Information processing device, information processing method, program, and information processing system

Abstract

The objective is to make it possible to display the distribution of reference data and the distribution of query history data. [Solution] An information processing device that can communicate with a terminal, comprising: a storage unit that stores a plurality of reference data that are prepared in advance for a user responding to an inquiry to refer to when responding to an inquiry, and a plurality of inquiry history data that show the history of each inquiry; a generation unit that generates distribution information which is the distribution of the plurality of reference data and the plurality of inquiry history data distributed along a predetermined axis, namely the distribution information of the reference data and the distribution information of the inquiry history data; and an output unit that outputs data including the generated distribution information of the reference data and the distribution information of the inquiry history data to the terminal for display on the terminal.

Description

Technical Field

[0008] , , ,

[0007] , ,

[0001] The present invention relates to an information processing apparatus, an information processing method, a program, and an information processing system.

Background Art

[0002] An operator who responds to inquiries from customers refers to necessary data from a plurality of reference data, including a history of responses to past inquiries (FAQ) and product manuals, etc., prepared in advance to respond to inquiries, and answers the inquiries from customers.

[0003] In order to enable an operator to answer more inquiries, it is desirable to grasp the overall picture of the inquiry history.

[0004] Patent Document 1 discloses a technique for classifying inquiry data by keywords in order to grasp the overall picture of the inquiry history.

Summary of the Invention

Problems to be Solved by the Invention

[0005] When preparing or updating reference data, it is desirable to grasp the distribution of inquiry history data and the distribution of reference data.

[0006] However, in Patent Document 1, it was not possible to let the user grasp the distribution of inquiry history data and the distribution of reference data.

[0007] An embodiment of the present invention aims to enable the display of the distribution of reference data and the distribution of inquiry history data.

Means for Solving the Problems

[0008] An information processing device according to one embodiment of the present invention is an information processing device that can communicate with a terminal and includes: a storage unit that stores a plurality of reference data that are prepared in advance for a user responding to an inquiry to refer to when responding to the inquiry, and a plurality of inquiry history data that show the history of each inquiry; a generation unit that generates distribution information which is the distribution of the plurality of reference data and the plurality of inquiry history data distributed along a predetermined axis, namely the distribution information of the reference data and the distribution information of the inquiry history data; and an output unit that outputs data including the generated distribution information of the reference data and the distribution information of the inquiry history data to the terminal for display on the terminal. [Effects of the Invention]

[0009] One embodiment of the present invention aims to make it possible to display the distribution of reference data and the distribution of query history data. [Brief explanation of the drawing]

[0010] [Figure 1] This is a diagram illustrating an example of an information processing system according to this embodiment. [Figure 2] This is a hardware configuration diagram of an example of a computer according to this embodiment. [Figure 3] This is a functional configuration diagram of an example of an information processing system according to this embodiment. [Figure 4] This is an example of an inquiry history dataset according to this embodiment. [Figure 5] This is an example of a reference dataset according to this embodiment. [Figure 6] This is an example of analysis result data according to this embodiment. [Figure 7] This figure illustrates an example of how the analysis results according to this embodiment are displayed. [Figure 8] This is an example of a processing sequence for the information processing system according to this embodiment. [Figure 9] This is an example of a flowchart for the data analysis process included in the dataset according to this embodiment. [Figure 10] This is an example of the display of a screen for registering a dataset according to this embodiment. [Figure 11] This is an example of the display of a screen for displaying analysis results according to this embodiment. [Figure 12] This is an example of user interaction on a screen for displaying analysis results according to this embodiment. [Figure 13] This is an example of user interaction on a screen for displaying analysis results according to this embodiment. [Figure 14] This is a functional block diagram of an example of an information processing system according to this embodiment. [Figure 15] This is an example of the sequence of processing of an information processing system according to this embodiment. [Figure 16] This is an example of a flowchart of a process for determining classification items to be presented to a user according to this embodiment. [Figure 17] This is an example of the display of a screen for displaying analysis results according to this embodiment. [Figure 18] This is an example of the display of a screen for displaying analysis results according to this embodiment.

Mode for Carrying Out the Invention

[0011] Hereinafter, each embodiment of the present invention will be described with reference to the accompanying drawings.

[0012] [First Embodiment] <Configuration of Information Processing System> FIG. 1 is a configuration diagram of an example of an information processing system according to this embodiment. The information processing system 1000 in FIG. 1 includes a terminal 100, an information processing device 200, and a data server 300. The terminal 100, the information processing device 200, and the data server 300 communicate via a network N1. The network N1 is a network such as the Internet or a LAN (Local Area Network).

[0013] The terminal 100 is a terminal having a display function. The terminal 100 is, for example, a mobile terminal or a PC (Personal Computer), etc. Mobile terminals include smartphones, mobile phones, tablet terminals, game machines, PDAs (Personal Digital Assistants), digital cameras, wearable terminals, etc.

[0014] The terminal 100 displays a screen and accepts operations from the user. The terminal 100 accepts operations from the user and transmits a registration request for a data set, an output request for a screen, etc. to the information processing apparatus 200.

[0015] The information processing apparatus 200 is a server apparatus that executes processing in response to requests from the terminal 100. Also, the information processing apparatus 200 may be, for example, a cloud server or an on-premises server, etc.

[0016] The information processing apparatus 200 performs analysis of data included in a data set, transmission of display screen data (display control) to the terminal 100, etc. in response to requests from the terminal 100. Analysis of data included in a data set refers to classifying the data included in the data set and distributing the data included in the data set. Classifying data means dividing a plurality of data into several sets (classification items). Distributing data means determining the position of the data based on the content of the data. The position of the data reflects the content or features of the data. Therefore, when the user visualizes a plurality of data at their positions, the user can grasp the similarity between the data and what kinds of data are included in the plurality of data.

[0017] The data server 300 is a server that stores a data set. The data server 300 is, for example, a cloud server or an on-premises server, etc.

[0018] The data server 300 stores and reads datasets in response to requests from the terminal 100 or the information processing device 200. If the dataset is already stored in the terminal 100 or the information processing device 200, the data server 300 may be omitted.

[0019] Figure 1 shows an example where the terminal 100, information processing device 200, and data server 300 are connected to the same network N1, but they may be connected to different networks.

[0020] Furthermore, the information processing device 200 or data server 300 may be an output device equipped with communication functions, such as a PJ (Projector), IWB (Interactive White Board), digital signage, HUD (Head Up Display), industrial machinery, imaging device, sound collection device, medical equipment, networked home appliances, automobile (Connected Car), notebook PC (Personal Computer), mobile phone, smartphone, tablet terminal, game console, PDA (Personal Digital Assistant), digital camera, wearable PC, or desktop PC.

[0021] <Hardware configuration of the information processing system> The terminal 100, information processing device 200, and data server 300 in Figure 1 can be implemented, for example, by a computer with the hardware configuration shown in Figure 2.

[0022] Figure 2 is a hardware configuration diagram of an example of a computer according to this embodiment. The computer 500 in Figure 2 has a configuration comprising a CPU (Central Processing Unit) 501, ROM (Read Only Memory) 502, RAM (Random Access Memory) 503, HD 504, HDD (Hard Disk Drive) controller 505, display 506, external device connection I / F (Interface) 508, network I / F 509, data bus 510, keyboard 511, pointing device 512, DVD-RW (Digital Versatile Disk Rewritable) drive 514, and media I / F 516.

[0023] The CPU 501 controls the overall operation of the computer 500. The ROM 502 stores programs used to drive the CPU 501, such as the IPL. The RAM 503 is used as the work area for the CPU 501. The HD 504 stores various data, such as programs. The HDD controller 505 controls the reading or writing of various data to the HD 504 according to the control of the CPU 501.

[0024] Display 506 displays various information such as cursors, menus, windows, text, or images. External device connection I / F 508 is an interface for connecting external devices. External devices include USB (Universal Serial Bus) memory and printers. Network I / F 509 is an interface for data communication over network N1, etc. Computer 500 is further equipped with bus line 510. Bus line 510 is an address bus, data bus, etc., for electrically connecting various components such as the CPU 501 shown in Figure 2.

[0025] The keyboard 511 is a type of input means equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting processing targets, and moving the cursor. The DVD-RW drive 514 controls the reading or writing of various data to the DVD-RW 513, which is an example of a removable recording medium. Note that the DVD-RW may be an optical storage medium such as a DVD-R. The media I / F 516 controls the reading or writing (storage) of data to the recording medium 515, such as flash memory.

[0026] <Functional configuration in the first embodiment> Figure 3 is a functional configuration diagram of an example of an information processing system according to this embodiment.

[0027] ≪Device≫ Terminal 100 includes a receiving unit 110, a transmitting unit 120, a reception unit 130, a display control unit 140, and a storage unit 150. The receiving unit 110, the transmitting unit 120, the reception unit 130, the display control unit 140, and the storage unit 150 are realized, for example, by a process in which a program deployed from HD 504 shown in Figure 2 onto RAM 503 is executed by CPU 501.

[0028] The receiving unit 110 receives data from the information processing device 200 and the data server 300. The receiving unit 110 receives screen data and analysis results from the information processing device 200. The receiving unit 110 receives datasets from the data server 300.

[0029] The transmitting unit 120 transmits data to the information processing device 200 and the data server 300. The transmitting unit 120 transmits the data set, a request for analysis of the data contained in the data set, and configuration information (described later) to the information processing device 200. The transmitting unit 120 transmits the data set, a request for storage of the data set, and a request for retrieval of the data set to the data server 300.

[0030] The reception unit 130 receives operations from the user. User operations include setting configuration information (described later), selecting datasets, pressing buttons, and zooming in and out of the display. User operations can be performed by any means, such as mouse operation, keyboard input, or voice control.

[0031] The display control unit 140 displays a screen corresponding to the screen data received from the information processing device 200 or a screen corresponding to the screen data generated by the terminal 100. The display method can be any means, such as displaying on a display or projecting onto a screen.

[0032] The memory unit 150 stores the query history dataset 151 and the reference dataset 152, which will be described later.

[0033] ≪Dataset≫ A dataset is a collection of multiple data points. Hereafter, unless otherwise specified, the query history dataset 151 and the reference dataset 152 will simply be referred to as datasets.

[0034] This section describes the inquiry history dataset 151. Inquiry history dataset 151 is a collection of historical data for multiple inquiries. In other words, the data included in the inquiry history dataset is inquiry history data. The inquiry history data shows the history for each individual inquiry.

[0035] Figure 4 shows an example of an inquiry history dataset according to this embodiment. Hereinafter, the dataset of customer inquiry history may be referred to as the inquiry history dataset. Figure 4 is a configuration diagram of an example of an inquiry history dataset according to this embodiment, which is an example of a customer inquiry history dataset.

[0036] Customer inquiry history data includes fields such as the date received, the question, the answer, and the product name.

[0037] The reception date is the date and time the customer's inquiry was received. The question is the content of the customer's inquiry. The answer is the user's (hereinafter referred to as the operator's) response to the customer's inquiry. The product name indicates which product the customer's inquiry pertains to. The product name may also be product identification information or a model number.

[0038] Figure 4 shows that the customer inquiry history dataset includes data from an inquiry on April 1, 2022, regarding a product called "MP Cxxxx," stating, "There's a strange noise and smell..." and that the response to the inquiry was, "A short circuit in the wiring is a possibility..."

[0039] Figure 4 shows an example of text data as customer inquiry history data included in the inquiry history dataset. However, the data included in the inquiry history dataset is not limited to text data. For example, the data included in the inquiry history dataset could be images or any other information that can be vectorized.

[0040] Figure 4 shows an example that includes the fields for reception date, question, answer, and product name. The fields of data in the inquiry history dataset are not limited to these. The data in the inquiry history dataset may include other fields, or it may be configured to omit some fields.

[0041] Let's explain reference datasets. A reference dataset is a collection of multiple reference data sets. In other words, the data contained in a reference dataset is reference data. Reference data is data that operators handling queries can refer to when responding to queries, and it is pre-prepared data.

[0042] The reference dataset may include, for example, a history of answers to past inquiries (FAQs) and product manuals. Figure 5 shows an example of a reference dataset according to this embodiment.

[0043] The reference data includes title and content fields.

[0044] The title is the title of the product manual or the content of a past inquiry. The content is the contents of the product manual or the answer to the inquiry.

[0045] In Figure 5, the data included in the document dataset contains responses to past inquiries such as "From a laptop..." to which the response was "Download the migration tool from the following page...".

[0046] Figure 5 shows an example of text data included in a reference dataset. However, the data included in a reference dataset is not limited to text data. For example, the data included in a reference dataset could be images, or any information that can be vectorized.

[0047] Figure 5 shows an example that includes title and content fields. The fields of reference data included in a reference dataset are not limited to these. The reference data included in a reference dataset may include other fields, or it may be configured to omit some fields.

[0048] ≪Information Processing Device≫ The information processing device 200 includes a receiving unit 210, an output unit 220, a classification unit 230, a generation unit 240, a storage unit 250, and a distribution unit 270. The receiving unit 210, the output unit 220, the classification unit 230, the generation unit 240, the storage unit 250, and the distribution unit 270 are realized, for example, by a process in which a program deployed from the HD 504 shown in Figure 2 onto the RAM 503 is executed by the CPU 501.

[0049] The receiving unit 210 receives data from the terminal 100 and the data server 300. The receiving unit 210 receives from the terminal 100 a dataset, a request for analysis of the data contained in the dataset, and configuration information described later. The receiving unit 210 also receives a dataset from the data server 300.

[0050] The output unit 220 outputs screen data, analysis results, etc. The output unit 220 outputs data to the terminal 100 and the data server 300. The output unit 220 outputs screen data and analysis results to the terminal 100. The output unit 220 outputs analysis results, a request to store analysis results, and a request for a dataset to the data server 300. Output includes sending data to a wired connected device and sending data to the terminal 100 via the network N1. The output unit 220 may also output data for display on a display.

[0051] The classification unit 230 classifies the data contained in the dataset. Specifically, it classifies the data contained in the inquiry history dataset (inquiry history data) and the data contained in the reference dataset (reference data) into classification items. Details of the classification process will be described later.

[0052] The generation unit 240 generates various types of data. The generation unit 240 generates data for displaying a screen on the terminal 100. The data for displaying a screen may be the screen data itself, or it may be data used to generate the screen data. Examples of data used to generate screen data include distribution data of reference data and distribution data of inquiry history data. Distribution data is an example of distribution information.

[0053] The generation unit 240 generates distribution data for reference data and distribution data for query history data based on the analysis result data described later. Hereinafter, the distribution data for reference data and the distribution data for query history data may be collectively referred to as distribution data. The distribution data for reference data is an example of the distribution information for reference data. The distribution data for query history data is an example of the distribution information for query history data.

[0054] The distribution data for reference data is the data included in the reference dataset distributed according to a predetermined axis. The distribution data for query history data is the data included in the query history dataset distributed according to a predetermined axis.

[0055] The predetermined axes represent the coordinate axes of the vectors obtained when the data contained in the dataset is vectorized and subjected to predetermined vector processing. The axes for the distribution data of the reference data and the axes for the distribution data of the query history are the same.

[0056] Distribution data may include location information of data included in the dataset, information about the shapes to be displayed, and so on.

[0057] The storage unit 250 stores the analysis result data 251, which will be described later. The storage unit 250 also stores the dataset received by the receiving unit 210.

[0058] The distribution unit 270 distributes the data contained in the dataset. Specifically, it distributes the data contained in the query history dataset (query history data) and the data contained in the reference dataset (reference data), and obtains the data's positional information, which will be described later. Details of the distribution process will be described later.

[0059] ≪Analysis Results Data≫ The analysis result data 251 includes the classification results of the data included in the query history dataset and the classification results of the data included in the reference dataset, performed by the classification unit 230. The analysis result data 251 also includes the distribution results of the data included in the query history dataset (distribution data of query history data) and the distribution results of the data included in the reference dataset (distribution data of reference data), performed by the distribution unit 270. In other words, the analysis result data 251 includes the analysis results of the data included in the query history dataset and the analysis results of the data included in the reference dataset.

[0060] Analysis result data 251 includes the data content of the dataset, dataset identification information, classification item information, and location information.

[0061] The data in a dataset consists of some or all of the data items included in the query history dataset or the reference dataset.

[0062] Dataset identification information is information that identifies a dataset. It only needs to identify the dataset; it could be the dataset name or a number indicating the dataset.

[0063] The classification item information is information that identifies the classification item classified by the classification unit 230. The classification item information only needs to be able to identify the classified classification item, and may include a classification number, classification item name, or a word that represents the classification item.

[0064] The location information is determined by the distribution unit 270 and determines the position where the data will be displayed when displaying the analysis result data. For a two-dimensional display, X coordinates, Y coordinates, etc., are sufficient. It is sufficient to determine the position where the data will be displayed, and it does not have to be coordinates. The location information indicates the distribution of the data. The location information indicates the position of the data within the distribution.

[0065] Figure 6 is a diagram illustrating an example of the analysis result data according to this embodiment.

[0066] Analysis result data 251 includes question / title, answer / content, dataset name, classification item number, X coordinate, and Y coordinate.

[0067] The question / title and answer / content are examples of the data content of the dataset. The dataset name is an example of dataset identification information. The classification item number is an example of classification item information. The X and Y coordinates are examples of location information.

[0068] Figure 6 shows that the query "There's a strange sound and smell..." included in the query history dataset is classified under classification item number 7, and the position where the data is displayed is X coordinate = 2.0, Y coordinate = 4.1.

[0069] Furthermore, Figure 6 shows that the reference data included in the reference dataset, titled "From a laptop..." and containing the content "The migration tool can be downloaded from the following page...", is classified under classification item number 4, and the position where the data is displayed is X coordinate = 1.2, Y coordinate = 3.0.

[0070] In Figure 6, the analysis results data 251 is structured to include the analysis results of the data included in the inquiry history dataset and the analysis results of the data included in the reference dataset. However, the analysis results of the data included in the inquiry history dataset and the analysis results of the data included in the reference dataset may be treated as separate data sets.

[0071] ≪Example of display of analysis result data≫ An example of how to display the analysis results data will be explained with reference to Figure 7. Figure 7 is a diagram illustrating an example of how to display the analysis results according to this embodiment. A user who manages the reference dataset (hereinafter referred to as the administrator) can understand the distribution of data included in the inquiry history dataset and the distribution of data included in the reference dataset by referring to the display of the analysis results.

[0072] The analysis results display area 804, which displays the analysis results data, includes a figure 804-1 showing each data (inquiry history data) included in the inquiry history dataset, a figure 804-2 showing each data (reference data) included in the reference dataset, and classification item information 804-3 showing the classification items.

[0073] Figure 804-1, which shows each data point included in the inquiry history dataset, illustrates the distribution of the data included in the inquiry history dataset. Figure 804-1, which shows each data point included in the inquiry history dataset, is displayed at a location based on the location information included in the analysis result data. Figure 804-1, which shows each data point included in the inquiry history dataset, is an example of the first figure.

[0074] Figure 804-1, which represents each data item included in the inquiry history dataset, has a different shape depending on the classified category. A different shape means that the appearance of the figure is different. This includes, for example, different colors, shapes, sizes, or transparency.

[0075] In Figure 7, the shape of Figure 804-1, which represents each data item included in the inquiry history dataset, differs depending on the classification item it is categorized under. For example, data classified under item number 7, where the representative word for the classification item is "hand, finger," is displayed as a star shape. Similarly, data classified under item number 5, where the representative word for the classification item is "notebook PC, startup," is displayed as a triangle shape.

[0076] Figure 804-2, which shows each data point in the reference dataset, illustrates the distribution of the data included in the reference dataset. Figure 804-2, which shows each data point in the reference dataset, is displayed at a location based on the location information included in the analysis result data. Figure 804-2, which shows each data point in the reference dataset, is an example of the second type of figure.

[0077] Figure 804-2, which represents each data item in the reference dataset, has a different shape from Figure 804-1, which represents each data item in the query history dataset.

[0078] In Figure 7, the figure 804-2 representing each data point in the reference dataset is displayed as a large circle with transparency (transparency of 1 or greater). The size of the figure 804-2 representing each data point in the reference dataset may be constant, or it may vary in size depending on the size of the data.

[0079] When Figure 804-2 is displayed as a large circle, administrators can easily understand what kind of data the referenced data contains. Furthermore, the difference in size between Figure 804-1 and Figure 804-2 makes it easier to determine whether the displayed figure represents data included in the reference dataset or data included in the query dataset.

[0080] In the analysis results display area 804, the distribution of data included in the inquiry history dataset and the distribution of data included in the inquiry history dataset are displayed together. Displaying them together means that both are displayed on the same screen, and they can be displayed redundantly or side by side.

[0081] In Figure 7, the distribution of data included in the inquiry history dataset (inquiry history data) and the distribution of data included in the reference dataset (reference data) are displayed overlappingly (overlaid).

[0082] Classification item information 804-3 indicates the classified classification items displayed around classification item information 804-3.

[0083] In this way, by displaying both the data distribution in the inquiry history dataset and the data distribution in the reference dataset together, administrators can understand the differences between the data distribution in the inquiry history dataset and the data distribution in the reference dataset.

[0084] For example, in Figure 7, there are multiple triangular shapes, but no great circles in their positions. Therefore, the administrator can understand the difference in distribution: although there are multiple data points in the inquiry history dataset classified under classification item number 5, there are no data points in the reference dataset classified under classification item number 5.

[0085] For example, in Figure 7, there are a few inverted triangle shapes, and large circles are concentrated around them. Therefore, the administrator can see the difference in distribution: there is a small amount of data in the inquiry history dataset classified under classification item number 7, but a large amount of data in the reference dataset classified under classification item number 5.

[0086] Understanding the differences between the data distribution in the inquiry history dataset and the data distribution in the reference dataset allows administrators managing the reference dataset to determine what data should be added to the reference dataset or what data should be removed from it.

[0087] <Processing procedure of the first embodiment> The processes performed by the information processing system 1000 will be explained with reference to Figures 8 and 9.

[0088] Figure 8 shows an example of the processing sequence of the information processing system according to this embodiment.

[0089] In step S101, the transmitting unit 120 of terminal 100 requests the information processing device 200 to display the dataset registration screen. The receiving unit 210 of the information processing device 200 receives the request.

[0090] In step S102, the generation unit 240 of the information processing device generates screen data for the dataset registration screen in response to the request to display the dataset registration screen received from the terminal 100 in step S101. The output unit 220 of the information processing device outputs the screen data for the dataset registration screen to the terminal 100. The receiving unit 110 of the terminal 100 receives the screen data for the dataset registration screen from the information processing device 200.

[0091] The dataset registration screen includes fields for setting configuration information and fields for configuring the dataset.

[0092] Configuration information refers to information that indicates the settings used when analyzing data in a dataset. This includes, for example, model settings, language settings, and extraction settings.

[0093] Model configuration information refers to the model information used when vectorizing data.

[0094] Language settings information determines the language of the dataset. The language settings information is determined according to the language of the data contained in the dataset, as set in the dataset settings section. For example, if the dataset contains Japanese data, the language setting information will be set to Japanese.

[0095] Extraction settings information is used to define the conditions for extracting specific data from the inquiry history dataset. An example of extraction settings information is period information. For example, if you want to analyze only the inquiry data from a specified period within the inquiry history dataset, you would set information indicating that period. Similarly, if you want to analyze only the inquiry data for a specific product within the inquiry history dataset, you would set information indicating that product.

[0096] The dataset settings section is where you configure the datasets. Multiple datasets can be configured in this section.

[0097] In step S103, the display control unit 140 of the terminal 100 displays the dataset registration screen based on the screen data of the dataset registration screen received in step S102.

[0098] In step S104, the reception unit 130 of terminal 100 receives operations from the administrator. The administrator inputs setting information and performs operations to configure the dataset on the dataset registration screen. The reception unit 130 of terminal 100 receives input of setting information and operations to configure the dataset.

[0099] The following explanation assumes that the query history dataset 151 and the reference dataset 152, both stored in the memory unit 150 of terminal 100, are selected as the dataset.

[0100] In step S105, the transmitting unit 120 of terminal 100 transmits the configuration information entered in step S104, and the selected datasets, the query history dataset 151 and the reference dataset 152, to the information processing device 200. The transmission of the configuration information and datasets may also serve as a request for analysis of the data contained in the datasets. The receiving unit 210 of the information processing device 200 receives the configuration information, query history dataset, and reference dataset transmitted from terminal 100. The storage unit 250 stores the received query history dataset and reference dataset.

[0101] In step S106, the information processing device 200 analyzes the data contained in each dataset received in step S105. Details of the data analysis process will be described later.

[0102] In step S107, the storage unit 250 of the information processing device 200 stores analysis result data 251, which is the result of analyzing the data included in the dataset in step S106. The analysis result data 251 includes the analysis results of the data included in the query history dataset and the analysis results of the data included in the reference dataset. The analysis result data 251 includes items such as the data content of the dataset, dataset identification information, classification item information, and location information.

[0103] In step S108, the transmitting unit 120 of terminal 100 sends a request for output of analysis results to the information processing device 200. The receiving unit 210 of the information processing device 200 receives the request for output of analysis results from terminal 100.

[0104] In step S109, the generation unit 240 of the information processing device 200 generates distribution data of the data included in the reference dataset (reference data) and distribution data of the data included in the query history dataset (query history data) based on the analysis results from step S106, in response to the output request for analysis results received in step S108. In other words, the generation unit 240 generates data for displaying screen data on the analysis results screen.

[0105] The output unit 220 of the information processing device 200 outputs data to the terminal 100 for displaying the analysis results screen. The data for displaying the analysis results screen includes distribution data of data (reference data) included in the reference dataset generated by the generation unit 240 and distribution data of data (inquiry history data) included in the inquiry history dataset. In other words, it outputs data that includes distribution data of data (reference data) included in the reference dataset generated by the generation unit 240 and distribution data of data (inquiry history data) included in the inquiry history dataset. The receiving unit 110 of the terminal 100 receives the data for displaying the analysis results screen from the information processing device 200.

[0106] In step S110, the display control unit 140 of the terminal 100 displays an analysis results screen based on the data received in step S109.

[0107] In this embodiment, terminal 100, which sent the configuration information and dataset, requests the output of the analysis results screen and displays the analysis results screen. However, a terminal other than the one that sent the configuration information and dataset may also request the output of the analysis results screen and display the analysis results screen.

[0108] In this embodiment, an example of sending a dataset from terminal 100 to information processing device 200 was shown, but a configuration in which multiple data items that are not grouped together like a dataset are sent individually is also possible. Alternatively, terminal 100 may send information indicating the location of the dataset or data to information processing device 200, and information processing device 200 may retrieve the dataset or data from, for example, a data server 300 based on the location information.

[0109] Referring to Figure 9, the process of analyzing the data included in the dataset (step S106) will be explained in detail. Figure 9 is an example of a flowchart of the process of analyzing the data included in the dataset according to this embodiment.

[0110] In step S106-1, the classification unit 230 extracts a portion of the data included in the query history dataset based on the extraction setting information included in the setting information received in step S105.

[0111] If the extraction setting information is "Period: This fiscal year", the classification unit 230 extracts only the data from the inquiry history dataset whose reception date is within this fiscal year.

[0112] If no extraction settings are configured, all data contained in the query history dataset will be extracted. Subsequent steps will be performed on the data extracted from the query history dataset and the data contained in the reference dataset.

[0113] In step S106-2, the classification unit 230 vectorizes the data using the model set in the model setting information included in the setting information received in step S105. An embedding model or the like can be used for data vectorization. Alternatively, a model trained on specific data or a model adjusted for each industry may be used.

[0114] By vectorizing data, it's possible to determine the data's position based on its content and reflect its characteristics. Displaying the data at this position allows for understanding its content or features. Furthermore, when multiple data points are displayed, it's possible to understand the relationships, such as similarities, between them.

[0115] In step S106-3, the classification unit 230 classifies the data vectorized in step S106-2. Classification may be performed using a clustering method. For example, k-means, GMM, OPTICS, DBSCAN, HDBSCAN, etc., can be used. The classification items are determined during clustering, and each data point in the dataset is classified into the determined classification item.

[0116] Furthermore, classification is not limited to clustering. Classification can also be performed using rules based on predetermined classification criteria.

[0117] In step S106-4, the distribution unit 270 acquires the position information of each data point. Specifically, it performs dimensionality reduction on the vectorized data in step S106-2. Dimensionality reduction can be performed using methods such as PCA, t-SNE, or UMAP. The dimensions after dimensionality reduction can be two or three. The coordinates of the dimensionality-reduced vector represent the position information.

[0118] In step S106-2, the coordinate axes of the vector obtained by dimensionality reduction are the axes of the distribution. Since the data included in the reference dataset and the data included in the query history dataset undergo the same vectorization and vector processing, the axes of the distribution of the data included in the reference dataset and the axes of the distribution of the data included in the query history dataset are the same.

[0119] <Display of the first embodiment> The various screens displayed by the display control unit 140 of the terminal 100 will be explained using Figures 10 to 13.

[0120] ≪Dataset Registration Screen≫ Figure 10 shows an example of the display of the screen for registering a dataset according to this embodiment. Specifically, it is an example of the dataset registration screen displayed on terminal 100 in step S103 of Figure 8.

[0121] The dataset registration screen 700 includes a display button for the dataset registration screen 701, a display button for the analysis results screen 702, a model settings field 703, a language settings field 704, a query history dataset settings field 705, a reference dataset settings field 706, an extraction settings field 707, and an execute button 708.

[0122] The Dataset Registration Screen Display Button 701 is a button for displaying the Dataset Registration Screen. When the Dataset Registration Screen Display Button 701 is pressed, the output unit 220 of the terminal 100 requests the Dataset Registration Screen data from the information processing device 200.

[0123] The analysis results screen display button 702 is a button for displaying the analysis results screen. Details of the analysis results screen will be described later. When the analysis results screen display button 702 is pressed, the transmission unit 120 of the terminal 100 requests the screen data of the analysis results screen from the information processing device 200.

[0124] The Model Settings field 703 is where information about the model used to vectorize the data contained in the dataset is set. In the Model Settings field 703, the administrator selects the model to be used when vectorizing the data contained in the dataset from multiple options. In the example in Figure 10, the Model Settings field 703 is displayed as a dropdown menu. The display method (model selection method) of the Model Settings field 703 is not limited to a dropdown menu; any method such as radio buttons or text input is acceptable. Furthermore, if there is no need to set model information, the Model Settings field 703 does not need to be displayed.

[0125] The language setting field 704 is for setting the language of the dataset. Enter the language according to the dataset you are registering. In the example in Figure 10, it is displayed as a dropdown menu. The display method (language selection method) of the language setting field 704 is not limited to a dropdown menu. Any method is acceptable, such as radio buttons or text input. Also, if there is no need to set a language, the language setting field 704 does not need to be displayed.

[0126] The inquiry history dataset setting field 705 is for setting the inquiry history dataset. In the example in Figure 10, a file list is opened from the file selection button, and the dataset can be selected. The display method of the inquiry history dataset setting field 705 is not limited to this. It may also be displayed so that the user can select the file by dragging and dropping, or it may be displayed so that the user can enter the location where the dataset stored on the data server 300 is saved.

[0127] The Reference Dataset Settings field 706 is for setting the reference dataset. In the example in Figure 10, the file list is opened via the file selection button, and the dataset can be selected. The display method of the Reference Dataset Settings field 706 is not limited to this. It may also be displayed as a drag-and-drop selection of the desired file, or as a prompt to enter the location where the dataset stored on the data server 300 is saved.

[0128] The extraction settings field 707 is a field for setting information (extraction settings information) that sets the conditions for extracting some data from the inquiry history dataset. In the example in Figure 10, the extraction settings field 707 is a field for setting period information as extraction settings information, where you can set the period you want to analyze from the inquiry history dataset. In the example in Figure 10, the extraction settings field 707 is displayed as a dropdown menu. The display method of the extraction settings field 707 is not limited to a dropdown menu; it may also be displayed as a field for entering a date range. Furthermore, the extraction settings information is not limited to period information.

[0129] The execute button 708 is used to register the entered configuration information and dataset. When the execute button 708 is pressed, the transmission unit of the terminal 100 sends the entered configuration information, inquiry history dataset, and reference dataset to the information processing device 200.

[0130] ≪Analysis result screen≫ Figure 11 shows an example of the display of the screen showing the analysis results according to this embodiment. Specifically, it is an example of the analysis results screen displayed on the display control unit 140 of the terminal 100 in step S110 of Figure 8. The analysis results display screen 800 includes a data set registration screen display button 801, an analysis results screen display button 802, a bibliographic display field 803, an analysis results display field 804, and a classification item display field 805.

[0131] The Dataset Registration Screen Display Button 801 is a button used to display Dataset Registration Screen 700. It is the same button as the Dataset Registration Screen Display Button 701 on Dataset Registration Screen 700.

[0132] The "Show Analysis Results Screen" button 802 is used to display the analysis results screen. It is the same button as the "Show Analysis Results Screen" button 702 on the "Dataset Registration Screen" 700.

[0133] The bibliographic information field 803 displays bibliographic information about the analyzed dataset. In Figure 11, the bibliographic information field 803 includes the registered file field, analysis target field, language information field, registration date and time field, registrant field, and analysis result download field.

[0134] The "Registered File" field displays the file name and extension of the dataset (analyzed dataset) registered on the dataset registration screen. The "Analysis Target" field displays information about the model set on the dataset registration screen.

[0135] The language information field displays the language information registered on the dataset registration screen. The registration date and time field displays the date and time when the dataset and settings information were registered.

[0136] The registrant section displays information about the administrator who registered the dataset and configuration settings. The analysis results download section displays a button for downloading the analysis results.

[0137] The bibliographic display field 803 shown in Figure 11 is just one example. It is not necessary to display all the items shown in Figure 11; other information set on the dataset registration screen may be displayed instead.

[0138] Analysis results display area 804 is a field that displays the analysis results of the data included in the dataset. Details of analysis results display area 804 are as explained in Figure 7. The display method of analysis results display area 804 is not limited to the method explained in Figure 7. The distribution of data included in the inquiry history dataset and the distribution of data included in the inquiry history dataset do not need to be displayed together; they may be displayed side by side. The distribution of data included in the inquiry history dataset and the distribution of data included in the reference dataset are displayed together.

[0139] The classification item display field 805 is a field that displays details about each classification item into which the classification unit 230 has classified the data included in the dataset. In Figure 11, the classification item number, the word representing the classification item, the number of data items in the query history dataset that are classified under that classification item, and the number of data items in the reference dataset that are classified under that classification item are displayed. In Figure 11, it is shown that eight data items in the query history dataset and three data items in the reference dataset are classified under the classification item "mouse, wireless" with classification number 3 and the word representing the classification item.

[0140] Interaction Figures 12 and 13 illustrate the interaction on the analysis results display screen 800 and other display examples of the analysis results display screen 800. For configurations similar to those in Figure 11, the same symbols used in Figure 11 are assigned, and their explanations are omitted.

[0141] Figure 12 shows an example of user interaction on the screen displaying the analysis results according to this embodiment. In the analysis results display area 804, the administrator can perform operations such as scrolling, dragging, zooming in (pinching in), and zooming out (pinching out). The reception unit 130 of the terminal 100 receives operations from the administrator. The analysis results display area 804 changes its display according to the operations from the administrator.

[0142] Figure 12 shows an example where the administrator has performed a pinch-in operation, and the display area of ​​the data classified under classification item number 3, the representative word for the classification item "mouse, wireless," is enlarged.

[0143] Figure 13 shows an example of user interaction on the screen displaying the analysis results according to this embodiment. Figure 13 also shows another example of the analysis results display screen 800.

[0144] The analysis results display screen 800 shown in Figure 13 has a data display area 806 in addition to the configuration described in Figure 11. Furthermore, a pointer 807 indicating the area to be operated by the administrator is displayed on the analysis results display screen 800.

[0145] Data display field 806 displays details of data categorized under the classification items selected by the administrator. The content displayed in data display field 806 is included in the analysis result data. In Figure 13, the classification item number, question / title, answer / content, and dataset name (file) from the analysis result data are displayed.

[0146] The administrator may select classification items in the analysis results display field 804 or in the classification item display field 805.

[0147] In Figure 13, the classification item "Notebook PC, Startup" with classification item number 5 and the representative word for the classification item "Notebook PC, Startup" is selected, with the pointer 807 displayed in the analysis results display area 804. The data classified under classification item number 5 is displayed in the data display area 806.

[0148] Specifically, data display area 806 shows data from the inquiry history dataset, categorized under classification item number 5, with the question "On my laptop..." and the answer "Check tool...". Additionally, data display area 806 also shows data from the reference dataset, categorized under classification item number 5, with the title "Turned on..." and the content "Error code...".

[0149] <Effects of the First Embodiment> According to this embodiment, the terminal 100 transmits configuration information (model configuration information, language configuration information, extraction configuration information), a query history dataset, and a reference dataset to the information processing device 200. The information processing device 200 can then analyze the data contained in the query history dataset and the reference dataset based on the configuration information. The information processing device 200 can extract data from the received dataset based on the extraction configuration information, vectorize the data contained in the dataset based on the model configuration information and language information, and classify the data contained in the dataset. It can also distribute the data contained in the dataset.

[0150] Furthermore, according to this embodiment, the information processing device 200 can generate an analysis results screen that displays both the distribution of data included in the inquiry history dataset and the distribution of data included in the reference dataset. The terminal 100 can display the analysis results screen that displays both the distribution of data included in the inquiry history dataset and the distribution of data included in the reference dataset.

[0151] The system can display an analysis results screen that shows both the data distribution in the inquiry history dataset and the data distribution in the reference dataset, allowing administrators to understand the differences between the data distribution in the inquiry history dataset and the data distribution in the reference dataset.

[0152] By understanding the differences in data distribution between the inquiry history dataset and the reference dataset, administrators can determine what data should be added to the reference dataset or what data should be removed from it.

[0153] <Functional configuration in the second embodiment> A second embodiment is described below. The difference between the first and second embodiments is that, in addition to the first embodiment, the second embodiment determines the classification items to be presented to the administrator and displays the determined classification items. In the following description of the second embodiment, the differences from the first embodiment will be explained, and components having the same functional configuration as the first embodiment will be assigned the same reference numerals as those used in the description of the first embodiment, and their explanations will be omitted.

[0154] The functional configuration of the second embodiment will be explained using Figure 14. Figure 14 is a functional configuration diagram of an example of an information processing system according to this embodiment.

[0155] The information processing system 1000A of the second embodiment includes a terminal 100, an information processing device 200A, and a data server 300. The configuration other than the information processing device 200A is the same as that of the information processing system 1000 of the first embodiment.

[0156] The information processing device 200A has the same functional configuration as the information processing device 200 of the first embodiment, plus a determination unit 260.

[0157] The decision unit 260 determines the classification items to present to the administrator. The classification items to present to the administrator are classification items that are presented to the administrator in a way that is different from other classification items. Presenting them in a way that is different means, for example, highlighting the classification item so that it can be understood, displaying it in an identifiable way, or describing details about the classification item. The classification items to present to the administrator may also be classification items that recommend actions to the administrator, such as classification items that should be supplemented with reference datasets or classification items that should have data in the reference datasets reduced.

[0158] The decision unit 260 determines whether or not to present a classification item to the administrator, using the number of data items classified into that classification item in the analysis results of the data included in the inquiry history dataset and the number of data items classified into that classification item in the classification results of the reference dataset, for each classification item that the classification unit 230 has classified the data included in the dataset. The decision on whether or not to present a classification item to the administrator may also be based on presentation condition settings.

[0159] Presentation condition settings refer to the conditions or priorities used to determine the classification items to be presented to the administrator. For example, presentation condition settings may involve setting a threshold for the difference between the number of data items classified under that category in the analysis results of the data included in the inquiry history dataset and the number of data items classified under that category in the classification results of the reference dataset.

[0160] The presentation conditions can be set by specifying that the classification item presented to the administrator is the one with the largest difference between the number of data items classified under that category in the analysis results of the data included in the inquiry history dataset and the number of data items classified under that category in the classification results of the reference dataset. Alternatively, the presentation conditions can be set by specifying a priority order, such as presenting classification items to the administrator in order of the largest difference between the number of data items classified under that category in the analysis results of the data included in the inquiry history dataset and the number of data items classified under that category in the classification results of the reference dataset.

[0161] The presentation conditions could also include setting a condition that a classification item should be presented to the administrator if the difference between the number of data items classified under that classification item in the analysis results of the data included in the inquiry history dataset and the number of data items classified under that classification item in the classification results of the reference dataset is greater than or equal to a threshold, AND the number of data items classified under that classification item in the classification results of the reference dataset is 0.

[0162] <Processing procedure of the second embodiment> The processing procedure of the second embodiment will be described using Figures 15 and 16. Figure 15 is an example of the processing sequence of the information processing system according to this embodiment.

[0163] The processing in steps S201 to S206 is the same as steps S101 to S106 in Figure 8.

[0164] In step S207, the decision unit of the information processing device 200A determines the classification items to present to the administrator. For each classification item into which the classification unit 230 has classified the data included in the dataset, the decision unit 260 uses the number of data items classified into that classification item in the analysis results of the data included in the inquiry history dataset and the number of data items classified into that classification item in the classification results of the data included in the reference dataset to determine whether or not to present that classification item to the administrator. Details will be described later with reference to Figure 16.

[0165] Steps S208 and S209 are the same as steps S107 and S209 in Figure 8.

[0166] In step S210, the generation unit 240, in response to the output request for display of the analysis result screen received in step S108, generates distribution data of the data included in the reference dataset (reference data) and distribution data of the data included in the inquiry history dataset (inquiry history data) based on the analysis results in step S206. The generation unit 240 also generates data for displaying the classification items to be presented to the administrator, which were determined in step S207. In other words, the generation unit 240 generates data for displaying the analysis result screen on the terminal. The data for displaying the analysis result screen includes distribution data of the data included in the reference dataset (reference data), distribution data of the data included in the inquiry history dataset (inquiry history data), and data for displaying the classification items determined in step S207.

[0167] Referring to Figure 16, the determination of classification items to be presented to the administrator (step S207) will be explained in detail. Figure 16 is an example of a flowchart of the process for determining classification items to be presented to the administrator according to this embodiment.

[0168] In step S207-1, the decision unit 260 calculates the difference between the number of data items classified into that category in the analysis results of the data included in the query history dataset and the number of data items classified into that category in the classification results of the reference dataset, for each category item that the classification unit 230 has classified the data included in the dataset.

[0169] In step S207-2, the determination unit 260 determines the classification items to be presented to the administrator based on the difference calculated in step S207-1 and the presentation condition settings.

[0170] For example, if the presentation condition setting is that the classification item with the largest difference calculated in step S207-1 will be presented to the administrator, the determination unit 260 will determine that the classification item with the largest difference calculated in step S207-1 will be presented to the administrator.

[0171] <Analysis results screen display in the second embodiment> The display of the analysis results screen in the second embodiment will be explained using Figures 17 and 18. The difference between the display of the analysis results screen in the second embodiment and the display of the analysis results screen in the first embodiment is that the display of the analysis results screen in the second embodiment includes a display showing the classification items that the decision unit 260 has determined and presents to the administrator. Components similar to those in the first embodiment are given the same reference numerals and their explanations are omitted.

[0172] Figure 17 shows an example of the display of the screen showing the analysis results according to this embodiment. Figure 17 shows an example of the analysis results screen displayed on terminal 100 in step S210 of Figure 15. As a display indicating the classification items to be presented to the administrator determined by the decision unit 260, a figure 808 indicating the classification items to be presented to the administrator is displayed in the analysis results display field 804 of the analysis results display screen 800.

[0173] Figure 17 shows an example of a shape 808 representing classification items to be presented to the administrator, which is an unfilled circle. The shape 808 representing classification items to be presented to the administrator may be any other shape.

[0174] In Figure 17, the classification item number 5 and the representative term for the classification item, "Notebook PC, Startup," are presented to the administrator by graphic 808, which shows the classification items to be presented to the administrator.

[0175] Figure 18 shows an example of the display of the screen showing the analysis results according to this embodiment. Figure 18 shows an example of the analysis results screen shown on terminal 100 in step S210 of Figure 15.

[0176] In Figure 18, the classification item presentation field 809 is displayed on the analysis result display screen 800 as a display showing the classification items that the decision unit 260 has decided to present to the administrator. The classification item presentation field 809 is a field that displays the classification items that the decision unit 260 has decided to present to the administrator.

[0177] In Figure 18, the classification item presentation field 809 displays the classification item number indicating the classification item to be presented to the administrator, a word representing the classification item, and details of the data included in the inquiry history dataset that have been classified under that classification item. The content displayed in the classification item presentation field 809 is not limited to this. The classification item presentation field 809 may also include the number of data items classified under that classification item in the analysis results of the data included in the inquiry history dataset, or the number of data items classified under that classification item in the classification results of the reference dataset.

[0178] Figure 18 shows that the classification item number 5, with the representative term "notebook PC, startup," is presented to the administrator. It can also be seen that the data classified under classification item number 5 includes the inquiry "When I press the power button on my notebook PC, it shuts down a few seconds later," which is included in the inquiry history dataset.

[0179] The administrator of the reference dataset can understand what kinds of queries are included in the presented classification items, making it easy to determine what data should be added to the reference dataset.

[0180] <Effects of the second embodiment> According to this embodiment, the classification unit 230 can determine which classification items to present to the administrator by using the number of data items classified into that classification item in the analysis results of the data included in the inquiry history dataset, the number of data items classified into that classification item in the classification results of the reference dataset, and the presentation condition settings for each classification item in which the classification unit 230 has classified the data included in the dataset.

[0181] Furthermore, according to this embodiment, the analysis results screen displayed on the terminal 100 can display the classification items to be presented to the administrator, which have been determined by the determination unit 260.

[0182] The analysis results screen displays the classification items presented to the administrator, allowing the administrator managing the reference dataset to understand which classification items should be added or deleted. Therefore, the administrator can understand what data should be added to the reference dataset, or which data should be removed from it.

[0183] On the analysis results screen, the classification items presented to the administrator, along with details of the data classified under those items within the inquiry history dataset, are displayed. This allows the administrator to understand the content of the data in the inquiry history dataset classified under the presented classification items. Therefore, the administrator can easily understand what data should be added to the reference dataset or what data should be removed from the reference dataset.

[0184] Although the present invention has been described above based on various embodiments, the present invention is not limited to the requirements shown in the above embodiments. These points can be modified as long as they do not impair the spirit of the present invention, and can be appropriately determined according to their application.

[0185] For example, a process that would normally be performed by multiple devices may be performed by a single device, and a process that would normally be performed by a single device may be performed by multiple devices.

[0186] [supplement] Each of the functions of the embodiments described above can be realized by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), FPGAs (field programmable gate arrays), and conventional circuit modules designed to execute each of the functions described above. [Explanation of Symbols]

[0187] 1000: Information Processing Systems 100: Terminal 110: Receiver 120: Transmitter 130: Reception Department 140: Display Control Unit 150: Storage section 200: Information Processing Device 210: Receiver 220: Output section 230: Classification department 240: Generation part 250: Storage section 260: Decision Section 270: Distribution part 300: Data Server [Prior art documents] [Patent Documents]

[0188] [Patent Document 1] Japanese Patent Publication No. 2006-065366

Claims

1. An information processing device capable of communicating with a terminal, A storage unit that stores multiple reference data sets that are pre-prepared for the user handling the inquiry to refer to when handling the inquiry, and multiple inquiry history data sets that show the history of each inquiry. A generation unit generates distribution information which is the distribution of the reference data and the query history data, respectively, by distributing the plurality of reference data and the plurality of query history data along a predetermined axis. An output unit that outputs data including the distribution information of the generated reference data and the distribution information of the query history data to the terminal for display on the terminal, An information processing device having

2. The system further includes a receiving unit that receives the aforementioned plurality of reference data and the aforementioned plurality of query history data from the terminal or a terminal other than the aforementioned terminal. The storage unit stores the received plurality of reference data and the plurality of query history data. The information processing apparatus according to claim 1.

3. The system further includes a classification unit that classifies each of the multiple reference data and each of the multiple query history data into predetermined classification items. The generation unit generates distribution information for the reference data and distribution information for the query history data, which are obtained by distributing each of the classified data of the plurality of reference data and each of the plurality of query history data along the predetermined axis. The information processing apparatus according to claim 1.

4. The classification unit performs the same vectorization process on each of the multiple reference data and each of the multiple query history data. Each of the data from the plurality of reference data and each of the data from the plurality of query history data, which have undergone the same vectorization process, are classified into the predetermined classification items. The information processing apparatus according to claim 3.

5. The classification unit analyzes the plurality of reference data and the plurality of query history data to determine a predetermined classification item, and classifies each of the plurality of reference data and each of the plurality of query history data according to the determined predetermined classification item. The information processing apparatus according to claim 3.

6. The output unit, upon receiving an output request transmitted from the terminal, outputs the distribution information of the generated reference data and the distribution information of the query history data to the terminal. The information processing apparatus according to claim 1.

7. The generating unit is By displaying a first figure representing each data in the query history data at the position of each data in the distribution of the query history data, and displaying a second figure representing each data in the reference data at the position of each data in the distribution of the reference data, the distribution information of the reference data and the distribution information of the query history data are generated in order to display the distribution of the query data and the distribution of the reference data superimposed. The information processing apparatus according to claim 1.

8. The first figure and the second figure have different shapes. The information processing apparatus according to claim 7.

9. The system further includes a determination unit that determines which classification item to present to the user for each of the predetermined classification items, using the number of data items classified under that classification item from the inquiry history data and the number of data items classified under that classification item from the reference data. The output unit outputs data to the terminal for displaying the classification item determined by the determination unit. The information processing apparatus according to any one of claims 3 to 5.

10. The aforementioned reference data includes a history of responses to past inquiries, or product manuals. The information processing apparatus according to any one of claims 1 to 8.

11. The generation unit generates distribution information for the reference data and distribution information for the query history data, which are used to display the distribution of the query data and the distribution of the reference data side by side. The information processing apparatus according to claim 1.

12. A storage unit that stores multiple reference data sets that are pre-prepared for the user handling the inquiry to refer to when handling the inquiry, and multiple inquiry history data sets that show the history of each inquiry. A generation unit that generates distribution information, which is the distribution of the reference data and the query history data, respectively, by distributing the plurality of reference data and the plurality of query history data along a predetermined axis, An output unit outputs data for display, which includes the distribution information of the generated reference data and the distribution information of the query history data. An information processing device having

13. An information processing method performed by a computer capable of communicating with a terminal, A storage step that stores multiple reference data sets that are pre-prepared for the user handling the inquiry to refer to when handling the inquiry, and multiple inquiry history data sets that show the history of each inquiry. A generation step to generate distribution information which is distribution information of the reference data and the query history data, respectively, which is distribution information of the reference data and the query history data distributed along a predetermined axis. An output step of outputting data including the distribution information of the generated reference data and the distribution information of the query history data to the terminal for display on the terminal, An information processing method having

14. To a computer that can communicate with the terminal, A storage step that stores multiple reference data sets that are pre-prepared for the user handling the inquiry to refer to when handling the inquiry, and multiple inquiry history data sets that show the history of each inquiry. A generation step to generate distribution information which is distribution information of the reference data and the query history data, respectively, which is distribution information of the reference data and the query history data distributed along a predetermined axis. An output step of outputting data including the distribution information of the generated reference data and the distribution information of the query history data to the terminal for display on the terminal, A program that executes the command.

15. An information processing system including a terminal and an information processing device, The aforementioned information processing device is A storage unit that stores multiple reference data sets that are pre-prepared for the user handling the inquiry to refer to when handling the inquiry, and multiple inquiry history data sets that show the history of each inquiry. A generation unit that generates distribution information, which is the distribution of the reference data and the query history data, respectively, by distributing the plurality of reference data and the plurality of query history data along a predetermined axis, An output unit that outputs data including the distribution information of the generated reference data and the distribution information of the query history data to the terminal for display on the terminal, It has, The aforementioned terminal is A display control unit that displays the distribution information of the reference data and the distribution information of the query history data. An information processing system having

Images