination 30 is actually a user terminal 30-1, a vehicle 30-2 with an automatic driving function, or the like.

[0013] 1, the information providing device 10 acquires information about the provider from the data source provider 20 (step S1). The information about the provider includes attribute information about the provider (business content, business scale, number of employees, number of registered members), and information about the area where the business is being conducted.

[0014] Next, the information providing device 10 determines whether the destination satisfies the reliability condition based on the information about the source (step S2). For example, the information providing device 10 determines that a source whose business involves news distribution (such as a newspaper company, a news agency, a broadcasting company, a publisher, or an online news provider) satisfies the reliability condition. In other words, the information providing device 10 determines that the data source of news articles provided by a source whose business involves news distribution is highly reliable and therefore satisfies the reliability condition. Furthermore, the information providing device 10 determines that a source whose business scale is equal to or larger than a certain level satisfies the reliability condition. The business scale may be, for example, the number of news distributions (number of copies published for a newspaper company, number of users to whom the news agency has distributed, viewer ratings for a broadcasting company, number of copies published for a publisher, number of distributions or number of registered users for an online news provider, etc.). In other words, the information providing device 10 determines that a source whose news articles are distributed to a certain number of users satisfies the reliability condition.

[0015] Furthermore, when the data source provider 20 is a device such as a user terminal 20-2 or a vehicle 20-3, the information providing device 10 determines whether the manufacturer of the device satisfies a condition regarding reliability. For example, the information providing device 10 determines that a manufacturer with sales revenue equal to or greater than a certain amount satisfies the condition regarding reliability.

[0016] Next, the information providing device 10 permits communication connection to the data source providers 20 that satisfy the reliability conditions, and collects data sources from the data source providers 20 (step S3). The information providing device 10 and the data source providers 20 are connected for communication via a VPN (Virtual Private Network).

[0017] The data source is data in the form of text, audio, image, etc. distributed by the server 20-1 of the data source provider 20. The data source is also user posted content (text, audio, image, etc.) provided by the user terminal 20-2. The data source is past travel routes provided by the vehicle 20-3, the congestion status of roads and sidewalks while traveling, the travel time required to reach the destination, the behavior of the vehicle 20-3 when traveling to the destination (accelerator, brake, steering, etc.), etc.

[0018] The information providing device 10 determines the reliability of the collected data source (step S4). For example, the information providing device 10 determines the reliability based on the information of the provider. Specifically, the information providing device 10 determines the reliability based on the attribute information of the provider and the type of the data source. For example, if an economics-related data source is provided by a provider that mainly disseminates economics-related news, the information providing device 10 determines the reliability to be high, and if a data source other than economics-related is provided, the information providing device 10 determines the reliability to be low. Note that the reliability is not limited to two values, high / low, but may be expressed as a score out of 10. Furthermore, the information providing device 10 may determine the reliability of a data source provided by a provider with a business scale of a certain level or more as high. The business scale may be, for example, the number of news distributions (number of copies published for a newspaper company, number of users distributed for a news agency, viewer rating for a broadcaster, number of copies published for a publisher, number of distributions or number of registered users for an online news provider, etc.). Furthermore, the information providing device 10 may determine the reliability of the currently provided data source based on the reliability of data sources previously provided by the provider. Specifically, if the reliability of all data sources previously provided by the provider is high, the information providing device 10 determines that the reliability of the currently provided data source is high. Furthermore, if the reliability of all data sources in a specific field among the data sources previously provided by the provider is high, the information providing device 10 determines that the reliability of the currently provided data source is high if the data source is in the specific field.

[0019] The information providing device 10 learns a model 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) that uses a neural network.

[0020] In this embodiment, the language model generates a text response to a query text (hereinafter referred to as a prompt) entered by a user. The model is pre-trained using a data source. The model may be trained using known machine learning techniques.

[0021] This allows the model to generate answers based on the data source. For example, if the prompt includes the keyword "electric vehicle," the model can generate answers based on news articles related to that keyword. In other words, the content of the news articles influences the answer generated by the model.

[0022] 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.

[0023] The information providing device 10 has two models that use different data sources for learning: a standard model and an advanced model.

[0024] The information providing device 10 learns two language models based on the data sources (step S5). Specifically, the information providing device 10 learns a standard model based on past data sources, and learns an advanced model based on current data sources.

[0025] Here, the past data source is a data source acquired up to a certain time period prior to the timing of model training. For example, if the certain period is two years, and training is performed at "2023 / 6 / 22 16:05", the past data source is a data source acquired from the start of data source acquisition up to "2021 / 6 / 22 16:05".

[0026] On the other hand, the current data source is the data source acquired up until the time when the model training is performed. For example, if training is performed at "2023 / 6 / 22 16:05", the current data source is the data source acquired from the start of data source acquisition up to "2023 / 6 / 22 16:05".

[0027] In other words, the information providing device 10 generates a standard model that learns from past data sources acquired up to a point in time going back a predetermined period, and an advanced model that learns from past data sources acquired up to the present, including the predetermined period.

[0028] The timing at which the model is learned may be every second, or every shorter time (for example, every nanosecond).

[0029] Furthermore, when training the advanced model, the information providing device 10 uses data sources acquired during a predetermined period whose reliability determined in step S4 satisfies a predetermined condition. Specifically, the information providing device 10 trains the advanced model using highly reliable data sources. This allows for training of a highly reliable advanced model while reducing the amount of training.

[0030] Here, the information providing device 10 receives a prompt from the user as an input to the language model (step S6), and then generates an answer to the prompt using a model according to the user's plan (step S7).

[0031] The prompt from the user is transmitted to the information providing device 10 via the answer providing destination 30. The information providing device 10 also transmits the answer to the answer providing destination 30.

[0032] The information providing device 10 provides answers as a service. The service is assumed to have a higher-level premium plan and a lower-level freemium plan. The premium plan is a subscription plan that incurs a fixed fee for a certain period (e.g., annually or monthly), or a pay-as-you-go plan where 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.

[0033] The information providing device 10 differentiates the service quality for each plan by using different data to train the model. That is, if the user subscribes to a premium plan, the information providing device 10 generates a response using an advanced model. On the other hand, if the user subscribes to a freemium plan, the information providing device 10 generates a response using a standard model.

[0034] The information providing device 10 provides the generated answer to the user (step S8). The information providing device 10 may accept the prompt and provide the answer via a chat-style user interface. Furthermore, when the answer destination 30 is the vehicle 30-2, the information providing device 10 causes the answer to be displayed on a display (e.g., a navigation device) mounted on the vehicle 30-2, for example. Alternatively, when the prompt is a request for autonomous driving to the destination, the information providing device 10 controls a control device of the vehicle 30-2 to perform autonomous driving.

[0035] Additionally, if the user subscribes to a premium plan, the information providing device 10 may update the advanced model based on the latest data sources and generate additional answers. Such updated advanced models are called real-time models. The information providing device 10 may provide additional answers generated using the real-time models.

[0036] The information providing device 10 continuously acquires data sources and updates the language model during the period from when the information providing device 10 generates an answer to when the generated answer is provided. By using a real-time model, the information providing device 10 can generate an answer that reflects the difference that occurs during this period.

[0037] Next, when the information providing device 10 provides an answer related to the data source to a user, it provides a reward to the data source provider 20 of the data source (step S9). For example, the information providing device 10 determines the content of the reward to be provided depending on the number of times an answer related to the data source has been provided (or the number of users). Furthermore, the information providing device 10 may provide different rewards for answers provided via the standard model and the advanced model. For example, the information providing device 10 provides a higher reward for answers provided via the advanced model when the answer related to the data source is provided than for answers provided via the standard model.

[0038] Furthermore, the information providing device 10 provides a reward according to the reliability determined in step S4. For example, the higher the reliability, the larger the reward provided by the information providing device 10. Furthermore, the information providing device 10 may determine the reward to be provided based on the reliability of multiple data sources previously provided to the user. Specifically, the more highly reliable data sources provided within a predetermined period in the past, the larger the reward provided by the information providing device 10. In this way, the information providing device 10 according to the embodiment can provide an appropriate reward to the provider by providing the provider with a reward according to the reliability.

[0039] In this way, the information providing device 10 can collect data sources only from data source providers 20 that meet the reliability conditions, thereby avoiding the inclusion of low-reliability data sources in the learning of the language model, thereby increasing the reliability of the information provided.

[0040] Furthermore, in the information provision system 1, the information provision device 10 and the data source provider 20 (the server 20-1, the user terminal 20-2, and the vehicle 20-3) incorporate semiconductor chips manufactured by the same manufacturer. These semiconductor chips may each perform machine learning or deep learning.

[0041] Furthermore, the semiconductor chips used in the information providing device 10 and the data source provider 20 are chips of a size appropriate for their respective housings. For example, assuming that the chip size of the information providing device 10 is XL, the server 20-1 and the vehicle 20-3 are L-sized, and the user terminal 20-2 is S- or M-sized. For the data source provider 20, which has an even smaller housing size than the user terminal 20-2, the SS-sized chip is used and incorporated into a system on a chip (SoC) to form a single chip. The XL-sized chip has 200 tiles, the L-sized chip has 50 tiles, the M-sized chip has 20 tiles, the S-sized chip has 10 tiles, and the SS-sized chip has 2 tiles. However, the number of tiles for each size is merely an example and is not limited to the above. If accessories such as a camera or microphone are to be attached to the user terminal 20-2, a dedicated chip for the accessories, separate from the semiconductor chip, may be set in an empty space near the semiconductor chip in the SoC.

[0042] In this way, by using semiconductor chips from the same manufacturer in the information providing device 10 and the data source provider 20, a closed system can be established between the information providing device 10 and the data source provider 20, and therefore a secure state can be maintained between the information providing device 10 and the data source provider 20. In other words, hacking, virus infection, and deep fakes can be avoided with high accuracy between the information providing device 10 and the data source provider 20, and privacy between the information providing device 10 and the data source provider 20 can be ensured.

[0043] 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.

[0044] As shown in FIG. 2, the information providing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0045] The communication unit 11 transmits and receives information to and from the data source provider 20 or the response destination 30 via the network.

[0046] 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), or an optical disk. 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.

[0047] The user information 121 is information about the plan that each user subscribes to. For example, the user information 121 is information that associates the user ID with a premium plan or a freemium plan.

[0048] 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. Parameters for constructing a model include, for example, weights and biases of a neural network. These parameters are updated during model training.

[0049] The control unit 13 is a controller and includes, for example, a microcomputer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM, input / output ports, etc., 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 determination unit 32, a collection unit 33, a generation unit 34, a provision unit 35, and a supply unit 36.

[0050] The acquisition unit 31 acquires information about the provider from the data source provider 20. The information about the provider is attribute information of the recipient (business content, business scale, number of employees, number of registered members), information about the area where the business is being developed, etc.

[0051] The determination unit 32 determines whether the destination satisfies the reliability condition based on the information about the source. For example, the determination unit 32 determines that a source whose business involves news distribution (such as a newspaper company, a news agency, a broadcasting company, a publisher, or an online news provider) satisfies the reliability condition. In other words, the determination unit 32 determines that the data source of news articles provided by a source whose business involves news distribution is highly reliable and therefore satisfies the reliability condition. The determination unit 32 also determines that a source whose business scale is equal to or greater than a certain level satisfies the reliability condition. The business scale may be, for example, the number of news distributions (number of copies published for a newspaper company, number of users to whom the news agency has distributed, viewer ratings for a broadcasting company, number of copies published for a publisher, number of distributions or number of registered users for an online news provider, etc.). In other words, the determination unit 32 determines that a source whose news articles are distributed to a certain number of users satisfies the reliability condition.

[0052] Furthermore, when the data source provider 20 is a device such as a user terminal 20-2 or a vehicle 20-3, the determination unit 32 determines whether the manufacturer of the device satisfies the conditions regarding reliability. For example, the determination unit 32 determines that a manufacturer with sales revenue equal to or greater than a certain amount satisfies the conditions regarding reliability.

[0053] The determination unit 32 also determines the reliability of the collected data source. For example, the determination unit 32 determines the reliability based on information about the provider. Specifically, the determination unit 32 determines the reliability based on attribute information about the provider and the type of data source. For example, if an economics-related data source is provided by a provider that mainly disseminates economic news, the determination unit 32 determines the reliability to be high, and if a data source other than economics-related data is provided, the determination unit 32 determines the reliability to be low. Note that the reliability is not limited to two values, high / low, but may be expressed as a score on a scale of 1 to 10. The determination unit 32 may also determine the reliability of a data source provided by a provider with a certain or larger business scale as high. The business scale may be, for example, the number of news distributions (number of copies published for a newspaper company, number of users distributed for a news agency, viewer rating for a broadcaster, number of copies published for a publisher, number of distributions or number of registered users for an online news provider, etc.). Furthermore, the determination unit 32 may determine the reliability of the currently provided data source based on the reliability of data sources previously provided by the provider. Specifically, if the reliability of all data sources previously provided by the provider is high, the determination unit 32 determines that the reliability of the currently provided data source is high. Furthermore, if the reliability of all data sources in a specific field among the data sources previously provided by the provider is high, the determination unit 32 determines that the reliability of the currently provided data source is high if the data source is in the specific field.

[0054] The collection unit 33 collects data sources from the data source providers 20 that have been determined by the determination unit 32 to satisfy the reliability conditions. The collection unit 33 stores the collected data sources in the storage unit 12. The collection unit 33 also continuously collects data sources asynchronously with the operation of other processing units. That is, the collection unit 33 continues to collect data sources asynchronously with processes such as model training and answer generation and provision.

[0055] The amount of data accumulated in the storage unit 12 by the collection unit 33 changes over time as shown in Fig. 3. Fig. 3 is a diagram for explaining the change in the amount of data.

[0056] The horizontal axis in Figure 3 is time (hours). The vertical axis in Figure 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.

[0057] Furthermore, the advanced model is trained at time t2, and the time when an answer is generated using the trained advanced model is t2 + Δt. Because the collection unit 33 continues to collect data, the amount of data increases by Δv during the period Δt.

[0058] The generation unit 34 generates language models. Specifically, the generation unit 34 generates a standard model and an advanced model. Specifically, the generation unit 34 trains two language models based on data sources. Specifically, the generation unit 34 trains the standard model based on past data sources. Also, the generation unit 34 trains the advanced model based on current data sources.

[0059] Furthermore, the generation unit 34 updates the parameters of the model through learning. The generation unit 34 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.

[0060] Furthermore, the generation unit 34 determines the reliability of the data sources collected from the providers, and determines whether or not to use the data sources for training the language model based on the reliability. For example, the generation unit 34 analyzes the content of the data sources (text analysis, voice analysis, image analysis), and if there is a possibility that the content of the data sources is false, prohibits the use of the data sources for training the language model.

[0061] Furthermore, when training the advanced model, the generation unit 34 trains the advanced model using data sources acquired during a predetermined period whose reliability determined in step S4 satisfies a predetermined condition. Specifically, the generation unit 34 trains the advanced model using data sources with high reliability.

[0062] The providing unit 35 uses the generated language model to generate and provide a response to a prompt received from the user.

[0063] The provision unit 35 determines the plan of the user by referring to the user information 121. The provision unit 35 determines whether the user has subscribed to a premium plan or a freemium plan.

[0064] The providing unit 35 inputs a prompt into a language model and generates an answer. The providing unit 35 generates an answer to the prompt input by the user using one of multiple language models that differ from each other in the amount of data source used in training. For example, the providing unit 35 generates an answer using one of a standard model and an advanced model.

[0065] The providing unit 35 provides the answer generated by the language model to the user along with information indicating the provider of the data source used to train the language model used to generate the answer. For example, the providing unit 35 displays an information providing screen on the user terminal. For example, the providing unit 35 may accept the prompt and provide the answer via a chat-style user interface. Furthermore, when the answer destination 30 is the vehicle 30-2, the providing unit 35 displays the answer on a display (e.g., a navigation device) mounted on the vehicle 30-2, for example. Alternatively, when the prompt is a request for autonomous driving to the destination, the providing unit 35 controls a control device of the vehicle 30-2 to perform autonomous driving.

[0066] When an answer related to a data source is provided to a user, the payment unit 36 ​​pays a reward to the data source provider 20 of the data source. For example, the payment unit 36 ​​determines the content of the reward to be paid depending on the number of times an answer related to the data source has been provided (or the number of users). Furthermore, the payment unit 36 ​​may provide different rewards for answers provided via the standard model and those provided via the advanced model. For example, the payment unit 36 ​​may provide a higher reward for answers provided via the advanced model when related to the data source is provided than for answers provided via the standard model.

[0067] Furthermore, the payment unit 36 ​​pays a reward according to the reliability determined in step S4. For example, the higher the reliability, the larger the reward paid by the payment unit 36. Furthermore, the payment unit 36 ​​may determine the reward to be paid based on the reliability of multiple data sources provided to the user in the past. Specifically, the more highly reliable data sources are provided within a predetermined period in the past, the larger the reward paid by the payment unit 36.

[0068] The flow of the reliability determination process will be described with reference to Fig. 4. Fig. 4 is a flowchart illustrating the flow of the reliability determination process.

[0069] As shown in FIG. 4, the information providing device 10 acquires information about the provider from the data source provider 20 (step S101).

[0070] Next, the information providing device 10 determines whether the reliability condition is met based on the information about the provider (step S102).

[0071] If the information providing device 10 satisfies the reliability conditions (step S102: Yes), it adopts the data source as a provider (step S103) and ends the process. On the other hand, if the information providing device 10 does not satisfy the reliability conditions (step S102: No), it does not adopt the data source as a provider and ends the process.

[0072] The flow of the pre-training process will be described with reference to Fig. 5. Fig. 5 is a flowchart illustrating the flow of the pre-training process.

[0073] 5, the information providing device 10 continuously acquires data sources (step S201). Next, the information providing device 10 determines whether it is time to generate a model (step S202).

[0074] If it is not time to generate a model (step S202: No), the information providing device 10 returns to step S201 and continues to acquire data sources. On the other hand, if it is time to generate a model (step S202: Yes), the information providing device 10 proceeds to step S203.

[0075] The information providing device 10 trains the standard model using past data sources for a certain period of time (step S203). The information providing device 10 also trains the advanced model using data sources up to the present (step S204). For example, the information providing device 10 trains the advanced model using data sources up to the present, and trains the standard model using data sources up to two years ago.

[0076] The flow of the information provision process will be described with reference to Fig. 6. Fig. 6 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.

[0077] 6, the information providing device 10 continuously acquires data sources (step S301). The information providing device 10 determines whether or not there is an inquiry from the user (step S302).

[0078] If there is no inquiry from the user (step S302: No), the information providing device 10 returns to step S301 and continues to acquire data sources. On the other hand, if there is an inquiry from the user (step S302: Yes), the information providing device 10 determines the user's plan (step S303).

[0079] If the user's plan is a freemium plan (step S303: freemium), the information providing device 10 proceeds to step S304. On the other hand, if the user's plan is a premium plan (step S303: premium), the information providing device 10 proceeds to step S306.

[0080] In step S304, the information providing device 10 inputs the inquiry content into the standard model and generates an answer. Then, the information providing device 10 provides the generated answer to the user (step S305). Then, the information providing device 10 pays a reward to the provider of the data source related to the answer (step S311), and ends the process.

[0081] In step S306, the information providing device 10 inputs the inquiry content into the advanced model and generates a response, and then provides the generated response to the user (step S307).

[0082] Furthermore, the information providing device 10 updates the advanced model using the latest data source (step S308). The information providing device 10 inputs the inquiry content into the updated advanced model (real-time model) and generates a response (step S309). The information providing device 10 provides the generated response to the user (step S310).

[0083] According to this embodiment, by partnering with companies that are generally recognized as reputable companies and using such companies as providers of data sources, the reliability of the service that provides answers using language models can be increased.

[0084] 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.

[0085] 7 is a diagram schematically illustrating an example of a computer hardware configuration that functions as an information providing device. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or can cause the computer 1200 to perform operations associated with the device according to the present embodiment or one or more "parts," and / or can cause the computer 1200 to perform 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 perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0086] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communications 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, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. 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.

[0087] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller itself, and causes the image data to be displayed on the display device 1218.

[0088] 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.

[0089] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend 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, etc.

[0090] 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, RAM 1214, or 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 causes cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

[0091] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into 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.

[0092] 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 may 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.

[0093] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on 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 sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on 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 multiple 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.

[0094] The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0095] The blocks in the flowcharts and block diagrams in the present embodiments 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, including integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0096] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including 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, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, etc.

[0097] 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.

[0098] Computer-readable instructions may be provided locally or over a wide area network (WAN) such as a local area network (LAN), the Internet, etc. to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or programmable circuitry, such that the processor or programmable circuitry executes 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.

[0099] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0100] It should be noted that the execution order 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 that the processes can be performed 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 described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0101] 10 Information provision device 11 Communications Department 12 Storage section 13 Control Unit 31 Acquisition Department 32 Judgment section 33 Collection Department 34 Generation part 35 Provision Department 36 Supply Department 121 User Information 122 Standard Model Information 123 Advanced Model Information 124 Real-time Model Information

Claims

1. A collection unit that collects data sources provided from providers that satisfy reliability conditions; A determination unit that determines the reliability of the collected data source; a generation unit for generating a language model that generates an answer to a prompt input by a user, the language model being generated by learning the data source whose reliability satisfies a predetermined condition; An information providing device having the above configuration.

2. The generation unit is Generate a standard model that learns the past data sources acquired up to a point going back a predetermined period of time, and an advanced model that learns the past data sources acquired up to the present, including the predetermined period of time; When training the advanced model, training is performed using the data sources acquired during the predetermined period whose reliability satisfies a predetermined condition.

2. The information providing device according to claim 1.

3. The determination unit is The reliability is determined based on the information of the provider.

2. The information providing device according to claim 1.

4. The determination unit is The reliability is determined based on attribute information of the provider and a type of the data source.

4. The information providing device according to claim 3.

5. The determination unit is The reliability of the data source provided this time is determined based on the reliability of the data source provided in the past by the provider.

2. The information providing device according to claim 1.

6. An information providing method executed by an information providing device, comprising: A collection step of collecting data sources provided by providers that satisfy reliability conditions; A determination step of determining the reliability of the collected data sources; a generation step of generating a language model generated by learning the data source whose reliability satisfies a predetermined condition, the language model generating an answer to a prompt input by a user; Methods of providing information, including:

7. A collection step of collecting data sources provided by providers that satisfy reliability criteria; a determining step of determining the reliability of the collected data sources; a generating step of generating a language model that generates an answer to a prompt input by a user, the language model being generated by learning the data source whose reliability satisfies a predetermined condition; An information providing program that causes a computer to execute the above.

Images