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

The information processing device improves usability by identifying intervenable and non-intervenable items and providing optimal intervention strategies for each cluster, enhancing decision-making speed and quality.

JP7593398B2Active Publication Date: 2024-12-03SONY GROUP CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2022514417
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-04-06
Filing Date
2021-03-29
Publication Date
2024-12-03
Estimated Expiration
2041-03-29

AI Technical Summary

Technical Problem

Conventional predictive analysis tools lack usability as users are often left to decide specific measures without clear guidance, and existing techniques struggle to effectively apply measures across data clusters with different characteristics.

Method used

An information processing device that identifies intervenable and non-intervenable items among explanatory variables, determines personas for each cluster, and provides optimal intervention strategies based on these items to enhance usability.

Benefits of technology

Enhances decision-making speed and quality by visualizing the best policy and its influence for each cluster, allowing users to make informed decisions quickly and effectively.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007593398000001
    Figure 0007593398000001
  • Figure 0007593398000002
    Figure 0007593398000002
  • Figure 0007593398000003
    Figure 0007593398000003
Patent Text Reader

Abstract

The present invention promotes further enhancement of usability. An information processing device (10) comprises: a specifying unit (1121) for specifying, among explanatory variables which are used for estimating a target variable, an intervenable item, i.e., an explanatory variable which allows a user to intervene; and a determination unit (1123) for determining information related to personas of clusters generated on the basis of non-intervenable items, i.e., explanatory variables other than the intervenable item specified by the specifying unit (1121).
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

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

[0002] In recent years, the development of predictive analysis tools using machine learning has become widespread. Predictive analysis tools can be used to support user decision-making. For example, predictive analysis tools can be used to formulate business measures by predicting next month's sales based on past sales performance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 130974 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, there is room for further improvement in usability. For example, in the conventional technology, the decision of what specific measures should be taken may be left to the user in many cases.

[0005] Therefore, the present disclosure proposes a new and improved information processing device, information processing method, and information processing program that can promote further improvement of usability. [Means for solving the problem]

[0006] According to the present disclosure, an information processing device is provided that includes an identification unit that identifies, among explanatory variables used to estimate a target variable, intervenable items that are explanatory variables in which a user can intervene, and a determination unit that determines information regarding a persona of each cluster generated based on intervenable items that are explanatory variables other than the intervenable items identified by the identification unit. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a dataset according to the embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a dataset according to the embodiment. [Figure 4] FIG. 13 is a diagram illustrating an example of a data set loading screen according to the embodiment. [Diagram 5] FIG. 13 is a diagram illustrating an example of a setting screen for a learning model according to an embodiment. [Figure 6] FIG. 13 is a diagram showing an example of a screen showing a learning status according to the embodiment. [Figure 7] FIG. 1 is a diagram showing an overview of functions of an information processing system according to an embodiment. [Figure 8] FIG. 1 is a diagram showing an overview of functions of an information processing system according to an embodiment. [Figure 9] 1 is a block diagram showing an example of the configuration of an information processing system according to an embodiment. [Figure 10] FIG. 4 illustrates an example of a storage unit according to the embodiment; [Figure 11] 5 is a flowchart showing a flow of processing in the information processing device according to the embodiment. [Figure 12] 5 is a flowchart showing a flow of processing in the information processing device according to the embodiment. [Figure 13] 5 is a flowchart showing a flow of processing in the information processing device according to the embodiment. [Figure 14] FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0009] The explanation will be given in the following order. 1. One embodiment of the present disclosure 1.1. Introduction 1.2. Information Processing System Configuration 2. Functions of the information processing system 2.1. Overview of Features 2.2. Example of functional configuration 2.3. Processing of Information Processing Systems 2.4. Variations of processing 3. Hardware configuration example 4. Summary

[0010] <<1. One embodiment of the present disclosure>> <1.1. Introduction> Most tabular data can be broken down into multiple similar data groups. These similar data groups are called "clusters," and breaking them down into clusters is called "clustering." Data contained in different clusters are likely to have different characteristics (properties). For this reason, for example, if the same measures are taken on all clusters, even if there is an overall improvement trend, this does not necessarily mean that the improvement has had an impact on all clusters. Therefore, by visualizing the best measures for each cluster and their impact, it is possible to promote improvements in the quality and speed of user decision-making.

[0011] In conventional technology, a contribution degree may be used to indicate the degree to which each item of explanatory variables contributes to the prediction (estimation) of the objective variable. However, in conventional technology, it may not be clear which item should be set and how, and the contribution degree may not be a measure proposal. Also, the contribution degree in conventional technology is the contribution degree to the whole. For this reason, applying the same measure to data with different characteristics is not necessarily effective, and there is room for further improvement in usability.

[0012] In conventional technology, determining personas by clustering may be performed in target analysis or persona analysis in marketing, etc. However, conventional technology may not know what measures should be taken for a persona. For this reason, there is room for further improvement of usability.

[0013] Therefore, the present disclosure proposes a new and improved information processing device, information processing method, and information processing program that can promote further improvement of usability.

[0014] <1.2. Information processing system configuration> A configuration of an information processing system 1 according to an embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of the information processing system 1. As shown in FIG. 1, the information processing system 1 includes an information processing device 10, a terminal device 20, and an information providing device 30. Various devices can be connected to the information processing device 10. For example, the terminal device 20 and the information providing device 30 are connected to the information processing device 10, and information is shared between the devices. The terminal device 20 and the information providing device 30 are wirelessly connected to the information processing device 10. For example, the information processing device 10 performs short-range wireless communication with the terminal device 20 and the information providing device 30 using Bluetooth (registered trademark). The terminal device 20 and the information providing device 30 may be connected to the information processing device 10 by wire or via a network.

[0015] (1) Information processing device 10 The information processing device 10 is an information processing device that performs a process of determining information on the persona of each cluster. Specifically, the information processing device 10 identifies explanatory variables that the user can intervene in (hereinafter, appropriately referred to as "intervention-enabled items") among explanatory variables used to estimate the objective variable. Then, the information processing device 10 determines information on the persona of each cluster generated based on explanatory variables other than the identified intervention-enabled items (hereinafter, appropriately referred to as "non-intervention-enabled items"). In addition, the non-intervention-enabled items are explanatory variables in which the user cannot intervene. Specifically, the non-intervention-enabled items are explanatory variables in which the user cannot intervene for the purpose of adjusting the objective variable. The non-intervention-enabled items are, for example, explanatory variables related to the attributes of the user. Details of the intervention-enabled items and the non-intervention-enabled items will be described later.

[0016] The information processing device 10 also has a function of controlling the overall operation of the information processing system 1. For example, the information processing device 10 controls the overall operation of the information processing system 1 based on information linked between the devices. Specifically, the information processing device 10 determines information related to the persona of each cluster based on information received from the terminal device 20 and the information providing device 30.

[0017] The information processing device 10 is realized by a PC (Personal computer), a WS (Work station), etc. The information processing device 10 is not limited to a PC, a WS, etc. For example, the information processing device 10 may be an information processing device such as a PC or a WS in which the functions of the information processing device 10 are implemented as an application.

[0018] (2) Terminal device 20 The terminal device 20 is an information processing device used by a user. The terminal device 20 provides a dataset to be processed to the information processing device 10 in response to a user operation. The dataset according to the embodiment includes data of objective variables and explanatory variables. The dataset according to the embodiment has at least an objective variable that is a target. The dataset according to the embodiment may be in any form as long as it is in a table format. The dataset according to the embodiment will be described with reference to Figs. 2 and 3.

[0019] FIG. 2 shows an example of a dataset according to an embodiment. FIG. 2 shows a customer list for online sales. Data DT11 indicates customer identification information. Data DT12 indicates the customer's name. Data DT13 indicates the customer's age. Data DT14 indicates the customer's gender. Data DT15 indicates the number of people living with the customer. Data DT16 indicates the amount of a coupon distributed to the customer. Data DT17 indicates whether or not the customer has received direct mail. Data DT18 indicates the customer's purchase result using two bits, "0" and "1".

[0020] Data DT11 and data DT12 do not contribute to the customer's purchasing results. For this reason, data DT11 and data DT12 are excluded from processing by the processing unit 112 described later. Data DT13 to data DT15 are information indicating the attributes of the customer. Data DT13 to data DT15 are non-intervention items. Data DT16 and data DT17 are information provided to the customer by others (e.g., an advertising agency). Data DT16 and data DT17 are intervention items. Data DT18 is a target variable. By learning this dataset, the processing unit 112 described later shows how to set intervention items to make it easier for a representative user to make a purchase.

[0021] FIG. 3 shows an example of a dataset according to an embodiment. FIG. 3 shows a factory line. It is assumed that the line operates twice a day, in the morning and in the afternoon in this factory. For this reason, the date and start time of the line are attributes of the line. Data DT21 indicates identification information of the line. Data DT22 indicates the date of the line. Data DT23 indicates the start time of the line. Data DT24 indicates a sensor value from sensor 1 provided on the line. Data DT25 indicates a sensor value from sensor 2 provided on the line. Data DT26 indicates the indoor temperature of the line. Data DT27 indicates the person in charge of the line. Data DT28 indicates the number of defective products by the line.

[0022] Data DT21 does not contribute to the result of the number of defective products. For this reason, data DT21 is excluded from the processing by the processing unit 112 described later. Data DT22 to data DT25 are information indicating the attributes of the line. Data DT22 to data DT25 are non-intervention items. Data DT26 and data DT27 are information set by the line manager. Data DT26 and data DT27 are intervention possible items. Data DT28 is a response variable. By learning this data set, the processing unit 112 described later shows how to set intervention possible items to make it difficult for defective products to occur in the state of representative non-intervention possible items.

[0023] Fig. 4 shows an example of a data set loading screen. In Fig. 4, data CS11 is loaded. Then, the terminal device 20 displays a display screen GU11 that prompts the user to input, as information for executing the process according to the embodiment, the model name of the learning model that estimates the estimation result of the objective variable, etc. In Fig. 4, it is assumed that "model20200319" is input as the model name.

[0024] FIG. 5 shows an example of a display screen GU21 displayed after reading data CS11. The display screen GU21 is displayed by, for example, the terminal device 20. The display screen GU21 displays setting information of a learning model. The setting information of a learning model is determined using the display screen GU21. In the conventional technology, when data CS11 is read, the item name of the data (e.g., "ID", "name"), the type of data (e.g., "numeric value", "character string"), and the like are often estimated. In the information processing system 1, when data CS11 is read, in addition to estimating the item name of the data, the type of data, and the like, whether or not the data can be intervened is estimated. An item estimated to be intervenible becomes an intervenible item, and an item estimated to be uninterventionable becomes an uninterventionable item. The display screen GU11 has a column CU21 for setting an intervenible item. Furthermore, whether or not the intervention can be performed may be estimated by the information processing system 1 after reading data CS11, or may be designated by the user. When designated by the user, the information processing system 1 may accept the user's designation. Furthermore, when a user modifies information estimated by the information processing system 1, the information processing system 1 may store the modified information and use it to estimate whether or not to intervene later. After the user inputs setting information, the display screen GU11 executes the processing according to the embodiment by operating (e.g., tapping or clicking) "Execute learning and evaluation." The information processing system 1 executes learning and evaluation of the learning model by the user operating "Execute learning and evaluation."

[0025] 6 shows an example of a display screen GU31 displayed during learning of the learning model. The display screen GU31 is displayed, for example, by the terminal device 20. The information processing system 1 performs processing for determining information about personas by clustering in addition to learning of the learning model.

[0026] The terminal device 20 is realized by a PC, a WS, etc. Note that the terminal device 20 is not limited to a PC, a WS, etc. For example, the terminal device 20 may be an information processing device such as a PC or a WS in which the functions of the terminal device 20 are implemented as an application.

[0027] (3) Information provision device 30 The information providing device 30 is an information processing device that provides the information processing device 10 with information on the setting history of intervention-enabled items.

[0028] The information providing device 30 is realized by a PC, a WS, etc. Note that the information providing device 30 is not limited to a PC, a WS, etc. For example, the information providing device 30 may be an information processing device such as a PC or a WS in which the function of the information providing device 30 is implemented as an application.

[0029] <<2. Functions of the information processing system>> Above, we have described the configuration of the information processing system 1. Next, we will describe the functions of the information processing system 1. In the embodiment, it is assumed that coupons are distributed and advertising is carried out by direct mail to some customers.

[0030] The contribution degree according to the embodiment is information indicating the degree to which each intervention possible item contributes to the estimation of the objective variable for each cluster.

[0031] <2.1. Overview of functions> FIG. 7 is a diagram showing an outline of the functions of the information processing system 1 according to the embodiment. Specifically, FIG. 7 shows an example of output information generated by the information processing device 10. The non-intervention items V11 to VA13 are non-intervention items, and are respectively age, number of cohabitants, and gender. The non-intervention item VA indicates that the customer's age is 0 to 75 years old, the number of cohabitants is 1 to 6, and the gender is female "F" or male "M". This non-intervention item VA may be an attribute range (for example, age range) based on the attribute layer of the customer included in the data set. In addition, the non-intervention item VA may be a condition previously determined by the user as the attribute of the target customer. The intervening item VB11 and the intervening item VB12 are intervening items, and are respectively the amount of a distributed coupon and the presence or absence of direct mail. The intervening item VB indicates that the amount of a distributed coupon is 0 yen to 5,000 yen, and the presence or absence of direct mail is "present" or "absent". The intervention possible item VB may be the range of information on the intervention possible item included in the data set of the customer of the intervention impossible item VA (e.g., the range of distribution amounts). The intervention possible item VB may also be a condition predetermined by the user to further narrow down the customers of the intervention impossible item VA. Note that the intervention impossible item VA and the intervention impossible item VB may be any type, and are not limited to numerical values ​​such as "0" to "10" or options such as "YES" or "NO" (e.g., two or three options).

[0032] Clusters CL11 to CL13 are clusters generated by clustering based on non-intervention items. Information included in clusters CL11 to CL13 is information about personas of each cluster determined by the information processing system 1. Specifically, in cluster CL11, personas PE11 to PE15 are information about personas. Personas PE11 to PE15 are information about representatives (representative images) representing cluster CL11. For example, personas PE11 to PE13 are attribute information of the representative image representing cluster CL11, and personas PE14 and persona PE15 are distribution information assigned to the representative image representing cluster CL11.

[0033] In FIG. 7, the purchase probability is the objective variable. Specifically, the purchase probability is an estimation result of the objective variable estimated based on information on the intervention-enabled item VB and information on the intervention-disabled item VA included in the cluster. The purchase probability can be adjusted by adjusting the information on the intervention-enabled item VB. For example, by changing the distribution coupon amount for the intervention-enabled item VB from 2,000 yen to 3,000 yen, the purchase probability can be changed from 0.76 to 0.86. In cluster CL11, the purchase probability of the persona is 0.76. This purchase probability can be adjusted by adjusting the information on the intervention-enabled item VB of the persona.

[0034] The optimal value ST11 indicated by a star mark is the optimal value at which the estimation result of the objective variable is optimal. In FIG. 7, the optimal value ST11 is the value at which the purchase probability is maximized by adjusting the information of the intervention-enabled item VB. In the cluster CL11, the optimal value ST11 indicates the same value as the persona PE14, so the purchase probability of the persona is the optimal result of the objective variable. Therefore, even if the persona PE14 is adjusted to the optimal value ST11, the adjustment amount is zero, so the change in the purchase probability is also zero. In the cluster CL12, the purchase probability increases from 0.58 to 0.76 by adjusting the persona PE24 to the optimal value ST21. In the cluster CL13, the purchase probability increases from 0.58 to 0.76 by adjusting the persona PE34 to the optimal value ST31. Note that the adjustment of the information of the intervention-enabled item VB may be performed by any means, not limited to an operation on the screen (e.g., dragging, tapping, or direct input).

[0035] FIG. 7 shows a case where the purchase probability of the optimal result is output, but is not limited to this example. For example, an estimation result according to adjustment of the information of the intervention-enabled item VB may be output. Also, a case where the increase rate of the purchase probability of the optimal result for the persona's estimation result is output is shown, but is not limited to this example. For example, a purchase probability increase rate according to adjustment of the information of the intervention-enabled item VB for the persona's estimation result may be output.

[0036] FIG. 8 is a diagram showing FIG. 7 in a different manner. The same description as in FIG. 7 will be omitted as appropriate. FIG. 8 shows an example of a display screen GU41 of output information. The display screen GU41 is displayed by, for example, the terminal device 20. The display screen GU41 has items of "model setting", "evaluation result", "prediction", and "measure proposal", and corresponding information is displayed by the user operating the items. In FIG. 8, information corresponding to the item of "measure proposal" is displayed. The item of this measure proposal indicates the influence degree of each cluster. In addition, a black star mark for the information of the intervention possible item indicates the optimal value of each cluster. For example, the optimal value ST41 indicates the optimal value of cluster C. In addition, a white star mark for the information of the intervention possible item indicates the persona of each cluster. For example, the persona PE44 indicates the persona of cluster C. The value of the objective variable may also change in conjunction with the information of the intervention possible item by freely adjusting the value of the information of the intervention possible item. In FIG. 8, the purchase probability may change in conjunction with the operation on the information of the intervention possible item. The value in parentheses for the purchase probability is the difference between the optimal result and the persona's estimated result. The display screen GU41 may include information that prompts the user to set the information of the intervention-available item to an optimal value.

[0037] In this way, the information processing system 1 executes a search for the optimal value for the persona and estimates the optimal result of the objective variable. The information processing system 1 may also present the user with information on the optimal value and the optimal result that maximizes the purchase probability as an improvement measure proposal. The information processing system 1 may also present how much the purchase probability changes when the user performs the intervention according to the embodiment, compared to when the intervention is not performed. This allows the information processing system 1 to propose an optimal improvement measure proposal to the user and visualize the impact when the user adopts the measure. This allows the user to more quickly make a decision on the formulation of the measure.

[0038] <2.2. Functional configuration example> FIG. 9 is a block diagram showing an example of a functional configuration of the information processing system 1 according to the embodiment.

[0039] (1) Information processing device 10 9, the information processing device 10 includes a communication unit 100 and a control unit 110. The information processing device 10 includes at least the control unit 110.

[0040] (1-1) Communication unit 100 The communication unit 100 has a function of communicating with an external device. For example, in communication with the external device, the communication unit 100 outputs information received from the external device to the control unit 110. Specifically, the communication unit 100 outputs information received from the terminal device 20 to the control unit 110. For example, the communication unit 100 outputs information related to a dataset to be processed to the control unit 110.

[0041] In communication with an external device, the communication unit 100 transmits information input from the control unit 110 to the external device. Specifically, the communication unit 100 transmits information regarding acquisition of information regarding the setting history of intervention-available items input from the control unit 110 to the information providing device 30.

[0042] (1-2) Control unit 110 The control unit 110 has a function of controlling the operation of the information processing device 10. For example, the control unit 110 performs a process for determining information regarding the persona of each cluster.

[0043] In order to realize the above-mentioned functions, the control unit 110 has an acquisition unit 111, a processing unit 112, and an output unit 113, as shown in FIG.

[0044] ·Acquisition part 111 The acquisition unit 111 has a function of acquiring information about a dataset. The acquisition unit 111 acquires information about a response variable and an explanatory variable included in the dataset. The acquisition unit 111 may acquire information about a response variable and an explanatory variable designated in advance by a user as targets for processing. The acquisition unit 111 acquires information about a dataset transmitted from the terminal device 20 via, for example, the communication unit 100. For example, the acquisition unit 111 may acquire information about a dataset in a tabular format designated by a user on a GUI (Graphical User Interface) of the terminal device 20.

[0045] The acquisition unit 111 acquires information regarding the setting history of the intervention possible items. The acquisition unit 111 acquires information regarding the setting history of the intervention possible items that the user manually set in the past. The acquisition unit 111 may acquire information regarding the setting history of the intervention possible items that other users set. For example, the acquisition unit 111 may acquire information regarding the setting history of the intervention possible items that other users who have similar attributes to the user set. The acquisition unit 111 acquires information regarding the setting history of the intervention possible items transmitted from the information providing device 30 via the communication unit 100, for example.

[0046] The acquisition unit 111 acquires information on an intervention-enabled item set by a user. For example, the acquisition unit 111 acquires user correction information on an intervention-enabled item identified by the identification unit 1121. For example, this is the case when the user corrects the intervention-enabled item identified by the identification unit 1121 to an intervention-disabled item. In addition, for example, the acquisition unit 111 may acquire user correction information on the intervention-disabled item identified by the identification unit 1121.

[0047] Processing section 112 The processing unit 112 has a function for controlling the processing of the information processing device 10. The processing unit 112 has a specification unit 1121, an execution unit 1122, a determination unit 1123, an estimation unit 1124, a calculation unit 1125, a generation unit 1126, and a learning unit 1127, as shown in FIG.

[0048] ·Specific section 1121 The identification unit 1121 has a function of identifying information on an intervention possible item. The identification unit 1121 identifies an intervention possible item in which a user can intervene, among explanatory variables used to estimate a target variable. The identification unit 1121 identifies an intervention possible item based on character information (e.g., item name) of an explanatory variable. For example, the identification unit 1121 identifies an intervention possible item by comparing with character information previously defined as an intervention possible item. Specifically, when an item name includes information on the provision of "coupon" or "distribution", the identification unit 1121 identifies the item as an intervention possible item. The identification unit 1121 may identify explanatory variables other than the intervention impossible items as intervention possible items by identifying the intervention impossible items.

[0049] The identification unit 1121 identifies information about the non-intervention item. The identification unit 1121 identifies the non-intervention item in which the user cannot intervene among the explanatory variables used to estimate the objective variable. The identification unit 1121 identifies the non-intervention item based on the character information of the explanatory variable. For example, the identification unit 1121 identifies the non-intervention item by comparing with character information previously defined as the non-intervention item. Specifically, when the item name includes information about attributes such as "age" or "gender", the identification unit 1121 identifies the item as the non-intervention item. The identification unit 1121 may identify the explanatory variables other than the non-intervention item as the non-intervention item by identifying the intervening item.

[0050] The identification unit 1121 identifies an intervening item based on information on the setting history of the intervening item. For example, when the user has set an item "AAA" as an intervening item in the past, the identification unit 1121 identifies the intervening item based on the item name of "AAA". Specifically, when the user has set an item "AABBCC" as an intervening item in the past, the identification unit 1121 identifies an item "AABBBC" that is determined to have a high similarity to "AABBCC" as an intervening item based on the similarity with the item name. The identification unit 1121 may identify an intervening item by learning the item names of the intervening items that the user has set in the past. The identification unit 1121 may also identify an intervening item based on information on the setting history of the intervening items of other users whose attributes are similar to the user. The identification unit 1121 may also identify an inintervening item based on information on the setting history of the intervening items.

[0051] When the user manually sets the intervention item, the identification unit 1121 may identify the intervention item based on information on the user's setting of the intervention item. The identification unit 1121 may identify the intervention item based on the user's modification information. For example, the identification unit 1121 may identify the intervention item based on the user's modification information for the intervention item identified based on the information on the setting history of the intervention item. For example, this is the case when the user modifies the intervention item identified based on the information on the setting history of the intervention item to an intervention-inhibited item. In addition, for example, the identification unit 1121 may identify the intervention item based on the user's modification information for the intervention-inhibited item identified based on the information on the setting history of the intervention item. For example, this is the case when the user modifies the intervention-inhibited item identified based on the information on the setting history of the intervention item to an intervention-inhibited item.

[0052] · Executive Division 1122 The execution unit 1122 has a function of executing clustering based on the non-intervention items. The execution unit 1122 executes clustering based on explanatory variables other than the intervention items. For example, the execution unit 1122 executes clustering based on the k-means method or the Ward method. Note that the k-means method or the Ward method may not be able to determine the optimal number of clusters. In this case, the execution unit 1122 may execute clustering based on the x-means method. The execution unit 1122 may also determine the optimal number of clusters based on the x-means method. The execution unit 1122 may also execute clustering based on a topic model. For example, the execution unit 1122 may execute clustering based on a topic model that determines the number of parameters and generates clusters by assigning weights to each determined parameter. The execution unit 1122 also generates clusters by executing clustering. As a result, the execution unit 1122 can generate clusters of data with similar feature amounts, for example.

[0053] Decision Unit 1123 The determination unit 1123 has a function of determining information regarding the persona of each cluster clustered by the execution unit 1122. For example, the determination unit 1123 determines the center of gravity (e.g., center value) or center (e.g., center value) of data included in each cluster as the persona of each cluster. The determination unit 1123 may also determine information regarding the persona of each cluster based on clustering based on the k-means method, Ward's method, x-means method, or topic model. The persona may also be manually set by the user. In this case, the determination unit 1123 may determine information regarding the persona of each cluster based on the user's setting.

[0054] ·Estimation part 1124 The estimation unit 1124 has a function of estimating an optimal result of the objective variable. The estimation unit 1124 estimates the optimal result based on an estimated result estimated by adjusting information on the intervention-enabled item. Specifically, the estimation unit 1124 estimates the optimal result based on an estimated result estimated by adjusting information on the intervention-enabled item indicated by the persona based on information on the persona determined by the determination unit 1123. The estimation unit 1124 estimates an optimal result for information on the intervention-enabled item indicated by the persona (for example, persona PE14 in FIG. 7). Specifically, the estimation unit 1124 estimates the optimal result by executing a search for an optimal value of the intervention-enabled item that most improves the objective variable in a predetermined direction. In the example of FIG. 2, the estimation unit 1124 executes a search for an optimal value that maximizes the purchase probability. In the example of FIG. 3, the estimation unit 1124 executes a search for an optimal value that minimizes the number of defective products. The estimation unit 1124 executes a search for an optimal value based on a random search or a grid search. In addition, a random search that performs a search probabilistically and a grid search that performs a search according to a predetermined condition may depend on data. The estimation unit 1124 may perform a search for an optimal value based on Bayesian Optimization. In addition, the search for the optimal value may be performed within a range of maximum and minimum values ​​of information of each intervention possible item. For example, in the example of the intervention possible item VB11 in FIG. 7, the estimation unit 1124 performs a search for the optimal value within a range of 0 yen to 5,000 yen.

[0055] In addition, when searching for an optimal value of an intervention possible item that will improve the objective variable most in a predetermined direction, the predetermined direction of the objective variable may be determined by a user. For example, the predetermined direction may be a direction designated by the user based on whether an intervention is better for an increase or decrease.

[0056] The estimation unit 1124 may perform the estimation using a trained model generated by the learning unit 1127 described later. For example, the estimation unit 1124 may perform a search for an optimal value based on information about the persona determined by the determination unit 1123 and the trained model generated by the learning unit 1127.

[0057] Calculation section 1125 The calculation unit 1125 has a function of calculating the contribution degree, which is the weight of each intervention possible item. The calculation unit 1125 calculates the contribution degree of each intervention possible item that contributes to the optimal result estimated by the estimation unit 1124. The calculation unit 1125 calculates the contribution degree of each intervention possible item based on the estimation result of the objective variable. For example, the calculation unit 1125 calculates the contribution degree of each intervention possible item based on the optimal result. Specifically, the calculation unit 1125 calculates the contribution degree of the intervention possible item higher as the fluctuation of the estimation result based on the adjustment of the information of the intervention possible item becomes larger. In addition, the calculation unit 1125 calculates the contribution degree of each intervention possible item based on the optimal value corresponding to the optimal result. For example, the calculation unit 1125 calculates the contribution degree of each intervention possible item based on information on the difference between each information of the intervention possible item corresponding to the optimal result and each information of the intervention possible item indicated by the persona. Specifically, the calculation unit 1125 uses information on an intervention possible item indicated by a persona (for example, persona PE14 in FIG. 7) as a criterion, and calculates the contribution degree of the intervention possible item to be higher as the amount of adjustment based on the criterion is larger.

[0058] ·Generation part 1126 The generating unit 1126 has a function of generating output information indicating information on the persona determined by the determining unit 1123. The generating unit 1126 generates output information indicating a corresponding estimation result in response to an adjustment based on the user's intervention for the information of the intervention-enabled item. For example, the generating unit 1126 generates output information indicating a change in the estimation result based on the user's intervention. This allows the user to appropriately grasp the change in the estimation result by freely changing the value of the intervention-enabled item. Here, if there is an intervention-enabled item that allows the amount of the distributed coupon to be adjusted, the more the amount of the coupon is increased, the more the objective variable is thought to improve, so the optimal value may become extremely high. Even if the optimal value does not exceed the range of the search determined by the estimating unit 1124, it may exceed the range that the user can tolerate. In this case, the user can appropriately grasp the degree of influence based on the change in value by freely changing the value of the intervention-enabled item. This allows the user to appropriately grasp the degree of influence, so that the user can make a decision quickly.

[0059] The generating unit 1126 generates output information indicating each intervention possible item based on a predetermined aspect according to the contribution degree calculated by the calculating unit 1125. The generating unit 1126 determines information on the predetermined aspect indicating each intervention possible item based on the contribution degree. Then, the generating unit 1126 generates output information indicating each intervention possible item based on the information on the determined predetermined aspect. For example, the generating unit 1126 generates output information indicating each intervention possible item in order of the magnitude of the contribution degree. Specifically, when the magnitude of the contribution degree is in the order of "distribution coupon amount" and "presence or absence of direct mail", the generating unit 1126 generates output information indicating each intervention possible item in accordance with that order. Also, for example, the generating unit 1126 may generate output information indicating each intervention possible item based on a heat map according to the contribution degree. For example, the generating unit 1126 may generate output information indicating each intervention possible item based on a heat map that indicates different color information as the contribution degree differs.

[0060] · Learning Department 1127 The learning unit 1127 has a function of generating a trained model that estimates the estimation result of the objective variable. The learning unit 1127 performs a process for generating the trained model. For example, the learning unit 1127 converts information on the data set acquired by the acquisition unit 111 into an appropriate format as a pre-processing of learning. Then, the learning unit 1127 generates the trained model by performing supervised learning using a predetermined learning model. Then, the learning unit 1127 outputs the trained model. Note that the learning unit 1127 may evaluate the accuracy of the trained model by performing cross-validation (cross-confirmation) of the trained model. Note that, when the evaluation of the accuracy of the trained model is equal to or lower than a predetermined threshold, the learning unit 1127 may perform a process for outputting information (for example, a warning) indicating that the evaluation of the accuracy of the trained model is low, from the output unit 113 described later.

[0061] Output section 113 The output unit 113 has a function of outputting the output information generated by the generation unit 1126. The output unit 113 provides the generated output information to, for example, the terminal device 20 via the communication unit 100. Upon receiving the output information provided from the output unit 113, the terminal device 20 displays the output information via the output unit 220. The output unit 113 may provide control information for displaying the output information.

[0062] (2) Terminal device 20 As shown in FIG. 9, the terminal device 20 includes a communication unit 200, a control unit 210, and an output unit 220.

[0063] (2-1) Communications Department 200 The communication unit 200 has a function of communicating with an external device. For example, in communication with the external device, the communication unit 200 outputs information received from the external device to the control unit 210. Specifically, the communication unit 200 outputs information received from the information processing device 10 to the control unit 210. For example, the communication unit 200 outputs output information generated by the information processing device 10 to the control unit 210.

[0064] (2-2) Control unit 210 The control unit 210 has a function of controlling the operation of the terminal device 20. For example, the control unit 210 transmits information about a dataset to the information processing device 10 via the communication unit 200. For example, the control unit 210 transmits information about a dataset input by a user to the information processing device 10.

[0065] (2-3) Output unit 220 The output unit 220 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 220 displays output information generated by the information processing device 10.

[0066] (3) Information provision device 30 As shown in FIG. 9, the information providing device 30 includes a communication unit 300, a control unit 310, and a storage unit 320.

[0067] (3-1) Communications unit 300 The communication unit 300 has a function of communicating with an external device. For example, in communication with the external device, the communication unit 300 outputs information received from the external device to the control unit 310. Specifically, the communication unit 300 outputs information received from the information processing device 10 to the control unit 310. For example, the communication unit 300 outputs information regarding acquisition of information regarding the setting history of intervention-enabled items to the control unit 310.

[0068] (3-2) Control unit 310 The control unit 310 has a function of controlling the operation of the information providing device 30. For example, the control unit 310 transmits information related to the setting history of the intervention possible items to the information processing device 10 via the communication unit 300. For example, the control unit 310 transmits information related to the setting history of the intervention possible items obtained by accessing the storage unit 320 to the information processing device 10.

[0069] (3-3) Storage section 320 The storage unit 320 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 320 has a function of storing data related to the processing in the information providing device 30.

[0070] Fig. 10 shows an example of the storage unit 320. The storage unit 320 shown in Fig. 10 stores information related to the setting history of the intervention possible items. As shown in Fig. 10, the storage unit 320 may have items such as "user ID" and "setting history".

[0071] "User ID" indicates identification information for identifying a user. "Settings history" indicates information related to the history of settings made by the user in the past. In the example shown in FIG. 10, conceptual information such as "settings history #11" and "settings history #12" is stored in "settings history", but in reality, information such as the item names used to set intervention-enabled items is stored.

[0072] <2.3. Processing of information processing system> The functions of the information processing system 1 according to the embodiment have been described above. Next, the processing of the information processing system 1 will be described.

[0073] (1) Process 1 in the information processing device 10: Determination of persona FIG. 11 is a flowchart showing a flow of processing in the information processing device 10 according to the embodiment. First, the information processing device 10 acquires a dataset (S101). Next, the information processing device 10 identifies a target variable and an explanatory variable included in the acquired dataset (S102). Next, the information processing device 10 identifies an intervention-enabled item and an intervention-disabled item among the identified explanatory variables (S103). Then, the information processing device 10 generates a cluster based on the identified intervention-disabled item (S104). Then, the information processing device 10 determines information related to the persona of each generated cluster (S105). Then, the information processing device 10 generates output information indicating information related to the determined persona (S106).

[0074] (2) Process 2 in the information processing device 10: Search for optimal value FIG. 12 is a flowchart showing a flow of processing in the information processing device 10 according to the embodiment. First, the information processing device 10 acquires an estimation result of a target variable estimated by adjusting information on an intervention-enabled item indicated by a persona (S201). Next, the information processing device 10 judges whether the acquired estimation result is optimal or not (S202). Then, when the information processing device 10 judges that the acquired estimation result is not optimal (S202; NO), the process returns to step S201. In this case, the information processing device 10 acquires a new estimation result estimated by adjusting information on an intervention-enabled item indicated by a persona. Also, when the information processing device 10 judges that the acquired estimation result is optimal (S202; YES), the information processing device 10 estimates the estimation result as an optimal result (S203). Then, the information processing device 10 generates output information indicating information on the optimal result (S204).

[0075] (3) Process 3 in the information processing device 10: Generation of output information based on the contribution degree 13 is a flowchart showing a process flow in the information processing device 10 according to the embodiment. First, the information processing device 10 calculates the contribution degree of each intervention possible item (S301). Next, the information processing device 10 determines information on a predetermined aspect indicating each intervention possible item based on the calculated contribution degree (S302). Then, the information processing device 10 generates output information indicating each intervention possible item based on the determined information on the predetermined aspect (S303).

[0076] <2.4. Processing variations> The embodiments of the present disclosure have been described above. Next, variations of the processing of the embodiments of the present disclosure will be described. The processing variations described below may be applied alone to the embodiments of the present disclosure, or may be applied in combination to the embodiments of the present disclosure. The processing variations may be applied in place of the configurations described in the embodiments of the present disclosure, or may be applied in addition to the configurations described in the embodiments of the present disclosure.

[0077] (1) Acquisition of information about setting history In the above embodiment, the information processing device 10 acquires information on the setting history of the intervention-enabled item from the information providing device 30. Here, the information processing device 10 may acquire information on the setting history of the intervention-disabled item from the information providing device 30. Specifically, the acquisition unit 111 may acquire information on the setting history of the intervention-disabled item. In this case, the storage unit 320 may store information on the setting history of the intervention-disabled item. Then, the control unit 310 may access the storage unit 320 to acquire information on the setting history of the intervention-disabled item, and provide it to the information processing device 10 via the communication unit 300. Also, the information processing device 10 may acquire information on the setting history of either one of the intervention-enabled item and the intervention-disabled item, or both. Then, the information processing device 10 may identify the intervention-disabled item based on the information on the setting history of the intervention-disabled item.

[0078] (2) Obtaining information to identify items that cannot be intervened In the above embodiment, the information processing device 10 acquires information for identifying an uninterventionable item included in the data set from the information providing device 30. Here, the information processing device 10 may have a storage unit (hereinafter, appropriately referred to as the "storage unit 120") that stores information similar to the storage unit 320. In this case, the control unit 110 may access the storage unit 120 to acquire information for identifying an uninterventionable item. In addition, the information processing device 10 may acquire information for identifying an uninterventionable item from the terminal device 20. The terminal device 20 may have a storage unit (hereinafter, appropriately referred to as the "storage unit 230") that stores information similar to the storage unit 320. In this case, the control unit 210 may access the storage unit 230 to acquire information for identifying an uninterventionable item. Then, the control unit 210 may provide the information for identifying an uninterventionable item to the information processing device 10 via the communication unit 200.

[0079] (3) Fixed items In the above embodiment, the information processing system 1 may receive information for performing clustering based on some of the non-intervention items from the user. For example, this is the case when the user wants to fix the information of some of the non-intervention items. For example, this is the case when the user wants to perform clustering by narrowing down to a specific age, sex, or generation. In order to perform clustering based on some of the non-intervention items, the non-intervention items specified by the user are hereinafter referred to as "fixed items" as appropriate. Fixed items are non-intervention items that are excluded from the target of clustering processing among non-intervention items. Note that fixed items may be specified at any timing before the clustering processing. In addition, since fixed items are non-intervention items, it is assumed that the information of the fixed items cannot be adjusted for the purpose of adjusting the objective variable after the generation of output information.

[0080] The acquisition unit 111 may acquire information about the fixed items designated by the user. The acquisition unit 111 may acquire information about the fixed items transmitted from the terminal device 20 via the communication unit 100, for example. Then, the identification unit 1121 may identify the non-intervention items other than the fixed items. Then, the execution unit 1122 may execute the clustering process based on the non-intervention items other than the fixed items. The generation unit 1126 may generate output information indicating information about the personas of each cluster generated based on the non-intervention items other than the fixed items. Note that the generation unit 1126 may generate output information including information about the personas of each cluster generated based on all non-intervention items without designation of the fixed items, together with information about the personas of each cluster generated based on the non-intervention items other than the fixed items. In this case, the generation unit 1126 may generate the output information such that information about the personas of each cluster generated based on the non-intervention items other than the fixed items is included in a predetermined area of ​​the output information.

[0081] The information processing system 1 may specify fixed items based on information on the user's past setting history, not limited to when the user specifies fixed items. Also, the user does not have to specify fixed items, but when a fixed item is specified, the information processing system 1 may modify the specified item as a fixed item and perform processing. Note that the information processing system 1 may have the user specify fixed items before executing the clustering process. Then, the information processing system 1 may specify non-intervention items to be subject to the clustering process, based on information on the fixed items specified based on information on the user's past setting history.

[0082] <<3. Hardware configuration example>> Finally, a hardware configuration example of the information processing device according to the embodiment will be described with reference to Fig. 14. Fig. 14 is a block diagram showing a hardware configuration example of the information processing device according to the embodiment. Note that the information processing device 900 shown in Fig. 14 can realize, for example, the information processing device 10, the terminal device 20, and the information providing device 30 shown in Fig. 9. Information processing by the information processing device 10, the terminal device 20, and the information providing device 30 according to the embodiment is realized by cooperation between software and hardware described below.

[0083] 14, the information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, and a RAM (Random Access Memory) 903. The information processing device 900 also includes a host bus 904a, a bridge 904, an external bus 904b, an interface 905, an input device 906, an output device 907, a storage device 908, a drive 909, a connection port 910, and a communication device 911. Note that the hardware configuration shown here is an example, and some of the components may be omitted. Also, the hardware configuration may further include components other than the components shown here.

[0084] The CPU 901 functions as, for example, an arithmetic processing device or a control device, and controls the overall operation or a part of the operation of each component based on various programs recorded in the ROM 902, the RAM 903, or the storage device 908. The ROM 902 is a means for storing programs loaded into the CPU 901 and data used for calculations. The RAM 903 temporarily or permanently stores, for example, programs loaded into the CPU 901 and various parameters that change appropriately when the programs are executed. These are connected to each other by a host bus 904a consisting of a CPU bus or the like. The CPU 901, the ROM 902, and the RAM 903 can realize the functions of the control unit 110, the control unit 210, and the control unit 310 described with reference to FIG. 9, for example, in cooperation with software.

[0085] The CPU 901, ROM 902, and RAM 903 are connected to one another via, for example, a host bus 904a capable of high-speed data transmission. On the other hand, the host bus 904a is connected to an external bus 904b having a relatively low data transmission speed via, for example, a bridge 904. In addition, the external bus 904b is connected to various components via an interface 905.

[0086] The input device 906 is realized by a device to which information is input by a listener, such as a mouse, a keyboard, a touch panel, a button, a microphone, a switch, and a lever. The input device 906 may be, for example, a remote control device using infrared rays or other radio waves, or an externally connected device such as a mobile phone or a PDA that supports the operation of the information processing device 900. Furthermore, the input device 906 may include, for example, an input control circuit that generates an input signal based on information input using the above-mentioned input means and outputs it to the CPU 901. An administrator of the information processing device 900 can input various data to the information processing device 900 and instruct the information processing device 900 to perform processing operations by operating the input device 906.

[0087] Alternatively, the input device 906 may be formed by a device that detects the position of the user. For example, the input device 906 may include various sensors such as an image sensor (e.g., a camera), a depth sensor (e.g., a stereo camera), an acceleration sensor, a gyro sensor, a geomagnetic sensor, a light sensor, a sound sensor, a distance sensor (e.g., a ToF (Time of Flight) sensor), and a force sensor. The input device 906 may also acquire information on the state of the information processing device 900 itself, such as the attitude and moving speed of the information processing device 900, and information on the surrounding space of the information processing device 900, such as brightness and noise around the information processing device 900. The input device 906 may also include a GNSS module that receives a GNSS signal from a GNSS (Global Navigation Satellite System) satellite (e.g., a GPS signal from a GPS (Global Positioning System) satellite) to measure position information including the latitude, longitude, and altitude of the device. Regarding the location information, the input device 906 may detect the location by transmitting and receiving data to and from a Wi-Fi (registered trademark), a mobile phone, a PHS, a smartphone, or by short-distance communication. The input device 906 may realize, for example, the function of the acquisition unit 111 described with reference to FIG.

[0088] The output device 907 is formed of a device capable of visually or aurally notifying the user of acquired information. Such devices include display devices such as CRT display devices, liquid crystal display devices, plasma display devices, EL display devices, laser projectors, LED projectors, and lamps, audio output devices such as speakers and headphones, and printer devices. The output device 907 outputs, for example, results obtained by various processes performed by the information processing device 900. Specifically, the display device visually displays the results obtained by various processes performed by the information processing device 900 in various formats such as text, image, table, and graph. On the other hand, the audio output device converts audio signals consisting of reproduced audio data, audio data, and the like into analog signals and aurally outputs them. The output device 907 can realize, for example, the functions of the output unit 113 and the output unit 220 described with reference to FIG. 9.

[0089] The storage device 908 is a data storage device formed as an example of a storage unit of the information processing device 900. The storage device 908 is realized by, for example, a magnetic storage device such as an HDD, a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 908 may include a storage medium, a recording device for recording data in the storage medium, a reading device for reading data from the storage medium, and a deleting device for deleting data recorded in the storage medium. The storage device 908 stores the programs and various data executed by the CPU 901, and various data acquired from the outside. The storage device 908 may realize, for example, the function of the storage unit 320 described with reference to FIG. 9.

[0090] The drive 909 is a reader / writer for a storage medium, and is built into or externally attached to the information processing device 900. The drive 909 reads out information recorded on a removable storage medium, such as an attached magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 903. The drive 909 can also write information to the removable storage medium.

[0091] The connection port 910 is a port for connecting an external device, such as a Universal Serial Bus (USB) port, an IEEE1394 port, a Small Computer System Interface (SCSI), an RS-232C port, or an optical audio terminal.

[0092] The communication device 911 is, for example, a communication interface formed by a communication device for connecting to the network 920. The communication device 911 is, for example, a communication card for a wired or wireless LAN (Local Area Network), LTE (Long Term Evolution), Bluetooth (registered trademark), or WUSB (Wireless USB). The communication device 911 may also be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communications. The communication device 911 can transmit and receive signals, for example, between the Internet and other communication devices in accordance with a predetermined protocol such as TCP / IP. The communication device 911 can realize the functions of the communication unit 100, the communication unit 200, and the communication unit 300 described with reference to FIG. 9.

[0093] The network 920 is a wired or wireless transmission path for information transmitted from devices connected to the network 920. For example, the network 920 may include public line networks such as the Internet, telephone lines, and satellite communication networks, as well as various types of LANs (Local Area Networks) including Ethernet (registered trademark), and WANs (Wide Area Networks). The network 920 may also include a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network).

[0094] An example of a hardware configuration capable of realizing the functions of the information processing device 900 according to the embodiment has been described above. Each of the above components may be realized using general-purpose components, or may be realized by hardware specialized for the function of each component. Therefore, the hardware configuration to be used can be changed as appropriate depending on the technical level at the time of implementing the embodiment.

[0095] <<4. Summary>> As described above, the information processing device 10 according to the embodiment performs a process of determining information about the persona of each cluster generated based on the non-intervention items. As a result, the information processing device 10 can determine a plurality of representative data items that should be noted by unsupervised learning, thereby enabling the user to make decisions more quickly. As a result, the information processing device 10 can promote further improvement of usability.

[0096] Furthermore, the information processing device 10 generates output information indicating information on the determined persona. For example, the information processing device 10 generates output information indicating a corresponding estimation result in response to an adjustment based on a user's intervention on information on an intervention-enabled item. This allows the information processing device 10 to propose an optimal improvement measure to the user and visualize the impact of the user adopting the measure. This allows the information processing device 10 to promote improvement in the quality and speed of user decision-making by visualizing the best measure for each cluster and its impact.

[0097] It is therefore possible to provide a new and improved information processing device, information processing method, and information processing program that can promote further improvement in usability.

[0098] Although the preferred embodiment of the present disclosure has been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person having ordinary knowledge in the technical field of the present disclosure can conceive of various modified or amended examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally belong to the technical scope of the present disclosure.

[0099] For example, each device described in this specification may be realized as a single device, or some or all of them may be realized as separate devices. For example, the information processing device 10, the terminal device 20, and the information providing device 30 shown in Fig. 9 may each be realized as a single device. Also, for example, they may be realized as a server device connected to the information processing device 10, the terminal device 20, and the information providing device 30 via a network or the like. Also, a configuration may be such that the function of the control unit 110 of the information processing device 10 is provided to a server device connected via a network or the like.

[0100] Furthermore, the series of processes performed by each device described in this specification may be realized using any of software, hardware, and a combination of software and hardware. The programs constituting the software are stored in advance, for example, in a recording medium (non-transitory medium) provided inside or outside each device. Then, each program is loaded into a RAM when executed by a computer, and executed by a processor such as a CPU.

[0101] In addition, the processes described herein using flowcharts do not necessarily have to be performed in the order shown. Some process steps may be performed in parallel. Additional process steps may be employed, and some process steps may be omitted.

[0102] In addition, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that are apparent to a person skilled in the art from the description of this specification, in addition to or in place of the above effects.

[0103] Note that the following configurations also fall within the technical scope of the present disclosure. (1) An identification unit that identifies an intervention possible item, which is an explanatory variable in which a user can intervene, among explanatory variables used to estimate a target variable; A determination unit that determines information regarding a persona of each cluster generated based on non-interventionable items that are explanatory variables other than the interventionable items identified by the identification unit; An information processing device comprising: (2) A calculation unit that calculates a contribution degree, which is a weight of each intervention possible item, based on an estimation result of the objective variable estimated by adjusting information of the intervention possible item indicated by the persona. The information processing device according to (1). (3) The calculation unit is The contribution degree is calculated based on an optimal result in which the estimation result is optimal. The information processing device according to (2). (4) The calculation unit is The contribution degree is calculated based on information on the difference between each piece of information on the intervention possible items corresponding to the optimal result and each piece of information on the intervention possible items indicated by the persona. The information processing device according to (3). (5) The calculation unit is Using the information indicated by the persona as a criterion, the greater the amount of adjustment based on the criterion, the higher the contribution degree of the intervention-enabled item that contributes to the optimal result is calculated. The information processing device according to (3) or (4). (6) The calculation unit is Calculating the contribution based on the optimal result determined based on a random search, a grid search, or Bayesian optimization. The information processing device according to any one of (3) to (5). (7) A generation unit that generates output information indicating information related to the persona determined by the determination unit. The information processing device according to any one of (2) to (6). (8) The generation unit is In response to the adjustment based on the user's intervention on the information of the intervention-enabled item, the output information indicating the corresponding estimation result is generated. The information processing device according to (7). (9) The generation unit is The output information indicating each of the intervention possible items is generated based on a predetermined aspect corresponding to the contribution degree calculated by the calculation unit. The information processing device according to (7) or (8). (10) The generation unit is Generate the output information indicating each of the intervention possible items in order of the contribution degree. The information processing device according to (9). (11) The generation unit is The output information indicating each of the intervention possible items is generated based on a heat map according to the contribution degree, the heat map indicating different color information as the contribution degree differs. The information processing device according to (9) or (10). (12) The identification unit is Identifying a fixed item, which is an inoperable item whose information has been fixed in advance by the user, among the inoperable items; The determination unit is Determine information about the persona of each cluster generated based on the non-intervention items other than the fixed items identified by the identification unit. The information processing device according to any one of (1) to (11). (13) The determination unit is Determine information about the persona based on k-means or topic models The information processing device according to any one of (1) to (12). [Explanation of symbols]

[0104] 1. Information Processing Systems 10. Information processing device 20 Terminal Equipment 30 Information provision device 100 Communications Department 110 Control section 111 Acquisition Department 112 Processing section 1121 Specific part 1122 Executive Department 1123 Decision Section 1124 Estimation Department 1125 Calculation Department 1126 Generation part 1127 Learning Department 113 Output section 200 Communications Department 210 Control section 220 Output section 300 Communications Department 310 Control section 320 Storage section

Claims

1. An identification unit that identifies an intervention possible item, which is an explanatory variable in which a user can intervene, among explanatory variables used to estimate a target variable; A determination unit that determines information regarding a persona of each cluster generated based on an inintervention-inhibited item that is an explanatory variable other than the intervention-inhibited item identified by the identification unit; An information processing device comprising:

2. A calculation unit that calculates a contribution degree, which is a weight of each intervention possible item, based on an estimation result of the objective variable estimated by adjusting information of the intervention possible item indicated by the persona. The information processing device according to claim 1 .

3. The calculation unit is The contribution degree is calculated based on an optimal result in which the estimation result is optimal. The information processing device according to claim 2 .

4. The calculation unit is The contribution degree is calculated based on information on the difference between each piece of information on the intervention possible items corresponding to the optimal result and each piece of information on the intervention possible items indicated by the persona. The information processing device according to claim 3 .

5. The calculation unit is Using the information indicated by the persona as a criterion, the greater the amount of adjustment based on the criterion, the higher the contribution degree of the intervention-enabled item that contributes to the optimal result is calculated. The information processing device according to claim 3 .

6. The calculation unit is The contribution is calculated based on the optimal result determined based on a random search, a grid search, or a Bayesian optimization. The information processing device according to claim 3 .

7. A generation unit that generates output information indicating information related to the persona determined by the determination unit. The information processing device according to claim 2 .

8. The generation unit is In response to the adjustment based on the user's intervention on the information of the intervention-enabled item, the output information indicating the corresponding estimation result is generated. The information processing device according to claim 7.

9. The generation unit is The output information indicating each of the intervention possible items is generated based on a predetermined aspect corresponding to the contribution degree calculated by the calculation unit. The information processing device according to claim 7.

10. The generation unit is Generate the output information indicating each of the intervention possible items in order of the contribution degree. The information processing device according to claim 9.

11. The generation unit is The output information indicating each of the intervention possible items is generated based on a heat map according to the contribution degree, the heat map indicating different color information as the contribution degree differs. The information processing device according to claim 9.

12. The identification unit is Identifying a fixed item, which is an inoperable item whose information has been fixed in advance by the user, among the inoperable items; The determination unit is Determine information about the persona of each cluster generated based on the non-intervention items other than the fixed items identified by the identification unit. The information processing device according to claim 1 .

13. The determination unit is Determine information about the persona based on k-means or topic models The information processing device according to claim 1 .

14. 1. A computer-implemented information processing method, comprising: An identification step of identifying an intervention possible item, which is an explanatory variable in which a user can intervene, among explanatory variables used to estimate the objective variable; A determination step of determining information regarding a persona of each cluster generated based on non-interventionable items that are explanatory variables other than the interventionable items identified by the identification step; An information processing method comprising:

15. A step of identifying an intervention-enabled item, which is an explanatory variable in which a user can intervene, among explanatory variables used to estimate a target variable; A determination procedure for determining information about a persona of each cluster generated based on non-intervention items, which are explanatory variables other than the intervention items identified by the identification procedure; An information processing program that causes a computer to execute the above.

Citation Information

Patent Citations

  • Method and apparatus of data analysis, program, and recording medium with the program recorded thereon

    JP2004220236A

  • Information processing device, information processing method, and program

    WO2019130974A1