JP7185888B1 - Information processing system, information processing method and information processing program - Google Patents

Abstract

An information processing system, an information processing method, and an information processing program are provided that make it easier for a user to specify a search range suitable for efficient searching of explanatory variables. In an information processing system in which an information processing device, a user terminal, and a database communicate with each other through an electric communication line, a control unit 23 of the information processing device comprising a communication unit, a storage unit, and a control unit is configured to: A data reception unit 231 that receives input data, an extraction unit 232 that extracts explanatory variables from the learning model based on the input data, and a search range for the extracted explanatory variables according to the format of the explanatory variables. and a visual information generator 234 that generates specifiable visual information. [Selection drawing] Fig. 4

Description

The present invention relates to an information processing system, an information processing method, and an information processing program.

As prior art, the following documents regarding learning devices can be cited.

Japanese Unexamined Patent Application Publication No. 2021-177428

When making predictions using a learning model, explanatory variables that maximize the objective function may be sought. However, in order to improve the efficiency of searching for explanatory variables, a relatively high level of knowledge about data science may be required.

(1) According to one aspect of the present invention, an information processing system is provided. This information processing system includes a control unit. The controller is configured to perform the following steps. The data receiving step receives input of input data. In the extracting step, explanatory variables are extracted from the learning model based on the inputted input data. In the visual information generation step, visual information is generated that can designate a search range for the extracted explanatory variables according to the format of the explanatory variables.

According to such an information processing system, it becomes easier for the user to specify a search range suitable for searching for explanatory variables more efficiently than in the prior art.

1 is a configuration diagram showing an information processing system 1; FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2; FIG. 3 is a block diagram showing the hardware configuration of the user terminal 3; FIG. An example of a functional unit included in the control unit 23 is shown. 4 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1; FIG. It is an example of display contents displayed on the display unit 34 .

Embodiments of the present invention will be described below with reference to the drawings. Various features shown in the embodiments shown below can be combined with each other.

By the way, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable medium (Non-Transitory Computer-Readable Medium), or may be downloaded from an external server. It may be provided as possible, or may be provided so that the program is activated on an external computer and the function is realized on the client terminal (so-called cloud computing).

Further, in the present embodiment, the term “unit” may include, for example, a combination of hardware resources implemented by circuits in a broad sense and software information processing that can be specifically realized by these hardware resources. . In addition, various information is handled in the present embodiment, and these information are, for example, physical values of signal values representing voltage and current, and signal values as binary bit aggregates composed of 0 or 1. It is represented by high and low, or quantum superposition (so-called quantum bit), and communication and operation can be performed on a circuit in a broad sense.

A circuit in a broad sense is a circuit implemented by appropriately combining at least circuits, circuits, processors, memories, and the like. Application Specific Integrated Circuits (ASICs), programmable logic devices (e.g., Simple Programmable Logic Devices (SPLDs), Complex Programmable Logic Devices (CPLDs), and field It includes a programmable gate array (Field Programmable Gate Array: FPGA).

1. Hardware configuration This section describes the hardware configuration.

<Information processing system 1>
FIG. 1 is a configuration diagram showing an information processing system 1. As shown in FIG. The information processing system 1 includes an information processing device 2, a user terminal 3, and a database DB1. The information processing device 2, the user terminal 3, and the database DB1 are configured to be able to communicate with each other through an electric communication line. In one embodiment, information handling system 1 is comprised of one or more devices or components. If, for example, the information processing system 1 consists only of the information processing device 2 , the information processing system 1 can be the information processing device 2 . These constituent elements are described below.

<Information processing device 2>
FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2. As shown in FIG. The information processing device 2 includes a communication section 21 , a storage section 22 and a control section 23 , and these components are electrically connected via a communication bus 20 inside the information processing device 2 . Each component will be further described.

The communication unit 21 is preferably a wired type communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but wireless LAN network communication, mobile communication such as 3G/LTE/5G, BLUETOOTH (registered trademark) Communication and the like may be included as desired. That is, it is more preferable to implement as a set of these communication means. That is, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.

The storage unit 22 stores various information defined by the above description. For example, it can be used as a storage device such as a solid state drive (SSD) for storing various programs related to the information processing device 2 executed by the control unit 23, or as a temporary storage device related to program calculation. It can be implemented as a memory such as a Random Access Memory (RAM) that stores information (arguments, arrays, etc.) required for the . The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the control unit 23 .

The control unit 23 processes and controls overall operations related to the information processing device 2 . The control unit 23 is, for example, a central processing unit (CPU) (not shown). The control unit 23 implements various functions related to the information processing device 2 by reading a predetermined program stored in the storage unit 22 . That is, information processing by software stored in the storage unit 22 can be specifically realized by the control unit 23 which is an example of hardware, and can be executed as each functional unit included in the control unit 23 . These are further detailed in the next section. Note that the control unit 23 is not limited to a single unit, and may be implemented to have a plurality of control units 23 for each function. A combination thereof may also be used.

<User terminal 3>
FIG. 3 is a block diagram showing the hardware configuration of the user terminal 3. As shown in FIG. The user terminal 3 includes a communication section 31 , a storage section 32 , a control section 33 , a display section 34 and an input section 35 . properly connected. Descriptions of the communication unit 31, the storage unit 32, and the control unit 33 are omitted because they are similar to the description of each unit in the information processing apparatus 2. FIG.

The display unit 34 may be included in the housing of the user terminal 3, or may be externally attached. The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. For example, it is preferable to use a display device such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the user terminal 3 .

The input unit 35 may be included in the housing of the user terminal 3 or may be externally attached. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. With a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, a switch button, a mouse, a QWERTY keyboard, or the like may be employed instead of the touch panel. That is, the input unit 35 receives an operation input made by the user. The input is transferred as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can execute predetermined control and calculation as necessary.

<Database DB1>
Database DB1 stores external data D0. The external data D0 may be, for example, data accessible to the public or data accessible only to specific users. Also, the external data D0 may be data that can be accessed only by the user using the information processing system 1 . The database DB1 may be realized by a single storage device or may be realized by a plurality of storage devices. The contents represented by the external data D0 are arbitrary, such as hygiene observation results, climate observation results, statistical data, and the like.

2. Functional Configuration FIG. 4 shows an example of functional units provided in the control unit 23 . As shown in FIG. 4, the control unit 23 includes a data reception unit 231, an extraction unit 232, an extraction unit 232, a variable name extraction unit 233, a visual information generation unit 234, and a variable display unit 235. .

The data reception unit 231 receives the input of the input data D. FIG. The input data D is data input to the information processing device 2 . For example, the input data D may include at least one of data owned by the user and data owned by someone other than the user, such as data stored in the database DB1. Input data D includes at least structured data. Structured data is data standardized to have a predetermined structure. Note that the input data D may include data other than structured data, such as unstructured data or semi-structured data. Unstructured data is any form of data that does not have a standardized structure like structured data. Semi-structured data consists of a combination of unstructured data and tags that can identify the unstructured data. Formats of semi-structured data include, for example, graph type, key-value type, document type, and column type.

The input data D is input to the learning device ML. The learning device ML generates a learning model M1 based on the input data D that is input to the learning device ML. In addition, it is not limited to what is stored inside the information processing system 1 , and may exist outside the information processing system 1 . The learning model M1 outputs an evaluation parameter y1 based on the explanatory variable x1 included in the input data D.

The extraction unit 232 extracts the explanatory variable x1 from the learning model M1 based on the input data D that is input. A learning model M1 is generated by inputting input data D to at least one learner ML.

The learning model M1 uses the explanatory variable x1 of the input data D to derive the evaluation parameter y1. The evaluation parameter y1 may be a preset parameter or a parameter arbitrarily set by the user.

The variable name extraction unit 233 extracts from the input data D the variable name VNx representing the extracted explanatory variable x1. Although any extraction method can be used, for example, the variable name extraction unit 233 extracts information such as numbers and character strings corresponding to each explanatory variable x1 included in the input data D as the variable name VNx. Also, the variable name extraction unit 233 extracts from the input data D the variable name VNy of the evaluation parameter y1. The extraction method is the same as that for the variable name of the explanatory variable x1.

The visual information generation unit 234 generates visual information IF2 that can specify the search range of the extracted explanatory variable x1 according to the format of the explanatory variable x1. Specifically, when the extraction unit 232 extracts a plurality of explanatory variables x1, the visual information generation unit 234 generates visual information IF2 corresponding to each of the plurality of explanatory variables x1. The format of explanatory variable x1 is, for example, a character string, a numerical value, a Boolean variable, or the like. Numerical values can be of any type, including natural numbers, fractional numbers, and floating point numbers.

The visual information IF2 includes information regarding the search range of the explanatory variable x1. The information about the search range of the explanatory variable x1 can include information about whether or not the target explanatory variable x1 is used for deriving the evaluation parameter y1, and information about the maximum and minimum values of the explanatory variable x1. The visual information IF2 can function as a user interface for the user to specify the search range of the explanatory variable x1. Specific aspects of the visual information IF2 as a user interface are optional, such as check boxes, radio buttons, pull-downs, drum rolls, input forms, and sliders. Hereinafter, for convenience of explanation, the user interface may be simply referred to as UI.

When the format of the explanatory variable x1 is a character string, the visual information IF2 is configured to be able to select whether or not to input the explanatory variable x1 to the learning model M1. When the format of the explanatory variable x1 is a numerical value, the visual information IF2 is configured to be able to specify the domain of the explanatory variable x1 input to the learning model M1. In this case, the search range R is defined based on the domain. The domain of the explanatory variable x1 is also referred to as the domain of the explanatory variable x1. The visual information IF2 may be configured to specify at least one of the upper limit value and the lower limit value of the explanatory variable x1 input to the learning model M1. In this case, the search range is defined based on at least one of the upper limit and the lower limit. Especially in this embodiment, when the format of explanatory variables is numerical values, the visual information is displayed as a slider. The search range is specified based on the position of the slider. Thereby, the user can intuitively specify the search range of the explanatory variable x1 based on the visual information IF2 of the slider. The visual information IF2 may be capable of specifying the search range discretely or continuously. A discretely specifiable state means, for example, when the format of the explanatory variable x1 is a floating point, the search range of the explanatory variable x1 can be discretely specified by an integer. Note that the visual information IF2 may be capable of continuously designating the search range.

An explanatory variable x1 that changes within a designated search range R can be input to the learning model M1. The learning model M1 searches the explanatory variables x1 within the search range R for the explanatory variables x1 that satisfy a predetermined search condition. The predetermined search condition is defined, for example, by the maximum/minimum value of the evaluation parameter y1 or the relationship between the evaluation parameter y1 and a predetermined threshold value. The search condition may be arbitrarily determined by the user or automatically determined by an arbitrary algorithm. Hereinafter, for convenience of description, searching for the explanatory variable x1 that satisfies the search condition may be referred to as search simulation.
The visual information IF2 may also include information on the search range R recommended based on the search conditions. Note that the recommended search range R is not limited to that specified by the upper limit value and/or the lower limit value described above. For example, the search range R may be specified by multiple domains. The visual information generator 234 may generate visual information IF2 in which the recommended search range R is specified in advance. The designation by the visual information generator 234 may be changeable by the user.

The variable display section 235 causes the display section 34 to display the variable name VNx extracted by the variable name extraction section 233 . The display mode is arbitrary, but for example, the variable display unit 235 causes the display unit 34 to display the visual information IF2 of the explanatory variable x1 and the variable name VNx in a viewable manner.

The result display unit 236 causes the display unit 34 to display the result information IF3. The result information IF3 is output from the learning model M1 based on the explanatory variable x1 in the specified search range. The result information IF3 includes, for example, an evaluation parameter y1 and an explanatory variable x1 that satisfy a predetermined condition. Specifically, the result display unit 236 displays the visual information IF2 and the result information IF3 in a viewable manner. The result display unit 236 of this embodiment further displays the history information IF4 of the result information IF3 output in the past. The result display unit 236 displays the result information IF3 and the history information IF4 so that they can be viewed. This makes it easier for the user to compare the result information IF3 generated most recently with the result information IF3 generated in the past.

3. Details of Information Processing In this section, information processing executed in the information processing system 1 described above will be described. Note that the information processing may include any exception handling not shown in the activity diagram. Exception processing includes interruption of the information processing and omission of each processing. The selection or input performed in the information processing may be based on the user's operation, or may be automatically performed without depending on the user's operation.

FIG. 5 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1. As shown in FIG. As shown in FIG. 5, the data receiving unit 231 receives input data D in activity A001. Hereinafter, for convenience of explanation, the input data D received by the activity A001 may be referred to as the first input data D1.

Next, the process proceeds to activity A002, and the control unit 23 inputs the input data D to the learning device ML. As a result, the learning device ML generates a learning model M1 based on the input data D. FIG. At this time, the control unit 23 may input to the learning device ML the second input data D2 obtained by subjecting the first input data D1 to predetermined conversion processing. In this case, the learning device ML uses the second input data D2 to generate the learning model M1. Note that the learning device ML may be stored in an arbitrary member included in the information processing system 1 or may be stored in an external device that can communicate with the information processing system 1 via an electric communication line. Note that the illustration of the external device is omitted.

Note that the conversion process is a process of converting the first input data D1 input to the data reception unit 231 into the second input data D2 that is in a form that can be input to the specified learning device ML. The conversion processing can include arbitrary processing such as deletion of part of the first input data D1, supplementation of missing values, deletion of outliers, normalization of the first input data D1, and the like. The conversion process is also called data shaping.
The conversion process may include a combination process, a separation process, a correction, and the like of a plurality of explanatory variables x1 included in the first input data D1. For example, when the first input data D1 has year, month, and day representing time series as different explanatory variables x1, the conversion process combines these multiple explanatory variables x1 into one input. can contain Further, in the conversion process, when a plurality of first input data D1 are received by a plurality of data receiving units 231, a combining process of these first input data D1 may be performed. As another example, the conversion processing may include addition processing of explanatory variable x1, addition of feature amount, and the like. For example, the control unit 23 may acquire arbitrary external data D0 from the database DB1 according to the first input data D1 and add the external data D0 to the first input data D1. The control unit 23 may add feature amounts based on the added external data D0.
The conversion processing includes processing that can be automatically executed by the control unit 23 based on the content of the first input data D1. Note that the conversion processing may include processing that can be executed based on designation by the user. Further, in this embodiment, the conversion processing includes automatic conversion processing specified by comparing the first input data D1 with predetermined conversion conditions. The conversion conditions include, for example, the capacity of the first input data D1, whether or not the variance of the statistical information of the first input data D1 is less than a threshold, and whether or not there is an outlier based on the statistical information of the first input data D1. is. Conversion conditions also suggest the need for conversion processing to be performed.
The conversion process also includes a process of converting the format of the first input data D1 input to the data reception unit 231 into a format suitable for each of the identified learning devices ML. The format of the first input data D1 includes, for example, the name of the first input data D1, character code, line feed code, writing language, delimiter, and the like.
For example, when the character code of the input data D that can be input to the specified learning device ML is UTF-8, but the character code of the first input data D1 is Shift-JIS, the control unit 23 A conversion process is executed to convert the first input data D1 into second input data D2 whose character code is changed to UTF-8.
As another example, the conversion process may include a process of giving a name to each of the second input data D2 that can be input to the identified plurality of learners ML. At this time, it is preferable that the conversion process gives the second input data D2 a name by which the control unit 23 can uniquely identify the second input data D2. This facilitates management of the second input data D2. Note that the name may be assigned by changing the name of the first input data D1.
As another example, when the first input data D1 includes a BOM (Byte Order Mark), the conversion process may include removal of the BOM. This makes it easier to suppress unintended errors.
As another example, the conversion process may include a process of removing explanatory variables x1 included in the first input data D1 that are not used to generate the learning model M1. The control unit 23 may determine whether or not the explanatory variable x1 is used to generate the learning model M1, for example, based on the format and distribution of the explanatory variable x1. This reduces the volume of the second input data D2, thereby shortening the time required to generate the learning model M1.

Next, the process proceeds to activity A003, and the control unit 23 acquires the learning model M1 generated from the learning device ML.

Next, the process proceeds to activity A004, and the extraction unit 232 extracts the explanatory variable x1 from the learning model M1 based on the input data D input to the learning device ML. At this time, the extraction unit 232 extracts the format of the explanatory variable x1.

Next, the process proceeds to activity A005, and the variable name extraction unit 233 extracts the variable name VNx of the learning model M1. The extracted variable name VNx preferably contains a character string. This makes it easier for the user to grasp the contents of the explanatory variable x1 from the variable name VNx. At this time, the variable name extraction unit 233 may extract the variable name VNy of the evaluation parameter y1.

Next, the process proceeds to activity A006, and the visual information generator 234 generates visual information IF2.

Next, the process proceeds to activity A007, and the variable display unit 235 causes the display unit 34 to display the variable name VNx extracted in activity A005. The variable display unit 235 displays the variable name VNx corresponding to the visual information IF2 of the explanatory variable x1 so as to correspond to the visual information IF2. For example, the variable display unit 235 displays the variable name VNx near the corresponding visual information IF2.

Next, the process proceeds to activity A008, and the control unit 23 receives designation of the search range R from the user. The user designates the search range R by operating the visual information IF2 displayed on the display unit . The operation is arbitrary, such as a cursor operation, a key input operation, a touch operation on the display unit 34, a swipe operation, or the like.

Next, the process proceeds to activity A009, and the control unit 23 executes a search simulation within the search range R specified in activity A008.

Next, the process proceeds to activity A010, and the result display unit 236 causes the display unit 34 to display the result information IF3. The result information IF3 is displayed so as to be viewable with the visual information IF2. At this time, the result display unit 236 may cause the display unit 34 to display the history information IF4. The history information IF4 is displayed so that it can be viewed at least with the result information IF3.

Next, the process proceeds to activity A011, and the control unit 23 determines whether or not to execute the search simulation again based on the user's operation. If the determination result in activity A011 is negative, that is, if the search simulation is not executed again, the control section 23 ends the search simulation and ends the information processing. On the other hand, if the determination result in activity A011 is affirmative, that is, if search simulation is to be executed again, the process returns to activity A008, and control unit 23 accepts designation of search range R. FIG. At this time, the visual information IF2 is displayed so as to be viewable with the result information IF3 displayed in the previous activity A010. The result information IF3 displayed in activity A010 before the previous one is displayed as history information IF4. At this time, the history information IF4 is displayed so as to be viewable with the result information IF3.

4. Example of Content Displayed on Display Unit 34 In this section, an example of content displayed on the display unit 34 based on the above information processing will be described with reference to FIG. FIG. 6 shows an example of display contents displayed on the display unit 34. As shown in FIG. In this embodiment, a case where the user uses input data D to predict the sales price of a product will be described. That is, the evaluation parameter y1 in this embodiment is the sales price of the product. Although the format of the evaluation parameter y1 is arbitrary, it is floating point in this embodiment. Further, examples of explanatory variables of the learning model M1 include a first explanatory variable x11, a second explanatory variable x12, and a third explanatory variable x13. The variable names VNx of these explanatory variables x11 to x13 are sometimes expressed as variable names VNx1, VNx2 and VNx3, respectively. Also, search ranges R for these explanatory variables x11 to x13 may be expressed as search ranges R1 to R3, respectively.

The first explanatory variable x11 represents the number of visitors to the store. The format of the first explanatory variable x11 is a numerical value, especially a natural number. The variable name VNx1 of the first explanatory variable x11 is "number of visitors". A second explanatory variable x12 represents whether or not a sale is held. The form of the second explanatory variable x12 is a boolean variable. That is, the second explanatory variable x12 is represented as either true or false. The variable name VNx2 of the second explanatory variable x12 is "sale". A third explanatory variable x13 represents the product category sold at the store. The format of the third explanatory variable x13 is a character string. In this embodiment, the third explanatory variable x13 is represented by at least one of "food", "miscellaneous goods", "books", or "others". The variable name VNx3 of the third explanatory variable x13 is "product category". In the following description, it is assumed that the generation of the learning model M1 based on the input data D and the extraction of the explanatory variable x1 and the variable name VNx of the learning model M1 have been completed.

A search range designation window 10, a result display window 11, and a learning history display window 12 can be displayed on the display unit 34 of the present embodiment. In this embodiment, a search range specification window 10 and a result display window 11 are displayed in a viewable manner. Also, a result display window 11 and a learning history display window 12 are displayed so as to be viewable. Therefore, the search range specifying window 10, the result display window 11, and the learning history display window 12 are displayed so as to be able to view each other.

4-1. Search Range Designation Window 10 In the search range designation window 10, a first visual information 101, a second visual information 102, a third visual information 103, a variable name display area 104, and a search range designation button 105 are displayed. , is included.

The first visual information 101 is configured so that the search range R1 of the first explanatory variable x11 can be specified. Since the format of the first explanatory variable x11 is numerical, the first visual information 101 is configured so that the domain 1011 can be designated as the search range R1 of the first explanatory variable x11 input to the learning model M1. . In this embodiment, the visual information IF2 is displayed with a slider. The user can specify the domain 1011 of the first explanatory variable x11 by specifying the position of the slider. Specifically, the user can specify the domain 1011 of the first explanatory variable x11 by specifying the upper limit and lower limit of the search range R1. This allows the user to intuitively specify the search range R1 for the explanatory variable x11 based on the visual information of the slider. Only the first explanatory variable x11 in the search range designated by the first visual information 101 is used for the search simulation. Note that the first explanatory variable x11 used in the search simulation may not be all numerical values within the search range, and may be numerical values sampled at predetermined intervals, for example. As a result, the processing during the search simulation is reduced, and the time required for the search simulation is shortened. The numerical interval may be a value arbitrarily set by the user, or may be derived by the control unit 23 based on the designated domain 1011 .

A first range 1012 and a second range 1013 are displayed in the first visual information 101 of the present embodiment. A first range 1012 is a range in which the domain 1011 of the first explanatory variable x11 can be specified. In other words, first range 1012 indicates the region between the upper limit and lower limit of domain 1011 . On the other hand, a second range 1013 is a range in which the domain 1011 of the first explanatory variable x11 cannot be specified. In other words, second range 1013 indicates at least one of a region smaller than the lower limit of domain 1011 and a region larger than the upper limit of domain 1011 . A first range 1012 and a second range 1013 are displayed in the first visual information 101 in a distinguishable manner. For example, the colors, outlines, etc. of the first range 1012 and the second range 1013 may be displayed in different manners so as to be distinguishable. Also, the first range 1012 and the second range 1013 may be displayed distinguishably using marks such as arrows, symbols, and figures. This makes it easier for the user to grasp the scale of the search range R1 of the first explanatory variable x11. Note that the first visual information 101 is not limited to this, and may be realized using an input form in which at least one of the upper limit value and the lower limit value of the search range R1 can be input, pull-down, drum roll, or the like. may be implemented using the UI of

The second visual information 102 is configured to be able to specify the search range R2 of the second explanatory variable x12. Since the format of the second explanatory variable x12 is a Boolean variable, the second visual information 102 is configured such that the explanatory variable x12 can specify at least one of true and false. Only the boolean variables specified in the second visual information 102 are used for exploration simulation.

In this embodiment, the second visual information 102 is displayed as checkboxes corresponding to true and false, respectively. When only the check box corresponding to true (true) is checked, the search simulation of the evaluation parameter y1 (sales price) is performed only under the condition that the sale is held. On the other hand, when only the check box corresponding to false is checked, the search simulation performs a simulation of the evaluation parameter y1 (sales price) only under the condition that no sale is held. If both check boxes are checked, for example, the evaluation parameter y1 (sales price) only under the condition that the sale is held and the evaluation parameter y1 (sales price) only under the condition that the sale is not held ) and a search simulation based on a weighted average of . The second visual information 102 may be displayed so that either one of true and false can be specified. Specifically, the second visual information 102 may be displayed using radio buttons or drum rolls.

The third visual information 103 is configured to be able to specify the search range R3 of the third explanatory variable x13. Since the format of the third explanatory variable x13 is a character string, the third visual information 103 is configured to be able to specify the product category represented by the character string. The third explanatory variable x13 of the present embodiment is represented by character strings "food", "miscellaneous goods", "books", and "others" as product categories. Therefore, the third visual information 103 is displayed as check boxes that allow each of the character strings to be selected. For example, a search simulation is performed for each sales price of the designated product category. Note that the evaluation parameter y1 is not limited to the individual sales prices of the designated product category, and the total sales price of the designated product category may be used.

The visual information 101, 102, 103 may each include a designated operation area B1. The designated operation area B1 is configured to be able to determine whether or not to perform a search simulation using the explanatory variables x11 to x13 of the search ranges R1 to R3 designated based on the operation of the visual information 101, 102, 103. . For example, the designated operation area B1 can be realized using radio buttons. When performing the search simulation using the explanatory variables x11 to x13 of the designated search range R1 to R3, the search simulation is performed using the explanatory variables x11 to x13 of the designated search range R1 to R3. On the other hand, when the search simulation is performed without using part of the designation, for example, the explanatory variable x1 corresponding to the designation not used in the search simulation is treated as a constant. In addition, each of these processes is arbitrary without being limited to these.

In the variable name display area 104, variable names VNx1, VNx2 and VNx3 of the explanatory variables x11 to x13 are displayed. A variable name display area 104 is provided for each explanatory variable x11 to x13. A variable name display area 104 is provided near each explanatory variable x11 to x13. This makes it easy to grasp the content of the explanatory variable x1 displayed in the search range designation window 10. FIG.

The search range designation button 105 is configured to allow determination as to whether or not to save the search range designated by the visual information 101 to 103 based on the user's operation.

4-2. Result Display Window 11 In the result display window 11, search simulation result information IF3 using the explanatory variables x11 to x13 within the search range R1 to R3 specified in the search range specification window 10 is displayed. The result display window 11 includes a search simulation execution button 111 , an evaluation parameter name display area 112 , an evaluation parameter display area 113 and an explanatory variable display area 114 .

The search simulation execution button 111 displays a UI for executing a search simulation using the explanatory variables x11 to x13 within the search range R1 to R3 specified in the search range specification window 10 based on the user's operation. By operating the search simulation execution button 111, the user causes the control unit 23 to input the explanatory variables x11 to x13 within the specified search range R1 to R3 to the learning model M1. As a result, the result information IF3 is output from the learning model M1.

The evaluation parameter name display area 112 displays the variable name VNy of the evaluation parameter y1. The variable name VNy in this embodiment is the sales price. When there are multiple candidates for the evaluation parameter y1, the evaluation parameter name display area 112 may be configured to allow selection of the candidate for the evaluation parameter y1.

In the evaluation parameter display area 113, the evaluation parameter y1 output from the learning model M1 by the search simulation is displayed as result information IF3. In this embodiment, the evaluation parameter display area 113 displays a numerical value indicating the sales price. Note that the content displayed as the result information IF3 in the evaluation parameter display area 113 is not limited to numerical values, and the evaluation parameter display area 113 may indicate whether or not the explanatory variable x1 that satisfies the search condition exists. .

In explanatory variable display area 114, explanatory variables x11 to x13 corresponding to evaluation parameter y1 displayed in evaluation parameter display area 113 are displayed as result information IF3. A variable name VNx may be displayed in each of the evaluation parameter display areas 113 .

4-3. Learning History Display Window 12 The learning history display window 12 includes a learning history display area 121 , a sort order designation area 122 , and window operation buttons 123 .

In the learning history display area 121, history information IF4 of search simulations executed in the past is displayed. History information IF4 includes at least part of result information IF3 generated by search simulations performed in the past. Also, the history information IF4 may include usage conditions for the learning model M1. The usage conditions of the learning model M1 are, for example, information about the time when the search simulation was performed, version information of the learning model M1, and the like. In the learning history display area 121, past learning histories are displayed in a comparable manner. This makes it easier to grasp the correlation between the search range R of the explanatory variable x1 and the result information IF3. Also, in the learning history display area 121, the past learning history is displayed in a viewable manner. This facilitates comparison of past learning histories.

The sorting order designation area 122 is configured so that the display order of the history information IF4 displayed in the learning history display area 121 can be designated. The method of specifying the display order is arbitrary, such as the time when the search simulation was performed or the magnitude of the value of the evaluation parameter y1. By specifying the display order in the sort order specification area 122, it becomes easy to compare the result information IF3 according to the purpose.

The window operation button 123 is a UI for determining whether to close the learning history display window 12 based on the user's operation. When the window operation button 123 is operated, the learning history display window 12 is closed.

5. Others Regarding the information processing system 1 according to the above-described embodiment, the following aspects may be adopted.

The first input data D1 and the second input data D2 may each be stored in the database DB1 as the external data D0. These external data D0 may be provided to other users under predetermined conditions.

For example, the control unit 23 may cause the display unit 34 to display a history of conversion processing performed on the first input data D1, ie, a so-called conversion processing version. This makes it easy to analogize the relationship between the conversion process and the accuracy information. Also, the control unit 23 may manage versions of conversion processing.

For example, when the first input data D1 does not satisfy a predetermined quality condition, the control unit 23 may cause the display unit 34 to display a warning. The quality conditions are, for example, the number of data points of the first input data D1, the capacity, the ratio of outliers, and the like. When the quality condition is not satisfied, for example, when the number of data points in the first input data D1 is less than a predetermined value, or when the number of outliers in the first input data D1 is greater than a predetermined reference number. be. Note that the warning is not limited to being displayed on the display unit 34, and can be implemented in any form such as sound, vibration, or light.

The information processing device 2 may be in an on-premise form or in a cloud form. The cloud-type information processing apparatus 2 may provide the above functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

In the above embodiment, the information processing device 2 performs various types of storage and control, but instead of the information processing device 2, a plurality of external devices may be used. That is, the input data D, the learning model M1, the result information IF3, and the history information IF4 may be distributed and stored in a plurality of external devices using blockchain technology or the like.

It may be provided in each aspect described below.

(2) In the information processing system, the learning model is generated by inputting the input data into at least one learning device.

According to such a configuration, the explanatory variables are extracted based on the input data input to generate the learning model. Therefore, it is possible to improve the accuracy of extracting explanatory variables.

(3) In the information processing system, when the format of the explanatory variable is a character string, the visual information is configured to allow selection of whether or not to input the explanatory variable to the learning model.

According to such a configuration, the user can visually recognize the selection method of whether or not to use the explanatory variable corresponding to the character string based on the visual information.

(4) In the information processing system, when the format of the explanatory variable is a numerical value, the visual information is configured to be able to specify the domain of the explanatory variable to be input to the learning model, and the search range is: Those defined based on the domain.

According to such a configuration, the user can visually recognize the search range of the explanatory variable as a variable region, so that the user can intuitively grasp the search range.

(5) In the information processing system, when the format of the explanatory variable is a numerical value, the visual information can specify at least one of an upper limit value and a lower limit value of the explanatory variable to be input to the learning model. and wherein said search range is defined based on at least one of said upper limit value and said lower limit value.

According to such a configuration, the user can specify the search range by specifying at least one of the upper limit value and the lower limit value. Therefore, even when the range of numerical values that can be specified as explanatory variables is enormous, the user can easily specify the search range.

(6) In the information processing system, when the format of the explanatory variable is a numerical value, the visual information is displayed with a slider, and the search range is specified based on the position of the slider.

According to such a configuration, when the format of the explanatory variable is a numerical value, the user can intuitively specify the search range of the explanatory variable based on the visual information of the slider.

(7) In the information processing system, in the visual information generating step, when a plurality of explanatory variables are extracted in the extracting step, the visual information corresponding to each of the plurality of explanatory variables is generated.

According to such a configuration, even when a plurality of explanatory variables are extracted, it is possible to intuitively specify the input mode of each explanatory variable to the learning model. Therefore, it becomes easier for the user to specify a more efficient search range for explanatory variables.

(8) In the information processing system, the variable name extraction step further extracts a variable name representing the extracted explanatory variable from the input data, and the variable display step includes the visual information of the explanatory variable, A listable display of said variable name.

According to such a configuration, it becomes easier for the user to grasp the variables corresponding to the visual information.

(9) In the information processing system, further, in the result display step, the visual information and the result information output from the learning model based on the explanatory variables in the specified search range are displayed in a viewable manner. ,thing.

According to such a configuration, the user can list the designated explanatory variable and the result information corresponding to the explanatory variable. Therefore, it becomes easier for the user to grasp the correspondence relationship between the explanatory variables and the result information.

(10) In the information processing system, the result display step further displays history information of the result information output in the past.

According to such a configuration, by comparing the latest result information and the past result information, it becomes easy to grasp the transition of the accuracy of the learning model.

(11) In the information processing system, the visual information can specify the search range discretely.

According to such a configuration, it is possible to specify the search range more clearly than in the case where the search range can be continuously specified.

(12) In the information processing system, the input data includes at least structured data.

(13) An information processing method, comprising steps of the information processing system.

(14) An information processing program that causes a computer to execute each step of the information processing system.
Of course, it is not limited to this.

Furthermore, the following points should also be noted.

The movement to use deep learning (DL) and other machine learning (machine learning, ML) technologies in various situations is accelerating, creating a situation that can be called a kind of boom. However, contrary to this excitement, 85% of ML introduction projects have failed, 10% of companies are able to utilize ML and AI (Artificial Intelligence) technology, and only 17% of information companies. It is said.

There are various causes for this. First, it is not easy to understand what problems ML and AI are effective against. Second, what kind of data should be prepared to use ML, and how to process and preprocess data. What to do depends on experience and intuition. Third, it is not easy to prepare a large amount of data. Fourth, it is not easy to understand how to build an ML or AI model. Moreover, it depends on experience and intuition. Fifth, it is difficult to understand why the desired output can be obtained from DL, which is a method of ML. and the fact that it is not possible to obtain

As mentioned above, there are various obstacles to the successful utilization of ML, but on the other hand, there are many ML services and AI services on the Internet, and it is a chaotic situation where you do not know which one to use. There is also

In addition, in order to use the above ML and AI services, many parameters must be entered, and it is difficult to understand the meaning of the parameters, and there is a reality that only ML and AI experts can use them. . In other words, ML services and AI services were not democratized services that could be used by non-specialists.

In view of the above-mentioned situation, it is possible to use ML services without specialized knowledge, and if you prepare input data, you can use ML services in 3 steps, and provide analysis of the obtained results, Furthermore, it is an object of the present invention to create an environment in which anyone can use ML services by providing a technique that can also perform prediction. This democratizes ML services.

A technical idea for solving the above problems is to provide a wrapping interface system for connecting to many ML (hereinafter referred to as AutoML) services existing on the Internet. As a result, data preparation such as data collection, preprocessing, and uploading (step 1), model construction and parallel execution of multiple MLs (step 2), performance comparison of each ML and introduction to actual work (step 3) It is possible to introduce ML in the following three steps.

For this purpose, the account setting, parameter input procedure, etc. are first unified, and then format conversion is applied to each AutoML. This makes it possible to create an account in 3 steps, which used to take 10 to 15 steps.

Next, collect internal and external data. The access points to internal and external data required for this are connected automatically or with user intervention and assistance, and the data is collected.

Next, the input data is processed. This includes, but is not limited to, data cleansing such as conversion to a unified format such as date data, processing data items with many missing points, and applying preprocessing including statistical processing from the original data. and transforming it into data suitable for the purpose, and using queries to perform data extraction, data merging, etc.

At this time, if necessary, the processed data may be displayed for confirmation and correction.

Next, prepare the ML model. It is not limited to the use of various ML services that exist on the Internet, but also a method of constructing an original model without programming based on a GUI (Graphical User Interface), and modifying various ML services that exist on the Internet to create an original model. This is done by a method of constructing and a method of importing an ML model that has already been constructed but has not been published on the Internet into the system of the present invention.

It also provides functionality that enables ML and statistical analysis without programming. In addition, a function is also provided to recommend from the input data what kind of template should be used to build a model with high accuracy.

The data input to the ML may be divided into learning data and prediction data, and the prediction data may be input to the ML that has been learned using the learning data. The prediction data is used hereafter for ML performance comparisons, etc.

Once the input data and the ML model have been prepared, training is started using the learning data.
At this time, multiple MLs may be executed in parallel.

After training, predictive data is injected into each ML service automatically or by user's instruction to obtain results. If multiple AutoMLs are executed in parallel at this time, the performance can be compared immediately.

View the results for each AutoML service. This includes graphical visualizations showing the level of prediction accuracy (coefficient of determination) for each ML service, comparison of item contributions, etc.

The above data collection, display and comparison of results are repeated, and when the user decides that it can be put into actual work, the operation is started.

In operation, it is within the scope of the present invention that the results are utilized by the application program by inquiring from the application program to this system using a prepared API (Application Program Interface), or that the results are displayed directly from this system. .

ML platforms including Kubeflow may be used for automation of operations.

The above series of operations may be pipelined to simplify the operations. Pipelining reduces the degree of freedom, but improves the overall outlook and allows non-experts to handle it. If it is necessary to increase the degree of freedom, specialized item settings may be performed by opening a detailed screen or the like.

Furthermore, it is possible to record and view various changes and operation histories along the flow of the pipeline, and it is possible to show the grounds for selecting ML services and models.

After the ML model to be adopted and the data preprocessing method required for it are decided, it is introduced into the actual business. For example, if you want a sales forecast as an ML output, you can directly see the screen displayed by the system of the present invention, or if necessary, request information provision from the application program via the API provided by the system of the present invention. may be issued and thereby displayed on the screen of the application program.

Therefore, in order to solve the above problems, an information processing method according to a first aspect includes a first step of unifying initial setting work including at least one of account setting and parameter input procedure setting; a second step of applying a format conversion to connect to possible automated machine learning services; a third step in which internal and external data is collected; a fourth step of processing said collected data; a fifth step of preparing an automated machine learning service to be used; splitting the data processed in said fourth step into learning data and prediction data; preparing said learning data in said fifth step; and a sixth step of learning by an automatic machine learning service performed by.

In order to solve the above problems, an information processing apparatus according to a second aspect includes a centralizing unit capable of centralizing initial setting work including at least one of account setting and parameter input procedure setting; A format conversion unit that performs format conversion for connecting to an automatic machine learning service that can exist in the a preparation unit that prepares for an automatic machine learning service to be performed, the data processed by the data processing unit is divided into learning data and prediction data, and the learning data is prepared by the preparation unit for automatic machine learning and a learning unit for learning by the service.

According to the above two aspects, even if you are not an expert in machine learning techniques such as deep learning, you can select and / or build a learning model as long as you prepare learning data, and from the results of a plurality of learning models Performance can be compared, the optimum model can be selected from among multiple learning models, and it can be applied to actual business operations to support operations after application.

As a third aspect, in the second aspect, the collected and prepared input data may be converted according to many automatic machine learning services existing on the Internet. According to this aspect, it is possible to omit the process of preparing different input data for each machine learning service. It should be noted that this third mode can also be used in a superimposed manner with respect to the first mode.

As a fourth aspect, in the second aspect, simple format conversion of input data, data cleansing including processing of missing data or redundant/unnecessary data, extraction of feature values from original data, preprocessing including statistical processing may be applied to perform data transformations including conversion to data suitable for the purpose, data extraction using queries, and/or data merging. According to this aspect, simple format conversion of input data, data cleansing including processing of missing data or redundant/unnecessary data, extraction of feature values from original data, preprocessing including statistical processing are applied to achieve the purpose Data conversion, including conversion to suitable data, data extraction using queries, or data merging, can be performed by giving simple instructions. It should be noted that this fourth aspect can also be used in a superimposed manner with respect to the first aspect.

As a fifth aspect, in the second aspect, a list part that can list a plurality of machine learning services or machine learning models existing on the Internet, and a plurality of machine learning services or machine learning models listed in the list part A selection unit that selects connection to one of the above, and data input to a plurality of machine learning services or machine learning models collectively by being selected by the selection unit, parallel execution, acquisition of results, and and an execution unit that executes at least one of the comparison. It should be noted that this fifth mode can also be used in a superimposed manner with respect to the first mode.

As a sixth aspect, in the second aspect, the learning section and/or the preparation section may be performed by graphical user interface means. According to this aspect, in addition to selecting the machine learning service described above, users can build their own machine learning models using a graphical user interface-based technique, and/or exist as public information. You can import a machine learning model that It should be noted that this sixth aspect can also be used in a superimposed manner with respect to the first aspect.

As a seventh aspect, in the second aspect, when the processed data is divided into the learning data and the prediction data in the learning unit, the input data to machine learning is compared in performance with the learning data. and/or may be divided into prediction data. According to this aspect, input data to the machine learning can be divided into learning data and performance comparison and/or prediction data for use. It should be noted that this seventh mode can also be used in a superimposed manner with respect to the first mode.

As an eighth aspect, the second aspect may further include an index providing unit that provides an index for comparing the performance of a plurality of machine learning services or machine learning models executed with the same input data. It should be noted that this eighth mode can also be used in a superimposed manner with respect to the first mode.

As a ninth aspect, in the eighth aspect, at least one of the coefficient of determination, mean absolute error, mean square deviation, item contribution, model prediction and actual comparison, residual histogram, as the indicator A metric may be presented to compare the performance of the machine learning service and the machine learning model. It should be noted that the ninth mode can also be used in a superimposed manner with respect to the mode in which the eighth mode is superimposed on the first mode.

As a tenth aspect, the second aspect may further include a selection unit that selects from a plurality of machine learning services and the result of each machine learning model out of the plurality. According to this aspect, the optimum one can be selected from a plurality of machine learning services and the results of the respective machine learning models out of the plurality and applied to actual business. It should be noted that this tenth aspect can also be used in a superimposed manner with respect to the first aspect.

As an eleventh aspect, in the second aspect, a maintenance and management unit capable of maintaining and/or managing the accuracy of the machine learning service and the machine learning model may be further provided. According to this aspect, a function is provided that can maintain and/or manage the accuracy of the machine learning service and the machine learning model after actual launch.
It should be noted that the eleventh aspect can also be used in a superimposed manner with respect to the first aspect.

As a twelfth aspect, in the second aspect, collection and preparation of the data, parallel execution of multiple machine learning services and machine learning models, performance comparison of machine learning services and machine learning models, input to actual business A pipeline section that pipelines the operations may be further provided. According to this aspect, the operation of collecting and preparing the above data, parallel execution of a plurality of machine learning services and machine learning models, performance comparison of machine learning services and machine learning models, and input to actual work is pipelined. , can improve the overall outlook. The twelfth mode can also be used in a superimposed manner with respect to the first mode.

As a thirteenth aspect, the twelfth aspect may further include a user intervention unit that allows a user to intervene as necessary at various intermediate stages of the pipelined processing. . According to this aspect, the user may intervene as necessary to perform detailed settings and operations at various intermediate stages of the pipelined processing. The thirteenth mode can also be used in a superimposed manner with respect to the mode in which the twelfth mode is superimposed on the first mode.

As a fourteenth aspect, in the second aspect, further comprising a data requesting unit for requesting the data from an application program via an application program interface in order to obtain the processing result of the machine learning service or the machine learning model It may be provided. According to this aspect, in order to obtain the processing results of a machine learning service or a machine learning model that has been put into actual business, an application program requests data from the system of the present invention via the application program interface. The application program may perform processing including display. It should be noted that the fourteenth aspect can also be used in a superimposed manner with respect to the first aspect.

As a fifteenth aspect, in the second aspect, the screen in at least one of the unification unit, the format conversion unit, the data collection unit, the data processing unit, the preparation unit, and the learning unit is a data screen. At least one of the screens related to collection and preparation, the screen related to selection/construction/execution of machine learning models, the screen related to performance comparison of each learning model, and the screen to decide the selection of machine learning models and introduce them to actual work. You may have a screen transition including. According to this aspect, information is exchanged with the user using a plurality of screens in each step from preparation and upload of data to comparison of performance between a plurality of MLs and introduction to actual work. is a screen related to data collection and preparation (preprocessing, uploading, etc.), a screen related to selection, construction, and execution of machine learning models (model construction, ML execution), a screen related to performance comparison of each learning model, and a machine Since it has screen transitions including screens for determining the selection of learning models and introducing them to actual work, the learning process can be designed in the screen transition definition. The fifteenth aspect can also be used in a superimposed manner with respect to the first aspect.

Further, in order to solve the above problems, a program according to a sixteenth aspect causes a computer to convert collected learning data to match each machine learning service or machine learning model without intervention of an expert. a data cleansing unit that processes missing, redundant, and unnecessary data; a feature value extraction unit that extracts feature values from the original data; and preprocessing including statistical processing. A data combining/splitting unit that converts data into data suitable for the purpose, extracts data using queries, and converts data including data combining; a normalization/standardization unit that normalizes and standardizes data; A service model selection section that selects learning services and machine learning models, a no-code development section for building machine learning models, a simulation section that executes multiple machine learning services and machine learning models in parallel, and results A model evaluation section that displays and compares, a model selection section that selects the optimal machine learning service or machine learning model, and an input/operation section that puts the selected model into actual work and operates it. It is characterized by functioning as a support part that supports.

According to the above aspect, the data processing/converting unit that converts the collected learning data so as to match each machine learning service or machine learning model without the intervention of an expert, and the processing of missing data, duplicated/unnecessary data, etc. a data cleansing unit including a data cleansing unit, a feature extraction unit that extracts feature values from the original data, a conversion to data suitable for the purpose by applying preprocessing including statistical processing, and data extraction and data combination using queries Data joining/splitting part that performs data transformation including normalization/standardization part that normalizes/standardizes data Service/model selection part that selects multiple machine learning services and machine learning models, without programming A no-code development department that builds its own machine learning model, a simulation department that runs multiple machine learning services and machine learning models in parallel, a model evaluation department that displays and compares results, and an optimal machine learning service or machine learning model. a model selection unit that selects a model, an input/operation unit that inputs the selected model into actual business operations and operates it, and a support unit that supports a series of these operations.

A seventeenth aspect can also be implemented as a recording medium storing the program according to the sixteenth aspect.

1: Information processing system 2: Information processing device 3: User terminal 10: Search range designation window 11: Result display window 12: Learning history display window 20: Communication bus 21: Communication unit 22: Storage unit 23: Control unit 30: Communication Bus 31: communication unit 32: storage unit 33: control unit 34: display unit 35: input unit 101: first visual information 102: second visual information 103: third visual information 104: variable name display area 105: Search range designation button 111 : Search simulation execution button 112 : Evaluation parameter name display area 113 : Evaluation parameter display area 114 : Explanatory variable display area 121 : Learning history display area 122 : Sort order designation area 123 : Window operation button 231 : Data acceptance Section 232 : Extraction section 233 : Variable name extraction section 234 : Visual information generation section 235 : Variable display section 236 : Result display section 1011 : Domain 1012 : First range 1013 : Second range A001 : Activity A002 : Activity A003 : Activity A004 : Activity A005 : Activity A006 : Activity A007 : Activity A008 : Activity A009 : Activity A010 : Activity A011 : Activity B1 : Designated operation area D : Input data D0 : External data D1 : First input data D2 : Second Input data DB1: Database IF2: Visual information IF3: Result information IF4: History information M1: Learning model ML: Learning device R: Search range R1: Search range R2: Search range R3: Search range VNx: Variable name VNx1: Variable name VNx2: variable name VNx3: variable name VNy: variable name x1: explanatory variable x11: first explanatory variable x12: second explanatory variable x13: third explanatory variable y1: evaluation parameter

Claims (14)

An information processing system,
Equipped with a control unit,
The control unit is configured to perform the following steps,
The data reception step receives input data,
In the extraction step, an explanatory variable is extracted from the learning model based on the input data to be input,
The visual information generating step generates visual information capable of designating a search range of the extracted explanatory variables according to the format of the explanatory variables.death,
In the search step, a search simulation searches for the explanatory variables satisfying a predetermined search condition defined based on the relationship between the input data and the output of the learning model from among the explanatory variables within the designated search range. and run
In the display processing step, the explanatory variables obtained by the search simulation are displayed. thing. In the information processing system according to claim 1,
When the format of the explanatory variable is a numerical value, the visual information is configured to be able to specify the domain of the explanatory variable to be input to the learning model,
wherein the search range is defined based on the domain . An information processing system,
Equipped with a control unit,
The control unit is configured to perform the following steps,
The data reception step receives input data,
In the extraction step, an explanatory variable is extracted from the learning model based on the input data to be input,
In the visual information generating step, generating visual information capable of designating a search range of the extracted explanatory variable according to the format of the explanatory variable;
When the format of the explanatory variable is a numerical value, the visual information is configured to be able to specify the domain of the explanatory variable to be input to the learning model,
The search range is defined based on the domain,
The visual information includes a first range in which the domain can be specified and a second range in which the domain cannot be specified,
wherein the first range and the second range are configured to be distinguishable . In the information processing system according to any one of claims 1 to 3 ,
The learning model is generated by inputting the input data into at least one learner. In the information processing system according to any one of claims 1 to 4 ,
When the format of the explanatory variable is a character string, the visual information is configured to allow selection of whether or not to input the explanatory variable to the learning model. In the information processing system according to any one of claims 1 to 5 ,
When the format of the explanatory variable is a numerical value, the visual information is configured to be able to specify at least one of an upper limit value and a lower limit value of the explanatory variable to be input to the learning model,
The search range is defined based on at least one of the upper limit and the lower limit. In the information processing system according to any one of claims 1 to 6 ,
When the format of the explanatory variable is a numerical value, the visual information is displayed with a slider,
The search range is specified based on the position of the slider. In the information processing system according to any one of claims 1 to 7 ,
In the visual information generation step, when a plurality of explanatory variables are extracted in the extraction step, the visual information corresponding to each of the plurality of explanatory variables is generated. In the information processing system according to any one of claims 1 to 8 ,
Furthermore, in the variable name extraction step, a variable name representing the extracted explanatory variable is extracted from the input data,
In the variable display step, the visual information of the explanatory variables and the variable names are displayed in a viewable manner. In the information processing system according to any one of claims 1 to 9 ,
Furthermore, in the result display step, the visual information and the result information output from the learning model based on the explanatory variables in the specified search range are displayed in a viewable manner. In the information processing system according to claim 10 ,
In the result display step, history information of the result information output in the past is further displayed. In the information processing system according to any one of claims 1 to 11 ,
The visual information can specify the search range discretely. An information processing method,
An object comprising each step of the information processing system according to any one of claims 1 to 12. An information processing program,
A computer that executes each step of the information processing system according to any one of claims 1 to 12.

Images