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

Abstract

To improve usability of a data analysis tool.SOLUTION: An information providing device 10 includes an interface unit 11, a prompt generating unit 13, a text generating unit 16, and a level selecting unit 17. The level selecting unit 17 selects a level related to data analysis of a user. The prompt generating unit 13 generates a prompt for causing a language model to generate text according to the level for supporting the use of a data analysis tool, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selecting unit 17. The text generating unit 16 generates the text by inputting the prompt generated by the prompt generating unit 13 into the language model. The interface unit 11 causes the terminal device to display the text generated by the text generating unit 16.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information providing device, an information providing method, and an information providing program. [Background technology]

[0002] In recent years, so-called no-code data analysis tools (e.g., applications) have been provided (see, for example, Patent Document 1 or Non-Patent Document 1). No-code data analysis tools are characterized by not requiring programming skills and being intuitively usable even by beginners. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-27964 A [Non-patent literature]

[0004] [Non-Patent Document 1] “No-code AI development tool Node-AI”, [online], [Retrieved July 21, 2023], Internet<https: / / sdpf.ntt.com / services / nodeai / > Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional data analysis tools can be difficult for users to use.

[0006] For example, even with no-code data analysis tools, users need to understand the concepts and methods of data analysis to use them effectively. When using a tool, users may conduct research on the Internet or books, or through question and answer sessions with experts, in order to understand the concepts and methods of data analysis. However, if the results of the research do not match the user's skill level, the research may be meaningless.

[0007] In particular, beginners in data analysis have difficulty distinguishing whether the results of their own research on analytical methods, etc. are basic or applied. For this reason, it is easy to run into the problem of not knowing whether the results of the research really match your own skill level.

[0008] The same can be said about how to use analytical tools; for example, a beginner in data analysis can be confused when taught how to set up tools for advanced users. [Means for solving the problem]

[0009] In order to solve the above-mentioned problems and achieve the objective, the information providing device is characterized by having a level selection unit that selects a user's level for data analysis, a prompt generation unit that generates a prompt for causing a language model to generate a sentence corresponding to the level, which is a sentence to assist in using the data analysis tool, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selection unit, a sentence generation unit that generates a sentence by inputting the prompt generated by the prompt generation unit into the language model, and a display control unit that displays the sentence generated by the sentence generation unit on the terminal device. Effect of the Invention

[0010] According to the present invention, the ease of use of data analysis tools can be improved. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information providing system according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the screen. [Diagram 3] FIG. 3 is a diagram showing an example of the screen. [Figure 4] FIG. 4 is a diagram showing an example of the screen. [Diagram 5] FIG. 5 is a diagram showing a modified example of the information providing system according to the first embodiment. [Figure 6] FIG. 6 is a flowchart showing a flow of processing of the information providing system according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of a computer that executes an information provision program. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of an information providing device, an information providing method, and an information providing program according to the present application will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiment described below.

[0013] [First embodiment] [Configuration of the first embodiment] The configuration of the information providing system will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the information providing system according to the first embodiment. As shown in Fig. 1, the information providing system 1 includes an information providing device 10 and a terminal device 20.

[0014] The information providing device 10 is a server connected to a terminal device 20 via a network. The terminal device 20 is a personal computer (PC), a tablet terminal, a smartphone, or the like.

[0015] The information providing device 10 has a function of a data analysis tool such as Node-AI described in Non-Patent Document 1. The information providing device 10 may have a function equivalent to that of the information processing device described in Patent Document 1. For example, a user executes the data analysis tool via the terminal device 20 to generate canvas data.

[0016] Node-AI employs flow-based programming, which allows designing a pipeline for data processing without coding. Node-AI also allows intuitive description of a pipeline for data processing by connecting data to be processed with functions that can execute each process. In this embodiment, a function that executes a specific process on data is referred to as a "card." Data for which a pipeline is described is referred to as "canvas data."

[0017] Furthermore, the information providing device 10 has a function of providing a sentence in a natural language to the user in addition to the function of the data analysis tool. The information providing device 10 supports the user in using the data analysis tool by providing a message.

[0018] The information providing device 10 provides, in the form of text, answers to questions about the user regarding the data analysis tool, hints on how to use the data analysis tool, actions recommended for the user, insights regarding data, indications of user errors, etc. At this time, the information providing device 10 provides text according to the user's level regarding data analysis.

[0019] As shown in FIG. 1, an information providing device 10 includes an interface unit 11, a request processing unit 12, a prompt generating unit 13, a history DB 14, a language model group 15, a sentence generating unit 16, and a level selecting unit 17.

[0020] The interface unit 11 exchanges data with the terminal device 20. For example, the interface unit 11 accepts a request from the terminal device 20. Also, for example, the interface unit 11 causes the terminal device 20 to display a screen.

[0021] The interface unit 11 receives, as a request, the text of an inquiry input by a user or the operation content of a data analysis tool from the terminal device 20. The interface unit 11 passes the received request to the request processing unit 12.

[0022] When a request is an operation of a data analysis tool, the request processing unit 12 obtains a result for the request. The result is canvas data that the data analysis tool returns in response to the operation.

[0023] The request processing unit 12 saves the request and the result in the history DB 14. The request processing unit 12 also passes the request and the result to the prompt generating unit 13 and the level selecting unit 17. If there is no result, the request processing unit 12 saves the request in the history DB 14 and passes the request to the prompt generating unit 13 and the level selecting unit 17.

[0024] The level selection unit 17 selects the user's level regarding data analysis. The level is information that indicates, in stages, the user's amount of knowledge regarding data analysis, proficiency with data analysis tools, etc. Here, the level is represented in two stages, advanced and beginner. However, the number of levels may be three or more.

[0025] The level selection unit 17 selects a level based on an input by a user. In this case, the interface unit 11 accepts the input of the level via the terminal device 20.

[0026] Alternatively, the level selection unit 17 may automatically select a level. For example, the level selection unit 17 selects a level based on the user's past operation details in the data analysis tool and the accuracy of data analysis by a process generated according to the past operation details.

[0027] The prompt generation unit 13 generates a prompt for causing the language model to generate a sentence for supporting the use of the data analysis tool, based on a request (or a request and a result) received from the terminal device 20 on which the data analysis tool is executed. The prompt generation unit 13 passes the generated prompt to the sentence generation unit 16.

[0028] The prompt generation unit 13 generates a prompt to cause the language model to generate a sentence appropriate to the level, which is a sentence to assist in the use of the data analysis tool, based on a request received from the terminal device on which the data analysis tool is executed and the level selected by the level selection unit 17.

[0029] The sentence generation unit 16 generates a sentence by inputting the prompt generated by the prompt generation unit 13 to a language model included in the language model group 15. The sentence generation unit 16 outputs the obtained sentence to the terminal device 20 via the interface unit 11.

[0030] 1, the language model group 15 includes an advanced language model 151 and a beginner language model 152. The advanced language model 151 is a language model that corresponds to an advanced level. The beginner language model 152 is a model that corresponds to a beginner level.

[0031] The sentence generation unit 16 can generate a sentence by inputting a prompt to a language model corresponding to a level selected by the level selection unit 17, among language models corresponding to each of a plurality of levels. The language model to be input may be specified by the prompt.

[0032] Even when the same prompt is input, the advanced language model 151 and the beginner language model 152 output different sentences.

[0033] The level selection unit 17 further selects a role. The prompt generation unit 13 generates a prompt for causing the language model to generate a sentence in a writing style according to the role. For example, the writing style may be either the desu-masu style or the dearu style, whether honorific language is used, whether interjections are used, whether an imperative tone is used, etc.

[0034] A role may be selected by the user via a screen as shown in Fig. 2. Fig. 2 is a diagram showing an example of the screen. The interface unit 11 causes the terminal device 20 to display a role selection screen 54 of Fig. 2. "Instructor", "Secretary", and "University Professor" are examples of roles. The user selects one of the roles displayed on the role selection screen 54. The selected role is notified to the prompt generation unit 13 by the level selection unit 17.

[0035] Here, the language models included in the language model group 15 are large language models (LLMs). The language models may be neural networks. In addition, the language models are, for example, ChatGPT (registered trademark) (Reference URL: https: / / openai.com / blog / chatgpt).

[0036] The language model performs inference based on the input prompt and outputs a natural language sentence obtained through the inference.

[0037] Here, the data analysis tool generates a series of processes (pipeline) for data analysis using a machine learning model in response to user operations. The machine learning model that performs data analysis is called an analysis model. For example, the data analysis tool outputs an executable file that executes a series of processes.

[0038] The process can be divided into three parts: data preprocessing, training an analytical model using the data (updating parameters), and evaluating the trained analytical model.

[0039] The language models may include language models tuned for each of the three processes. For example, the language model group 15 includes a language model tuned for preprocessing, a language model tuned for learning, and a language model tuned for evaluation.

[0040] For example, a language model tuned for preprocessing learns prompts based on operation content that specifies preprocessing of data used for training, and sentence advice from an experienced user for the operation content. A language model tuned for preprocessing can generate sentences that are more appropriate for preprocessing than other language models.

[0041] The process of the data analysis tool is not limited to the above-mentioned division, and may be further divided. The language model group 15 includes language models tuned for each of the divided processes. For example, the language model group 15 may include language models tuned for each of the cards in the data analysis tool.

[0042] Furthermore, the language model group 15 may include language models that are subdivided into processes and correspond to each of a plurality of levels. For example, the language model group 15 includes six language models: a beginner-level language model tuned for preprocessing, a beginner-level language model tuned for learning, a beginner-level language model tuned for evaluation, an advanced-level language model tuned for preprocessing, an advanced-level language model tuned for learning, and an advanced-level language model tuned for evaluation.

[0043] The sentence generator 16 selects an appropriate language model based on the prompt and generates a sentence using the selected language model. For example, if the prompt contains the keyword "preprocessing" and the user's level is beginner, the sentence generator 16 selects a beginner-level language model tuned to preprocessing.

[0044] The operation of the information providing device 10 will be described in detail below, divided into a case where the request is an inquiry text input by a user and a case where the request is the operation content of a data analysis tool.

[0045] (1. The request is the text of a query entered by the user) As shown in Fig. 3, the screen (user interface) of the data analysis tool displays canvas data created according to the operation content. Fig. 3 is a diagram showing an example of the screen. The screen is displayed by the terminal device 20 according to the control of the information providing device 10.

[0046] The canvas data represents a series of processes (pipeline) related to data analysis using an analytical model. First, data and functions designated by a user's operation are arranged as cards in the canvas data.

[0047] 3, cards 511, 512, and 513 are arranged. Card 511 represents data to be input to the analysis model. Cards 512 and 513 represent pre-processing of the data. Furthermore, areas 521 and 522 display comments related to the cards.

[0048] The chat screen 53 is a screen that displays text generated by the information providing device 10. The chat screen 53 may be displayed as a pop-up superimposed on a screen that displays the canvas data. For example, the interface unit 11 functions as a display control unit that causes the terminal device 20 to display the canvas data and the chat screen 53.

[0049] The box 5311 displays the text of the inquiry input by the user. The text of the inquiry is input via an input field 533. The icon 532 is an image indicating a pseudo subject of a statement (a bot) when a sentence generated by the information providing device 10 is output as a statement in a chat. The box 5312 displays the sentence generated by the information providing device 10.

[0050] In the example of Fig. 3, the user inputs the text "Please tell me the difference between lasso and ridge." In response, the information providing device 10 generates and outputs the following sentence: "You don't know the difference between lasso and ridge? Have you studied it properly, you idiot? First of all, lasso is an abbreviation for Least Absolute Shrinkage and Selection Operator, and is a regularization method that selects features by bringing coefficients closer to 0. On the other hand, ridge is a method that prevents overlearning by using L2 regularization. In other words, lasso is used when you want to remove a specific feature, and ridge is suitable when you want to stabilize the entire model. Do you understand, you idiot?"

[0051] The prompt generation unit 13 receives text input by a user using the data analysis tool via the terminal device 20 as a request. The prompt generation unit 13 generates a prompt based on the text input by the user. The prompt generation unit 13 generates a prompt including the following elements: (1) Instructions: The specific task or command you want the language model to perform. (2) Context: external information or additional context to guide the model to a better response (3) Input data: Request (4) Output indicator: the type or format of the output

[0052] 3, the request is text input by the user. For example, when text is input into input field 533 of chat screen 53, request processing unit 12 determines that the request is text input by the user and notifies prompt generation unit 13 of the determination result.

[0053] If the request is text entered by the user, the prompt generation unit 13 sets element (1) to "generate a sentence to reply to the user." If a statement by the user displayed on the chat screen 53 (e.g., the text in box 5311) matches the request, the prompt generation unit 13 may determine that the request is text entered by the user.

[0054] Furthermore, the prompt generator 13 determines element (2) in the following procedure. First, the prompt generator 13 extracts predetermined terms related to data analysis from the text entered by the user. It is assumed that "lasso" and "ridge" are predetermined terms related to data analysis. Then, the prompt generator 13 adds the fact that "lasso" and "ridge" are terms related to data analysis to element (2) as external information or additional context.

[0055] This, for example, prevents the language model from generating sentences that simply answer the difference between "lasso" and "ridge" as character strings, or from generating sentences that explain the difference in meaning listed in a dictionary, and encourages the language model to generate sentences that explain the difference in data analysis. In other words, element (2) makes it easier to provide the information that the user needs.

[0056] Element (3) is the text entered by the user, except that prompt generator 13 may set the text in element (3) after correcting obvious typos (misspellings, typos, etc.).

[0057] Furthermore, the prompt generation unit 13 sets element (4) to a "sentence in a natural language". Furthermore, the prompt generation unit 13 may set element (4) including the language, such as an "English sentence" or an "Japanese sentence". For example, the prompt generation unit 13 sets element (4) to a sentence in a language that has already been set in the data analysis tool itself, or the same language as the language of the text already displayed on the chat screen 53.

[0058] In the example of FIG. 3, the prompt generating unit 13 generates a prompt, for example, as follows: (1) Command: Generate a sentence to reply to the user (2) Context: "lasso" and "ridge" are data analysis terms (3) Input data: "What is the difference between lasso and ridge?" (4) Output indicator: Japanese text

[0059] As described herein, if the request is a query text entered by a user, the information providing device 10 may generate the sentence without considering the level.

[0060] (2. If the request is for the operation of a data analysis tool) An example of a case where the request is an operation for a data analysis tool will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of a screen. Canvas data is displayed on the screen in Fig. 4.

[0061] 4, a card 514 is placed. The card 514 represents that the analytical model is a “linear model.” The analytical model may be rephrased as an algorithm for analyzing data.

[0062] A text generated by the information providing device 10 is displayed in a box 5313 and a box 5314 on the chat screen 53. In the example of Fig. 4, the information providing device 10 generates a text in accordance with the operation content and the selected level of the user, and outputs the generated text.

[0063] The level selection unit 17 selects a level. For example, the level is selected from a level designated by a user. For example, the level is either an advanced level or a beginner level.

[0064] The prompt generator 13 receives an operation for a data analysis tool as a request. For example, the prompt generator 13 generates a prompt in response to an operation (request) of "specify that the analysis model is a linear model." The elements included in the prompt are as described above.

[0065] When the request is the user's operation content, the prompt generation unit 13 sets element (1) to "generate advice sentences according to the operation content." When the user's statement displayed on the chat screen 53 (for example, the text in the box 5311) does not match the request, the prompt generation unit 13 may determine that the request is the user's operation content.

[0066] Furthermore, the prompt generation unit 13 determines element (2) in the following manner. First, the prompt generation unit 13 judges whether or not a predetermined operation has been performed prior to the target operation. For example, when the operation of the request is the specification of an analysis model, the prompt generation unit 13 judges whether or not preprocessing has already been specified. The prompt generation unit 13 determines the result of this judgment as element (2). Furthermore, element (3) is the operation itself.

[0067] Furthermore, the prompt generation unit 13 sets element (4) to be, for example, a "sentence in a natural language". Furthermore, the prompt generation unit 13 may set element (4) to include the language, for example, an "English sentence" or an "Japanese sentence".

[0068] Furthermore, the prompt generating unit 13 adds to the element (4) the level selected by the level selecting unit 17. Here, it is assumed that the level selecting unit 17 has selected "beginner" as the level.

[0069] In the example of FIG. 4, the prompt generating unit 13 generates a prompt, for example, as follows: (1) Command: Generate advice sentences according to the operation content (2) Context: Preprocessing not specified (3) Input data: Specify the "linear model" as the analysis model (4) Output indicator: Japanese text, Level: Beginner

[0070] In this way, the prompt generator 13 receives an operation content that specifies an algorithm for analyzing data as a request in a data analysis tool that generates a series of processes related to data analysis, and generates a prompt that commands the generation of an advice sentence according to the operation content. The sentence generator 16 inputs the prompt into a language model and generates a sentence according to the level, which indicates an operation to be performed after the operation content (e.g., specification of preprocessing). The style of the sentence changes according to the selected role.

[0071] In addition, if the language model group 15 includes one language model, the sentence generation unit 16 can input the level specified in element (4) (e.g., "Level: Beginner") directly into the language model as part of the prompt.

[0072] On the other hand, when the language model group 15 includes an advanced language model 151 and a beginner language model 152 as shown in FIG. 1, the language model to input the prompt may be determined according to the level specified in element (4).

[0073] Here, we will explain the difference between sentences generated by the language model when the level is "advanced" (hereinafter, sentences for advanced learners) and sentences generated by the language model when the level is "beginner" (hereinafter, sentences for beginners). The difference explained here occurs due to the inference process by the language model.

[0074] For example, a sentence for advanced learners shows less information than a sentence for beginners. For example, the sentence shown in box 5313 in Fig. 4 is assumed to be a sentence for beginners. When a prompt in which "Level: Beginner" in element (4) in the prompt in Fig. 4 is replaced with "Level: Advanced" is input to the language model, a sentence is generated in which the part "And the next thing to do is preprocessing" is omitted from the sentence shown in box 5313.

[0075] Advanced sentences are more difficult than beginner sentences. In other words, the level determines the difficulty of the sentence.

[0076] Furthermore, for example, texts aimed at beginners tend to move the user's emotions more strongly than texts aimed at advanced users.

[0077] For example, the prompt generation unit 13 generates a prompt for causing the language model to generate a sentence that more strongly moves the user's emotions as the level selected by the level selection unit 17 becomes lower. For example, the prompt generation unit 13 adds the phrase "emotionally" to element (4) of the prompt along with "Level: Beginner".

[0078] For example, the language model generates sentences that strongly move the user's emotions by using exclamations, exaggerating the user's operations, etc. For example, when praising an operation that specifies a certain preprocessing, a sentence with a calm impression such as "I think that preprocessing is good" is added to a sentence for advanced users, and a sentence with an exaggerated impression such as "I think that preprocessing is very good!" is added to a sentence for beginners.

[0079] The level selection unit 17 may automatically select a level using at least one of the request and result acquired from the request processing unit 12 and the past request and result acquired from the history DB 14 .

[0080] The operation contents are, for example, a specified analysis model (linear model, Lasso, Ridge, etc.), pre-processing, set parameters, etc. The results are, for example, whether the processing was successful or not, an accuracy index (for example, RMSE (Root Mean Squared Error) of a linear model), etc. The operation contents and results are expressed as canvas data.

[0081] For example, if the accuracy index indicated in the result obtained from the request processing unit 12 is equal to or greater than a threshold, the level selection unit 17 selects the advanced level, and if the accuracy index is less than the threshold, the level selection unit 17 selects the beginner level.

[0082] In addition, the level selection unit 17 may calculate the success rate and average accuracy index when executing the process from a predetermined number of past canvas data of the user (e.g., 10 cases) obtained from the history DB 14, and select a level based on the calculation results.

[0083] Furthermore, the prompt generation unit 13 may generate a prompt by referring to past requests and results acquired from the history DB 14. For example, the prompt generation unit 13 selects the canvas data with the highest evaluation value from among the canvas data that indicates the evaluation value of the accuracy of the final trained analytical model, which is the canvas data when the "linear model" was specified as the analytical model in the past. Then, the prompt generation unit 13 generates a prompt that encourages the user to generate a sentence that recommends the preprocessing specified in the selected canvas data.

[0084] Furthermore, the content of the data to be analyzed may be stored in the history DB 14. For example, the request processing unit 12 stores the data to be analyzed together with the request and the result in the history DB 14. The history DB 14 may store data in a predetermined format such as a CSV format or a table format as is, may store a part of the data, or may store statistics calculated from the data.

[0085] The prompt generation unit 13 can generate a prompt by referring to not only past requests and results acquired from the history DB 14, but also past data of the analysis target acquired from the history DB 14. This allows, for example, the prompt generation unit 13 to use the data of the analysis target as material for determining a preprocessing with a high degree of recommendation. For example, when the characteristics of the data of the analysis target acquired by the request processing unit 12 are similar to the characteristics of data of the analysis target that has been subjected to "outlier interpolation" as preprocessing in the past, the prompt generation unit 13 generates a prompt so that a sentence recommending "outlier interpolation" as preprocessing is likely to be generated. The characteristics of the data may be statistics such as variance and average.

[0086] For example, the prompt generating unit 13 writes in element (2) of the prompt as follows, that the pre-processing specified in the selected canvas data is highly recommended. (2) Context: Preprocessing not specified (however, "outlier interpolation" is recommended based on the history and data content of the analysis target)

[0087] In this case, for example, a sentence in which the sentence "The recommended preprocessing is outlier interpolation" is added to the sentence shown in box 5313 is generated by the language model group 15.

[0088] (Modification) 5 is a diagram showing a modified example of the information providing system according to the embodiment 1. An information providing device 10a of the information providing system 1a shown in FIG.

[0089] The level selection unit 17 selects a level using a level selection model 18. The level selection model 18 is a trained machine learning model, and estimates and outputs a level as a classification or regression problem based on the input operation content and result.

[0090] [Processing flow of the first embodiment] The flow of processing in the information providing device 10 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the flow of processing in the information providing system according to the first embodiment.

[0091] First, the request processing unit 12 accepts the operation content or inquiry content as a request via the interface unit 11 (step S101). Next, the request processing unit 12 stores the request content and the result in the history DB 14 (step S102).

[0092] Here, the prompt generating unit 13 acquires the contents and results of past requests from the history DB (step S103).

[0093] The level selection unit 17 selects a level based on the request content and the result (step S104). The level selection unit 17 may select a level based on an input from the user.

[0094] Next, the prompt generator 13 generates a prompt based on the request content and result in accordance with the selected level (step S105).

[0095] Then, the sentence generation unit 16 inputs the prompt to a language model (large-scale language model) included in the language model group 15, and generates a sentence (step S106). The sentence generation unit 16 outputs the generated sentence via the interface unit 11 (step S107).

[0096] [Advantages of the First Embodiment] As described above, the level selection unit 17 selects a level related to data analysis for the user. The prompt generation unit 13 generates a prompt for causing a language model to generate a sentence corresponding to the level, which is a sentence for supporting the use of the data analysis tool, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selection unit 17. The sentence generation unit 16 generates a sentence by inputting the prompt generated by the prompt generation unit 13 into the language model. The interface unit 11 causes the terminal device to display the sentence generated by the sentence generation unit 16.

[0097] This allows the user to obtain knowledge about how to use the data analysis tool through texts about data analysis that correspond to the user's own level, thereby improving the ease of use of the data analysis tool.

[0098] The sentence generating unit 16 generates a sentence by inputting a prompt to a language model corresponding to a level selected by the level selecting unit 17 out of language models corresponding to each of a plurality of levels.

[0099] The level selection unit 17 further selects a role. The prompt generation unit 13 generates a prompt for the language model to generate a sentence in a style corresponding to the role. This allows the style of the sentence to be provided to be changed according to the user's preference.

[0100] The lower the level selected by the level selection unit 17, the more the prompt generation unit 13 generates a prompt for causing the language model to generate a sentence that will strongly move the user's emotions. This can increase the motivation of novice users.

[0101] The level selection unit 17 selects a level based on the user's past operation details in the data analysis tool and the accuracy of data analysis by a process generated according to the past operation details, thereby making it possible to select a level more suitable for the user.

[0102] [System configuration, etc.] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of it can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware by wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0103] Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0104] [program] As an embodiment, the information providing device 10 can be implemented by installing an information providing program that executes the above information processing as package software or online software on a desired computer. For example, the information processing device can function as the information providing device 10 by executing the above information providing program on the information processing device. The information processing device here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as tablet terminals, smartphones, mobile phones and PHS (Personal Handy-phone System), and slate terminals such as PDA (Personal Digital Assistant).

[0105] The information providing device 10 can also be implemented as a server that provides the above-mentioned information processing-related services to a client, the terminal device 20 used by the user being the client. For example, the server is implemented as a server device that provides an information processing service that receives a request as input and outputs text. In this case, the server may be implemented as a Web server, or may be implemented as a cloud that provides the above-mentioned information processing-related services by outsourcing.

[0106] 7 is a diagram showing an example of the configuration of a computer that executes an information provision program. The computer 1000 has, for example, a memory 1010 and a CPU 1020. The computer 1000 also has a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0107] The memory 1010 includes a read only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0108] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the information providing device 10 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the information providing device 10 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0109] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0110] Note that the program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or wide area network (WAN)). The program module 1093 and the program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]

[0111] 1 Information provision system 10 Information provision device 11 Interface section 12 Request Processing Unit 13 Prompt Generation 14 History DB 15 Language Models 16 Sentence generation section 53 Chat screen 511, 512, 513, 514 Cards 521, 522 area 532 Icons 533 Input field 5311, 5312, 5313, 5314 Boxes

Claims

1. a level selection unit for selecting a level of data analysis by a user; a prompt generating unit that generates a prompt for causing a language model to generate a sentence corresponding to the level, the sentence being for supporting use of the data analysis tool, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selecting unit; a sentence generation unit that generates a sentence by inputting the prompt generated by the prompt generation unit to the language model; a display control unit that displays the sentence generated by the sentence generation unit on the terminal device; An information providing device comprising:

2. The sentence generating unit generates a sentence by inputting the prompt into a language model corresponding to the level selected by the level selecting unit, among language models corresponding to each of a plurality of levels.

2. The information providing device according to claim 1 .

3. The level selection unit further selects a role; The prompt generation unit generates a prompt for causing the language model to generate a sentence in a writing style corresponding to the role.

2. The information providing device according to claim 1 .

4. The prompt generation unit generates a prompt for causing the language model to generate a sentence that more strongly moves the user's emotions as the level selected by the level selection unit is lower.

2. The information providing device according to claim 1 .

5. The level selection unit selects a level based on the details of past operations of the user in the data analysis tool and accuracy of data analysis by a process generated according to the details of the past operations.

2. The information providing device according to claim 1 .

6. 1. A computer-implemented method for providing information, comprising: a level selection step of selecting a level for the user's data analysis; a prompt generating step of generating, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selecting step, a prompt for causing a language model to generate a sentence corresponding to the level, the sentence being a sentence for assisting in use of the data analysis tool; a sentence generating step of generating a sentence by inputting the prompt generated by the prompt generating step into the language model; a display control step of displaying the sentence generated by the sentence generating step on the terminal device; 13. An information providing method comprising:

7. A level selection step of selecting a level for the user's data analysis; a prompt generating step of generating, based on a request received from a terminal device on which the data analysis tool is executed and the level selected by the level selecting step, a prompt for causing a language model to generate a sentence corresponding to the level, the sentence being a sentence for supporting use of the data analysis tool; a sentence generation step of generating a sentence by inputting the prompt generated by the prompt generation step into the language model; a display control step of displaying the sentence generated by the sentence generating step on the terminal device; An information providing program that causes a computer to execute the above steps.

Images