JP2025013095A - Information processing device, method, program, and system - Google Patents

Abstract

To provide a technique for obtaining an appropriate data analysis result at low cost and in a short time regardless of a level of a user's data analysis skill.SOLUTION: A program causes a computer to execute means of: managing a progress state of a chat relating to data analysis performed with a user; specifying a purpose of the analysis of the user through the progress of the chat; analyzing an object data set according to the purpose of analysis; and outputting a result of the analysis of the object data set.SELECTED DRAWING: Figure 4

Description

This disclosure relates to an information processing device, a method, a program, and a system.

Traditionally, various BI (Business Intelligence) tools have been known to help companies collect, accumulate, analyze, and process the vast amounts of data they have acquired, and to support decision-making for business strategies.

Patent Document 1 also discloses a technical idea that aims to provide high-quality "managed model self-service BI" in a shorter period of time by using a common design framework, without relying on individual design skills.

JP 2019-175236 A

However, in many cases, it is not easy for people without advanced data analysis skills, such as those in a company's planning department, to use BI tools on their own, and support from data analysis experts is often required. Receiving support from an expert is costly, and it takes a long time to obtain analysis results. In addition, the technical idea of Patent Document 1 also requires input of necessary information into a requirements definition template and an analysis model detailed definition document, and is therefore understood to be premised on a certain level of design and analysis skills.

The purpose of this disclosure is to provide technology that enables users to obtain appropriate data analysis results at low cost and in a short time, regardless of their level of data analysis skill.

A program according to one aspect of the present disclosure causes a computer to function as a means for managing the progress of chats regarding data analysis conducted with a user, a means for identifying the user's objective of analysis through the progress of the chats, a means for analyzing a target dataset according to the objective of the analysis, and a means for outputting the results of the analysis of the target dataset.

1 is a block diagram showing a configuration of an information processing system according to an embodiment of the present invention; FIG. 2 is a block diagram showing a configuration of a client device according to the present embodiment. FIG. 2 is a block diagram showing a configuration of a server according to the present embodiment. FIG. 1 is an explanatory diagram of one aspect of the present embodiment. FIG. 2 is a diagram showing an overall flow of information processing according to the present embodiment. 11 is a flowchart of a process for setting an analysis objective according to the present embodiment. 13A and 13B are diagrams illustrating an example of a screen displayed in the process of setting an analysis objective according to the present embodiment. 13A and 13B are diagrams illustrating an example of a screen displayed in the process of setting an analysis objective according to the present embodiment. 13A and 13B are diagrams illustrating an example of a screen displayed in the process of setting an analysis objective according to the present 13 is a flowchart of an analysis process according to the present embodiment. FIG. 13 is a diagram showing an example of a screen displayed in the analysis process of the present embodiment. FIG. 13 is a diagram showing an example of a screen displayed in the analysis process of the present embodiment.

One embodiment of the present invention will be described in detail below with reference to the drawings. In the drawings used to explain the embodiment, the same components are generally designated by the same reference numerals, and repeated explanations will be omitted.

(1) Configuration of the Information Processing System The configuration of the information processing system will be described below. Fig. 1 is a block diagram showing the configuration of the information processing system according to this embodiment.

As shown in FIG. 1, the information processing system 1 includes a client device 10 and a server 30 .
The client device 10 and the server 30 are connected via a network (for example, the Internet or an intranet) NW.

The client device 10 is an example of an information processing device that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer. A user of the client device 10 is assumed to be, for example, a person in a company's planning department who has a need for data analysis but who often does not have the advanced skills to carry out the data analysis. However, the information processing system 1 of this embodiment is also useful when the user of the client device 10 is a highly skilled data analysis expert.

The server 30 is an example of an information processing device that provides the client device 10 with a response in response to a request sent from the client device 10. The server 30 is, for example, a web server.

(1-1) Configuration of the Client Device The configuration of the client device will be described below with reference to Fig. 2, which is a block diagram showing the configuration of the client device according to this embodiment.

As shown in FIG. 2, the client device 10 includes a storage device 11, a processor 12, an input/output interface 13, and a communication interface 14. The client device 10 is connected to a display 21.

The storage device 11 is configured to store programs and data. The storage device 11 is, for example, a combination of Read Only Memory (ROM), Random Access Memory (RAM), and storage (for example, flash memory or a hard disk).

The programs include, for example, the following programs:
- Operating System (OS) programs - Programs for applications that perform information processing (e.g., web browsers, applications for data analysis, etc.)

The data includes, for example, the following data:
- Databases referenced in information processing - Data obtained by executing information processing (i.e., the results of executing information processing)

The processor 12 is a computer that realizes the functions of the client device 10 by running a program stored in the storage device 11. The processor 12 is, for example, at least one of the following:
・CPU (Central Processing Unit)
・GPU (Graphic Processing Unit)
・ASIC (Application Specific Integrated Circuit)
・FPGA (Field Programmable Gate Array)

The input/output interface 13 is configured to obtain information (e.g., user instructions) from an input device connected to the client device 10, and to output information (e.g., images) to an output device connected to the client device 10.

The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display 21, a speaker, or a combination thereof.

The communication interface 14 is configured to control communication between the client device 10 and an external device (e.g., the server 30).

The display 21 is configured to display an image (still image or video). The display 21 is, for example, a liquid crystal display or an organic EL display.

(1-2) Server Configuration The following describes the server configuration: Fig. 3 is a block diagram showing the server configuration of this embodiment.

As shown in FIG. 3, the server 30 includes a storage device 31, a processor 32, an input/output interface 33, and a communication interface 34.

The storage device 31 is configured to store programs and data. The storage device 31 is, for example, a combination of ROM, RAM, and storage (e.g., flash memory or a hard disk).

The programs include, for example, the following programs:
・OS programs ・Application programs that execute information processing

The data includes, for example, the following data:
- Databases referenced in information processing - Results of information processing

The processor 32 is a computer that realizes the functions of the server 30 by running a program stored in the storage device 31. The processor 32 is, for example, at least one of the following:
CPU
・GPU
・ASIC
・FPGA

The input/output interface 33 is configured to obtain information (e.g., user instructions) from an input device connected to the server 30, and to output information (e.g., images) to an output device connected to the server 30.

The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display.

The communication interface 34 is configured to control communication between the server 30 and an external device (e.g., the client device 10). The server 30 may be configured to access an external system to utilize some of the functions of a natural language model (hereinafter simply referred to as a "natural language model") such as a large-scale language model or a data analysis tool.

(2) One aspect of the embodiment One aspect of the present embodiment will be described below. Fig. 4 is an explanatory diagram of one aspect of the present embodiment.

As shown in FIG. 4, the information processing system 1 performs data analysis required by the user US1 mainly on a chat basis between the user US1 and the data analysis agent AG2, and ultimately provides the results of the analysis to the user US1.

Specifically, the server 30 manages the progress of a chat regarding data analysis between the user US1 and the data analysis agent AG2. The management of the chat progress may include understanding the intent of the user's instructions, generating a system response based on the intent of the user's instructions and the data analysis scenario, and outputting the system response. In managing the chat progress, the server 30 can use a natural language model as appropriate. On the other hand, the client device 10 accepts user instructions from the user US1 and outputs them to the server 30, and displays a UI (User Interface) for the user US1 based on the system response received from the server 30.

Through the progress of the chat, the server 30 identifies (verbalizes) the purpose of the data analysis of the user US1. The verbalized purpose is stored in the storage device 31 as a guideline for subsequent analysis and is referenced by the server 30. The server 30 also accepts data sets provided by the user US1 via the client device 10. The server 30 analyzes a target data set based on the accepted data set, and outputs a system response including the results of the analysis to the client device 10. The client device 10 displays a UI showing the results of the analysis to the user US1.

As a result, user US1 can obtain the analysis results that user US1 needs (which may include the results of analysis that he or she potentially needed) simply by answering questions from data analysis agent AG2 and performing actions requested by data analysis agent AG2 (e.g., specifying a data set, etc.). In particular, user US1 does not need to prepare solutions in advance before starting the chat, such as what purpose the analysis should be performed for, what analysis method should be selected, or what data set should be prepared, as these elements can be determined through the chat and the necessary analysis can be performed.

(3) Information Processing The information processing of this embodiment will be described with reference to Fig. 5, which is a diagram showing the overall flow of the information processing of this embodiment.

In this embodiment, information processing starts when a predetermined start condition is met. The start condition may be, for example, a user starting a new analysis project.

As shown in FIG. 5, the server 30 acquires a data set (S100).
Specifically, the server 30 obtains a system response (e.g., a chat message) requesting the user to provide a data set that will be used as material for analysis, and transmits it to the client device 10 .
The client device 10 displays a UI based on the received system response on the display 21. The client device 10 accepts a data set designation from the user, and acquires the designated data set. The client device 10 transmits the acquired data set to the server 30.

After step S100, the server 30 executes setting of the purpose of the analysis (S110).
Specifically, the server 30 starts a chat to identify the user's purpose of analysis. The server 30 identifies (verbalizes) the user's purpose of analysis based on an exchange of messages between the user and the data analysis agent. The server 30 stores the identified purpose of analysis in the storage device 31 and transmits it to the client device 10. The client device 10 provides the user with a UI that allows the user to refer to the received purpose of analysis.
The details of setting the purpose of the analysis (S110) will be described later.

After step S110, the server 30 performs an analysis (S120).
Specifically, the server 30 performs an analysis on the data set acquired in step S100 or a data set obtained by processing the data set (e.g., by performing preprocessing such as data cleansing) in accordance with the purpose of the analysis set in step S110. The server 30 transmits the results of the analysis to the client device 10. The client device 10 displays a UI indicating the received analysis results on the display 21.
The analysis (S120) will be described in detail later.

(3-1) Analysis Goal Setting Process The analysis goal setting process of this embodiment will now be described. FIG. 6 is a flowchart of the analysis goal setting process of this embodiment. FIG. 7 is a diagram showing an example of a screen displayed in the analysis goal setting process of this embodiment. FIG. 8 is a diagram showing an example of a screen displayed in the analysis goal setting process of this embodiment. FIG. 9 is a diagram showing an example of a screen displayed in the analysis goal setting process of this embodiment.

As shown in FIG. 6, the server 30 generates a system response (S111).
Specifically, the server 30 generates a system response (message) that asks the user about the analysis target, and transmits the response to the client device 10 .

As a first example of generating a system response (S111), the server 30 may identify (extract) candidates to be analyzed based on the data item names (variable names) included in the dataset acquired in step S100, and generate a system response including a question regarding the candidates. The question may ask the user which of the candidates is the analysis target, or may ask the user whether each candidate is the analysis target.

In the following description, unless otherwise specified, the server 30 may generate a system response using one or both of a predetermined template and a natural language model. For example, the server 30 may generate a system response by inserting a sentence generated by a natural language model into a template.

As a second example of generating a system response (S111), the server 30 may generate a standard message as the system response, regardless of the data item names contained in the data set acquired in step S100.

After step S111, the client device 10 executes screen display (S211).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S111. The client device 10 displays a screen based on the received system response on the display 21. An example of such a screen is shown in FIG.

The screen of FIG. 7 includes objects J20 to J27.
Object J20 indicates which of a number of phases that define the progress of the chat (i.e., the progress of the analysis project) the chat is currently in. In the example of Fig. 7, object J20 indicates that the progress of the chat is "setting the goal of the analysis."

Object J21 displays the main UI. Object J21 displays chat between the user and the data analysis agent, or analysis results (in other words, system responses and user instructions). Object J21 is configured to be able to display at least the most recent system response or user instruction. Furthermore, object J21 may be configured to be able to display past system responses or user instructions, for example, in response to a scroll operation.

In the example of FIG. 7, object J21 displays the system response "What would you like to analyze?" Furthermore, in the example of FIG. 7, objects J210a to J210b are placed on object J21.

Object J210a accepts user instructions to select candidates for analysis. In the example of FIG. 7, object J210a corresponds to a drop-down list, but can be replaced with any selection-based GUI component such as a list box, check box, or radio button.

Object J210b accepts a user instruction to confirm the selection of object J210a. When object J210b is selected, the client device 10 transmits information that can identify the candidate selected by object J210a to the server 30.

Object J22 accepts user instructions. The client device 10 transmits the user instructions accepted by object J22 to the server 30. In the example of FIG. 7, by using object J22, the user can directly specify the analysis target without selecting object J210a.

Object J23 displays a sub-UI. Object J23 is configured to be able to display information about key points of the analysis project, such as the dataset used in the analysis, the purpose of the analysis (text), the results of the analysis, and chat history. Objects J24 to J27 are placed in object J23.

The object J24 accepts a user instruction to switch between displaying and hiding information about the dataset used in the analysis. When the object J24 is selected, the client device 10 displays the information about the dataset used in the analysis in the object J23, or closes the information that has already been displayed. The information about the dataset used in the analysis may include, for example, at least one of the following pieces of information:
- The name of the file in which the dataset is stored - The names of the data items (variables) included in the dataset (e.g., sales, date and time, etc.)
- The type of data items (variables) contained in the dataset (e.g., integer type, date type, etc.)
- Examples of values of data items (variables) included in the dataset

Object J25 accepts a user instruction to switch the display/non-display of the purpose of analysis. When object J25 is selected, the client device 10 displays the purpose of analysis in object J23, or closes the information that has already been displayed. However, when the purpose of analysis has not been set, the client device 10 can use fixed text or an image, such as "Undecided," in place of the purpose of analysis. Optionally, when object J25 is selected, in addition to the purpose of analysis, an object that accepts a user instruction to edit the purpose may be displayed.

Object J26 accepts a user instruction to switch between displaying and hiding the results of an analysis that has already been performed in the current analysis project. When object J26 is selected, the client device 10 displays the results of the analysis in object J23, or closes the information that has already been displayed. However, if the analysis has not been performed, the client device 10 can use fixed text or an image, such as "none," in place of the results of the analysis. Optionally, when object J26 is selected, in addition to the results of the analysis, an object that accepts a user instruction to edit the visual representation of the results (e.g., the format of a graph, etc.) may be displayed.

Object J27 accepts a user instruction to switch between displaying and hiding the chat history. When object J27 is selected, the client device 10 displays the chat history in object J23, or closes the information that has already been displayed.

After step S211, the client device 10 executes reception of a user instruction (S212).
Specifically, the client device 10 receives a user instruction to select or specify an analysis target from the user. In the example of Fig. 7, the user can select or specify an analysis target by operating objects J210a to J210b or by operating object J22. The client device 10 transmits the received user instruction to the server 30.

After step S212, the server 30 executes identification of an analysis target (S112).
Specifically, the server 30 receives the user instruction transmitted from the client device 10 in step S212. The server 30 identifies the analysis target based on the received user instruction. Here, for example, when a user instruction is obtained that specifies the analysis target by text, the server 30 may identify the analysis target by providing a model input based on the text to the natural language model. Optionally, when sufficient information to identify the analysis target is not obtained from the user instruction, the server 30 may re-execute steps S111 to S112.

After step S111, the server 30 generates a system response (S113).
Specifically, the server 30 generates a system response (message) asking the user what kind of analysis he or she wants to perform on the analysis target (i.e., the direction of the analysis), and transmits it to the client device 10. For example, the server 30 may generate the system response by inserting text corresponding to the analysis target identified in step S112 (which may include text generated by a natural language model based on the text) into a predefined message template. The system response may also include information indicating candidates for the direction of analysis that can be taken on the analysis target. The information indicating the candidates for the direction of analysis may include text that verbalizes the direction, an image (e.g., a graph) that helps understand the concept of the direction, or a combination thereof. The candidates for the direction of analysis may be predefined according to, for example, the type of data item of the analysis target, the type of data item other than the analysis target, other elements, or a combination thereof.

After step S113, the client device 10 executes screen display (S213).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S113. The client device 10 displays a screen based on the received system response on the display 21. An example of such a screen is shown in FIG.

The screen of FIG. 8 includes objects J20 to J27.
In the example of Fig. 8, object J21 displays a system response saying, "The analysis target is 'Sales'. Next, please choose the type of analysis you would like to perform. If there is no corresponding option, please enter it in the chat." Furthermore, in the example of Fig. 8, objects J211a to J211b are placed in object J21.

Object J211b accepts a user instruction to select a candidate analysis direction. In the example of FIG. 8, object J211a corresponds to a radio button, but can be replaced with any selection-based GUI component such as a drop-down list, list box, or radio button.

Object J211b accepts a user instruction to confirm the selection of object J211a. When object J211b is selected, the client device 10 transmits information capable of identifying the candidate selected by object J211a to the server 30.

In the example of Figure 8, by using object J22, the user can directly specify the direction of analysis without selecting object J211a.

After step S213, the client device 10 executes reception of a user instruction (S214).
Specifically, the client device 10 receives a user instruction to select or specify the direction of analysis from the user. In the example of Fig. 8, the user can select or specify the direction of analysis by operating the objects J211a to J211b or the object J22. The client device 10 transmits the received user instruction to the server 30.

After step S214, the server 30 executes specification of the purpose of the analysis (S114).
Specifically, the server 30 receives the user instruction transmitted from the client device 10 in step S214. The server 30 identifies the purpose of the analysis (i.e., a combination of the analysis target and the direction of the analysis) based on the received user instruction. That is, the server 30 obtains text indicating the purpose of the analysis. Here, for example, when a user instruction is obtained that specifies the direction of the analysis by text, the server 30 may provide a model input based on the text (which may further include text indicating the analysis target) to the natural language model to identify the purpose of the analysis. Optionally, when sufficient information is not obtained from the user instruction to identify the purpose of the analysis, the server 30 may re-execute steps S113 to S114.

After step S114, the server 30 generates a system response (S115).
Specifically, the server 30 generates a system response including the purpose of the analysis identified (verbalized) in step S114, and transmits the system response to the client device 10. For example, the server 30 may generate the system response by inserting text corresponding to the purpose of the analysis identified in step S114 into a predefined message template.

After step S115, the client device 10 executes screen display (S215).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S115. The client device 10 displays a screen based on the received system response on the display 21. An example of such a screen is shown in FIG.

The screen of FIG. 9 includes objects J20 to J27.
In the example of FIG. 9, an object J212 is placed on the object J21.

Object J212 displays a system response that informs the user of the purpose of the analysis identified in step S114. Thereafter, the purpose of the analysis can be expanded and displayed in object J23 via object J25, as necessary.

(3-2) Analysis Processing The analysis processing of this embodiment will be described. Fig. 10 is a flowchart of the analysis processing of this embodiment. Fig. 11 is a diagram showing an example of a screen displayed in the analysis processing of this embodiment. Fig. 12 is a diagram showing an example of a screen displayed in the analysis processing of this embodiment.

As shown in FIG. 10, the server 30 executes prediction of a suitable analysis method (S121).
Specifically, the server 30 predicts an appropriate analysis method for the purpose of the analysis identified in step S110, based on the user input in the chat and the system response.

As an example, the server 30 may provide the natural language model with model input based on information obtained by user input, and infer an analysis method suitable for the purpose of the analysis. The analysis method may be, for example, regression (which may include future prediction) for the analysis target, classification, clustering, dimensionality reduction (e.g., principal component analysis), or a combination thereof. Furthermore, identifying the analysis method may include identifying data items to be used as explanatory variables.

As another example, an analysis method suitable for the purpose of the analysis may be identified, and the available methods may be narrowed down from the analysis methods. The analysis method suitable for the purpose of the analysis may be defined in advance, for example. Furthermore, whether each analysis method is available may be determined based on the name or type of the data items included in the dataset acquired in step S100, the number of data samples included in the dataset, etc.

As an option for predicting an appropriate analysis method (S121), when there is insufficient information to predict an appropriate analysis method for the purpose of the analysis, the server 30 may generate a system response to ask the user a question or to prompt a predetermined action, and output the system response to the chat. As an example, the server 30 may generate a system response to ask whether there are any additional data sets related to the analysis, or to prompt the user to provide the additional data sets.

After step S121, the server 30 generates a system response (S122).
Specifically, the server 30 generates a system response (message) asking the user whether to adopt the analysis method predicted in step S121. As an example, the system response may ask the user which of a plurality of analysis methods to select (multiple selections may be possible), or may ask the user whether to adopt each analysis method. For example, the server 30 may generate the system response by inserting text corresponding to the analysis method predicted in step S121 into a predefined message template. In addition, the system response may include, as information indicating possible analysis methods, text that verbalizes the method, an image (e.g., a graph) that helps understand the concept of the method, or a combination thereof.

After step S122, the client device 10 executes screen display (S221).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S122. The client device 10 displays on the display 21 a screen based on the received system response.

After step S221, the client device 10 executes reception of a user instruction (S222).
Specifically, the client device 10 receives a user instruction to select or specify an analysis method from the user, and transmits the received user instruction to the server 30.

After step S222, the server 30 determines the analysis method (S123).
Specifically, the server 30 receives the user instruction transmitted from the client device 10 in step S222. The server 30 determines the analysis method based on the received user instruction. Here, for example, when a user instruction is obtained that specifies the analysis method by text, the server 30 may determine the analysis method by providing a model input based on the text (which may further include text indicating the analysis target, the direction of the analysis, or a combination thereof) to the natural language model. Optionally, when sufficient information is not obtained from the user instruction to determine the analysis method, the server 30 may re-execute steps S121 to S123.

After step S123, the server 30 performs an inspection of the data set (S124).
Specifically, the server 30 checks the data set provided by the user with a predetermined algorithm in step S100 or at another timing. The algorithm may be determined differently depending on the analysis method determined in step S123. The check of the data set may include, for example, at least one of the following:
・Detection of data imperfections (e.g., missing values, outliers, inappropriate variation, inappropriate granularity, or a combination of these) ・Determining whether the conditions for applying specified pre-processing are met

After step S125, the server 30 executes generation of a system response (S125).
Specifically, the server 30 generates a system response based on the results of the check in step S124. The system response may include, for example, at least one of the following:
A system response that prompts correction of imperfections in the data set discovered by the inspection in step S124 (for example, removal of samples including missing values or outliers) A system response that suggests carrying out a predetermined preprocessing (if it is determined in step S124 that the conditions for applying the predetermined preprocessing are met)
A system response that searches for another dataset from an external source to supplement the deficiencies in the dataset discovered by the inspection in step S124 and suggests using the dataset discovered from the external source.

The predetermined pre-processing may include, for example, at least one of the following:
- Name matching - Removal of missing values - Feature engineering (e.g., variable transformation, removal of similar (highly correlated) variables)
Here, the server 30 may obtain inference results regarding the types of variables, hypotheses about relationships between variables, and the like from the natural language model, and perform preprocessing (particularly, feature engineering) based on the inference results.

After step S125, the client device 10 executes screen display (S223).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S125. The client device 10 displays on the display 21 a screen based on the received system response.

After step S223, the client device 10 executes reception of a user instruction (S224).
Specifically, the client device 10 accepts a user instruction corresponding to a response from the user to the screen displayed in step S223. The client device 10 transmits the accepted user instruction to the server 30.

As an example, the client device 10 can accept at least one of the following user instructions:
A user instruction to correct the deficiencies pointed out by the system response (e.g., to edit the dataset) A user instruction to provide (upload) a dataset in which the deficiencies pointed out by the system response have been corrected A user instruction to request the implementation or non-implementation of preprocessing suggested by the system response

After step S224, the server 30 acquires the target data set (S126).
Specifically, in step S224, the server 30 receives the user instruction transmitted from the client device 10. In response to the received user instruction, the server 30 acquires a data set actually used for analysis (hereinafter, referred to as a "target data set").

As a first example of acquiring the target dataset (S126), when a user instruction is obtained to correct a defect indicated by the system response, the server 30 acquires the target dataset by editing the dataset inspected in step S124 in accordance with the user instruction.

As a second example of acquiring the target dataset (S126), when a user instruction is received to provide a dataset in which the deficiencies pointed out by the system response have been corrected, the server 30 acquires the dataset provided by the user instruction as the target dataset. Alternatively, the server 30 may re-execute the dataset inspection (S124) on the dataset provided by the user instruction.

As a third example of acquiring a target dataset (S126), when a user instruction is received requesting the implementation of preprocessing proposed by the system response, the server 30 acquires the target dataset by performing the preprocessing on the dataset inspected in step S124.

As a fourth example of acquiring the target dataset (S126), when a user instruction is received requesting not to perform the preprocessing suggested by the system response, the server 30 acquires the dataset inspected in step S124 as the target dataset as is.

Note that if the inspection in step S124 finds no defects in the dataset and determines that the dataset does not satisfy any of the conditions for applying preprocessing, steps S125 to S126 can be omitted. In other words, the server 30 can acquire the dataset inspected in step S124 as the target dataset as is.

After step S126, the server 30 performs an analysis (S127).
Specifically, the server 30 performs analysis on the target data set acquired in step S126 using the analysis method determined in step S123.

The server 30 may also generate a graph illustrating the results of the analysis. As an example, the server 30 may obtain the graph by providing a command generated by the natural language model to a data analysis tool. The type of graph (e.g., line graph, bar graph, scatter plot, pie chart, bubble chart, radar chart, stacked graph, box plot, etc.) may be determined depending on the purpose of the analysis and the analysis method. The server 30 may determine important points in the graph depending on the purpose of the analysis and the analysis method.

Furthermore, the server 30 may generate text representing suggestions obtained from the results of the analysis. As an example, the server 30 may obtain the suggestions by providing a model input based on the results of the analysis to a natural language model. The suggestions may include, for example, at least one of the following information:
Information that describes the dependent variable, explanatory variables, or a combination of them (i.e., the variables selected according to the objective of the analysis) (e.g., information summarizing the variables, such as the spread of the distribution or typical values)
- Information explaining the relationship between the objective variable and explanatory variables (i.e., the results of the analysis) - Information explaining the relationship between different explanatory variables - Information explaining the statistical treatment of the results of the analysis (for example, if the results of the analysis are not statistically significant, a message stating that the results of this analysis may be due to chance, or if the results of the analysis are statistically significant, a message stating that the results of this analysis are unlikely to be due to chance (i.e., there is a certain degree of reliability)).
- Information explaining statistically significant explanatory variables (e.g., the explanatory variable with the lowest significance level, or the explanatory variable with the largest absolute value of the correlation coefficient among the significant explanatory variables) (e.g., the value of the correlation coefficient between the explanatory variable and the objective variable)
Information that explains the outliers (e.g., where they occur, what their value is, etc.)
- Information explaining important points in the graph - Information recommending the implementation of analysis using other analysis methods

The topics covered by the suggestions may be narrowed down depending on the purpose of the analysis. Specifically, the server 30 may score the topics that may be covered by the suggestions using a natural language model, and generate suggestions only for topics whose scores meet a criterion.

The suggestions may be generated, for example, by inserting the results of the analysis (numerical values) into a pre-prepared template. The template is preferably a text that describes the results of the analysis without using statistical or data analysis terminology. This can aid the user's understanding and help them translate the suggestions into concrete business actions.

After step S127, the server 30 generates a system response (S128).
Specifically, the server 30 generates a system response based on the results of the analysis generated in step S127. The system response may include, for example, a graph, a portion of the graph determined to be important, a suggestion, or a combination thereof.

After step S125, the client device 10 executes screen display (S225).
Specifically, the client device 10 receives the system response transmitted from the server 30 in step S127. The client device 10 displays a screen based on the received system response on the display 21. An example of such a screen is shown in Figs. 11 and 12.

The screen of FIG. 11 includes objects J20 to J27.
In the example of FIG. 11, object J20 indicates that the chat progress status is "analysis."

In the example of Figure 11, objects J213a, J213a1, and J213b are placed on object J21.

The object J213a displays a line graph showing the relationship between the objective variable "sales volume" and the explanatory variable "date."
Object J213a1 displays information indicating outliers as important points in the graph shown in object J213a.

Object J213b displays a suggestion. Specifically, object J213b includes information about a summary of the objective variable and information explaining the outlier, such as "Sales volume generally fluctuates between approximately 100 and 400 units per day. During the New Year holidays and Golden Week, sales volume increases to approximately 600 units per day, which is an outlier."

In the example of Figure 12, objects J214a, J214a1, and J214b are placed on object J21.

Object J214a displays a box plot showing the relationship between the objective variable "sales volume" and the explanatory variable "neighborhood events."

Object J214a1 displays information indicating the difference between a value of interest (the median sales volume for the nearby event "nationwide") and the baseline (in the example of Figure 12, the median sales volume for the nearby event "none") as an important point in the graph shown in object J214a.

Object J214b displays a suggestion. Specifically, object J214b includes information explaining the relationship between the objective variable and the explanatory variable, such as "When there is a nearby event 'nationwide,' the number of sales tends to be higher compared to when there is no nearby event. When comparing with the median, the increase in the number of sales is 30 units/day."

The server 30 may perform the analysis (S127) in stages across multiple phases (e.g., aggregation, simple analysis, machine learning, etc.). That is, the client device 10 may accept a user instruction regarding the analysis results after step S225, and the server 30 may perform further analysis (S127), generate a system response (S128), and display the screen (S225). In this case, the server 30 may change at least one of the graph and the suggestions in response to the transition of the phase.

(4) Summary As described above, the server 30 of this embodiment manages the progress of chats regarding data analysis conducted with the user, and identifies the purpose of the user's analysis through the progress of the chat. The server 30 analyzes the target data set according to the purpose of the analysis, and outputs the results of the analysis of the target data set. This allows the user to obtain the analysis results required by the user simply by answering questions given on the chat or performing actions requested on the chat. Therefore, even if a user is resistant to the CUI (Character User Interface) or GUI (Graphical User Interface), which are often seen in conventional BI tools, they can freely try analysis from the perspective of their interest without feeling any technical or psychological hurdles.

The progress of the chat may be defined using a number of predetermined phases. In each of the multiple phases, the server 30 may provide predetermined information or output a response to the chat to prompt the user to take a predetermined action without relying on input from the user. In this way, the user does not need to prepare solutions in advance before starting the chat, such as what purpose the analysis should be performed for, what analysis method should be selected, or what data set should be prepared, as these elements can be determined through the chat and the necessary analysis can be performed.

The server 30 may predict an analysis method suitable for the purpose of the analysis based on user input on the chat and system responses, and output information on the analysis method suitable for the predicted purpose of the analysis. This allows a user to perform an analysis according to the intended purpose and obtain the required results, even if the user does not have sufficient skills to incorporate the purpose of the analysis into the analysis design.

If the server 30 does not have enough information to predict an analysis method suitable for the purpose of the analysis, it may ask the user a question or output a system response to the chat to prompt the user to take a specific action. This allows the server 30 to appropriately predict the analysis method required by the user.

The server 30 may acquire a first dataset, which is a dataset provided by a user, detect any deficiencies in the first dataset based on the purpose of the analysis, and output a response to the chat prompting the user to correct the deficiencies in the first dataset based on the detection result. In this way, when the dataset provided by the user has deficiencies or an appropriate dataset is not provided, and a highly accurate analysis cannot be obtained as is, the deficiencies can be corrected and a more accurate analysis can be performed.

The server 30 may acquire a first dataset, which is a dataset provided by a user, and if the first dataset meets a predetermined condition, output a response to the chat proposing the implementation of preprocessing corresponding to the condition. This allows the user to select the necessary preprocessing even if the user does not have sufficient knowledge about preprocessing such as data cleansing. In other words, the amount of work required for preprocessing can be reduced.

The server 30 may output information for displaying an area for displaying chat and an area for displaying the results of the analysis of the target dataset on a single screen or in a switchable manner. This allows the user to refer to the results of the analysis and the chat simultaneously or alternately, to consider the next instructions to the system, or to deepen their understanding of the results of the analysis.

The results of the analysis of the target dataset may include a graph illustrating the results of the analysis of the target dataset and text that presents suggestions based on the results of the analysis of the target dataset. This allows the user to check the graph without performing command operations, etc., and to understand the key points of the analysis results even if the user does not have sufficient statistical knowledge. In other words, it is possible to prevent a situation in which the user subjectively interprets the results of the analysis and takes something that cannot be shown to be objectively correct as if it were true, or overlooks something that can be shown to be objectively correct.

The suggestions may provide an explanation of the variables selected based on the purpose of the analysis, or an explanation of the relationships between two or more variables, allowing the user to gain a deeper understanding of the variables (data items) that were the subject of the analysis.

The server 30 may determine the type of graph based on the purpose of the analysis and the analysis method used in the analysis. This allows the user to view a graph type suitable for checking the results of the analysis without having to perform command operations, etc.

The server 30 may determine important points in the graph according to the purpose of the analysis and the analysis method used in the analysis, and output information indicating the points in the graph that are determined to be important. This allows a user to understand the main points of the graph even if the user does not have sufficient background knowledge to properly interpret the graph.

The analysis of the target dataset may be performed in stages across multiple phases. The server 30 may change at least one of the graphs and the suggestions in response to the transition of the phases. This allows the results of even complex analyses to be presented in stages, allowing a user to follow along and understand the gist of the results of the analysis, even if the user does not have sufficient background knowledge to properly interpret the results of the analysis.

(5) Other Modifications The storage device 11 may be connected to the client device 10 via the network NW. The display 21 may be integrated with the client device 10. The storage device 31 may be connected to the server 30 via the network NW.

Each step of the above information processing can be performed by either the client device 10 or the server 30. For example, processing described as being performed by one device may be performed by another device, and processing described as being performed by the interaction of multiple devices may be performed by a single device.

In the above explanation, an example was given in which each step in each process is executed in a specific order, but the execution order of each step is not limited to the example described, as long as there is no dependency. For example, in the above explanation, an example was given in which the purpose of the analysis is set after the data set is acquired. However, the two may be executed in the reverse order, or in parallel.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited to the above-mentioned embodiments. Furthermore, the above-mentioned embodiments can be improved or modified in various ways without departing from the spirit of the present invention. Furthermore, the above-mentioned embodiments and modifications can be combined.

1: Information processing system 10: Client device 11: Storage device 12: Processor 13: Input/output interface 14: Communication interface 21: Display 30: Server 31: Storage device 32: Processor 33: Input/output interface 34: Communication interface

Claims (15)

Computer,
A means for managing the progress of chats regarding data analysis conducted between users;
means for identifying a purpose of analysis of the user through the progress of the chat;
means for analyzing a subject data set according to a purpose of said analysis;
means for outputting the results of the analysis of said target dataset;
A program that functions as a The progress of the chat is defined using a plurality of predetermined phases;
causing the computer to function as a means for providing predetermined information or outputting a response to the chat for prompting the user to take a predetermined action without an input from the user in each of the plurality of phases;
The program according to claim 1. The computer,
A means for predicting an analysis method suitable for the purpose of the analysis based on a user input and a system response on the chat;
A means for outputting information on an analytical method suitable for the predicted purpose of the analysis;
To function as
The program according to claim 2. The computer is caused to function as a means for outputting a system response to the chat to ask the user a question or to prompt the user to take a predetermined action when there is insufficient information for making a judgment to predict an analysis method suitable for the purpose of the analysis.
The program according to claim 3. The computer,
means for obtaining a first data set, the first data set being a data set provided by the user;
means for detecting deficiencies in the first data set based on the objective of the analysis;
means for outputting a response to the chat in response to a result of the detection, the response prompting the user to correct the deficiency in the first data set;
To function as
The program according to claim 2. The computer,
means for obtaining a first data set, the first data set being a data set provided by the user;
means for outputting, when the first data set meets a predetermined condition, a response to the chat suggesting the execution of a preprocessing corresponding to the condition;
To function as
The program according to claim 2. The output means outputs information for displaying the area displaying the chat and the area displaying the result of the analysis of the target dataset on a single screen or in a switchable manner.
The program according to claim 1. The results of the analysis of the target dataset include a graph illustrating the results of the analysis of the target dataset and text presenting suggestions based on the results of the analysis of the target dataset.
The program according to claim 7. The suggestion provides a description of variables selected for the purpose of the analysis, or a description of relationships between two or more variables.
The program according to claim 8. causing the computer to function as a means for determining the type of the graph in accordance with a purpose of the analysis and an analysis method used in the analysis;
The program according to claim 8. The computer,
a means for determining important points in the graph according to a purpose of the analysis and an analysis method used in the analysis;
means for outputting information indicating points determined to be important in the graph;
To function as
The program according to claim 8. The analysis of the subject dataset is conducted in a stepwise manner over multiple phases;
The output means changes at least one of the graph and the suggestion in response to a transition of the phase.
The program according to claim 8. The computer
Managing the progress of a chat regarding data analysis conducted with a user;
Identifying an objective of the user's analysis through the progress of the chat;
Analysing a target dataset according to a goal of said analysis;
and outputting the results of the analysis of the target dataset. A means for managing a progress state of a chat regarding data analysis conducted with a user;
A means for identifying an objective of the user's analysis through the progress of the chat;
means for analyzing a subject data set according to a purpose of said analysis;
and means for outputting a result of the analysis of the target data set. A system composed of a plurality of computers,
A means for managing a progress state of a chat regarding data analysis conducted with a user;
A means for identifying an objective of the user's analysis through the progress of the chat;
means for analyzing a subject data set according to a purpose of said analysis;
and means for outputting results of the analysis of the target dataset.