JP7138067B2 - Information processing device and control method for information processing device - Google Patents

Description

The present invention relates to an information processing device and a control method for the information processing device.

Conventionally, there are various techniques for quantitatively evaluating human tactile sensations. For example, Patent Literature 1 discloses a technique for quantitatively evaluating gripping comfort including human tactile sensation and familiarity using compression characteristics, compression strain amount, friction coefficient, and the like.

JP 2006-101935 A

By the way, even if the same object is touched in the same way, the tactile sensation and the impression recollected from the tactile sensation differ from person to person. In other words, there are individual differences in impressions when touching objects. One of the reasons for this is that when the human brain recognizes and processes tactile stimuli, the person's past memories or preferences greatly affect the recognition process. However, in the tactile evaluation using the conventional technology, individual differences in impressions of objects as described above are not taken into consideration.

An object of one aspect of the present invention is to make it possible to estimate individual differences in impressions.

In order to solve the above-described problems, an information processing apparatus according to an aspect of the present invention includes a physical property data acquisition unit that acquires physical property data indicating material physical properties of a product; a phenomenon data acquisition unit that acquires phenomenon data that is related data; a sensitivity data acquisition unit that acquires sensitivity data representing the perception that the person feels when the product is touched and the impression that is recollected from the perception; a cluster identifying unit that identifies a personality cluster indicating a type of correlation between the tactile stimulus and the impression based on the phenomenon data and the sensibility data; a model construction unit that constructs a learning model obtained by machine-learning the correlation between the 1 input data and the individual clusters.

In order to solve the above-described problems, a control method for an information processing apparatus according to an aspect of the present invention includes a physical property data obtaining step of obtaining physical property data indicating material physical properties of a product; A phenomenon data acquisition step of acquiring phenomenon data, which is data related to tactile stimulation, and a sensory data acquisition step of acquiring sensory data representing the perception that the person feels when touching the product and the impression evoked by the perception. a personality cluster identifying step of identifying a personality cluster indicating a type of correlation between the tactile stimulus and the impression based on the phenomenon data and the sensibility data; the physical property data, the phenomenon data, and the sensibility A model construction step of constructing a learning model by machine-learning the correlation between the first input data consisting of data and the personality cluster.

According to the above configuration or processing, the correlation between the tactile stimulus and the impression is based on the material physical properties of the product, the data on the human tactile stimulus, and the data indicating the impression that the human has on the product. It is possible to construct a learning model that can estimate personality clusters that show The correlation between tactile stimuli and impressions can also be understood as individual differences in impressions. Therefore, according to the configuration or processing described above, it is possible to construct a learning model capable of estimating individual differences in impressions.

The cluster identifying unit of the information processing device identifies a perceptual cluster indicating a type of correlation between the tactile stimulus and the perception, and a sensitivity cluster indicating a type of correlation between the perception and the impression. Alternatively, the personality cluster may consist of a combination of the perception cluster and the sensitivity cluster.

According to the above configuration, the personality cluster can be specified in more detail. Therefore, it is possible to construct a learning model capable of estimating individual differences in impressions in more detail.

The cluster identification unit of the information processing device may identify the individual cluster based on similarity of the phenomenon data and the sensitivity data of a plurality of persons with respect to the same product. According to the above configuration, individuality clusters can be specified more accurately.

To solve the above-described problems, an information processing apparatus according to an aspect of the present invention includes an estimation physical property data acquisition unit that acquires estimation physical property data; an estimation phenomenon data acquisition unit that acquires certain user estimation phenomenon data; an estimation sensory data acquisition unit that acquires the estimation sensory data of a given user; and the estimation physical property data, the estimation phenomenon data, and the estimation sensory data to create second input data. a second input data creation unit, physical property data indicating material properties of a product, phenomenon data indicating tactile stimulation when a human touches the product, and when the human touches the product. The correlation between the first input data created using the sensitivity data indicating the perception and the impression evoked from the perception, and the personality cluster indicating the type of correlation between the tactile stimulus and the impression. an estimating unit that estimates the personality cluster of the user from the second input data using a learning model subjected to machine learning, wherein the physical property data for estimation is obtained from at least part of information of the physical property data. The phenomenon data for estimation consists of at least part of information of the phenomenon data, and the sensitivity data for estimation consists of information of at least part of the sensitivity data.

In order to solve the above problems, a control method for an information processing apparatus according to an aspect of the present invention is a control method for an information processing apparatus, comprising: an estimation physical property data acquisition step of acquiring estimation physical property data; an estimation phenomenon data acquisition step of acquiring estimation phenomenon data of a user; an estimation sensitivity data acquisition step of acquiring estimation sensitivity data of a certain user; the estimation physical property data; the estimation phenomenon data; a second input data creating step of creating second input data using the sensory data for estimation; physical property data representing material properties of the product; and data relating to tactile stimulation when a human touches the product first input data created using phenomenon data and sensory data representing the perception that a person feels when touching the product and the impression evoked by the perception; and the tactile stimulus and the impression. and an estimating step of estimating the personality cluster of the certain user from the second input data using a learning model obtained by machine-learning the correlation between a personality cluster indicating a type of correlation, and The physical property data consists of at least part of the physical property data, the estimation phenomenon data consists of at least part of the phenomenon data, and the estimation sensitivity data consists of at least part of the sensitivity data. Consists of information.

According to the above configuration or processing, the personality cluster of a certain user is determined based on the material properties of the product, the data on the user's tactile stimulus, and the data indicating the user's impression of the product. can be estimated.

In the information processing device, the phenomenon data and the estimation phenomenon data may include data relating to physical properties of the user's fingers. According to the above configuration, individual clusters can be estimated in consideration of the physical properties of fingers that differ from person to person. Therefore, it is possible to improve the estimation accuracy of individuality clusters.

In the information processing device, the phenomenon data and the estimating phenomenon data may include data relating to a physical action occurring between the product and a finger of the user touching the product. According to the above configuration, the individuality cluster can be estimated in consideration of how the user touches the product. Therefore, it is possible to improve the estimation accuracy of individuality clusters.

The information processing device provides an axis indicating a physical property value related to material properties of an object, or an axis indicating an action value, which is a value related to a physical action occurring between the object and a human finger, each of which has a different type. In a multidimensional space consisting of a plurality of axes indicating the physical property value or the action value of the multidimensional space, an impression area indicating the type of impression that humans have with respect to the physical property value or the action value indicated by each coordinate value in the multidimensional space an impression map creating unit for creating a mapped impression map for each of the individuality clusters; an input information acquisition unit for acquiring information indicating an input operation for designating one of the impression areas; and the input operation in the product impression map. a product identifying unit that identifies, as a recommended product, a product whose coordinate values are included in the impression area designated by the .

According to the above configuration, it is possible to recommend a product included in an impression area designated by the user, that is, a product having a physical property value or an effect value that can give an impression designated by the user. Thereby, an appropriate product can be recommended to the user.

In the information processing device, at least one of the plurality of axes of the impression map may be an axis indicating the effect value. The information processing device includes a product effect value calculation unit that calculates the effect value of each product based on the estimation phenomenon data acquired by the estimation phenomenon data acquisition unit, and the product impression map is created. A unit may plot the coordinate values including the effect value of each of the products calculated by the product effect value calculation unit.

According to the above configuration, it is possible to create a product impression map and present a recommended product in consideration of individual differences such as how a user touches a product. Therefore, a more suitable product can be recommended to the user.

In the information processing device, the product identification unit identifies a plurality of the recommended products, and the product information presentation unit selects the impression specified in the product impression map from among information related to each of the plurality of recommended products. A recommended product plotted closer to the center of the area may be preferentially presented.

According to the above configuration, it is possible to recommend a product that is more likely to give the user the specified impression. Therefore, it is possible to recommend a more appropriate product to the user.

According to one aspect of the present invention, it is possible to estimate individual differences in impression.

1 is a diagram showing an overview of a learning system according to Embodiment 1; FIG. 2 is a block diagram showing a configuration of main parts of an information processing device included in the learning system; FIG. It is a figure which shows the flow of a learning model construction process. FIG. 11 is a diagram showing an outline of an estimation system according to Embodiment 2; FIG. It is a block diagram which shows the principal part structure of the information processing apparatus 2 contained in the said estimation system. It is a figure which shows the flow of a personality cluster estimation process. FIG. 11 is a block diagram showing the main configuration of an information processing apparatus according to Embodiment 3; FIG. 11 is a diagram showing an outline of processing of an information processing apparatus according to a fourth embodiment; FIG. 3 is a block diagram showing a configuration of main parts of the information processing apparatus; FIG. It is a figure which shows an example of an impression map and a product impression map. It is a figure which shows the flow of recommendation processing. FIG. 12 is a block diagram showing the main configuration of an information processing apparatus according to Embodiment 5; FIG. 10 is a diagram showing the flow of range specifying processing; FIG. 12 is a block diagram showing the main configuration of an information processing apparatus according to Embodiment 6; FIG. 14 is a block diagram showing the main configuration of an information processing apparatus according to Embodiment 7;

Aspects of the present invention will be described below based on Embodiments 1 to 8. The scope of application of the present invention is not particularly limited. It can be suitably used for recommendation and development of the product.

[Embodiment 1]
≪Outline of the learning system≫
A learning system 1000 according to an aspect of the present invention is a system for constructing a learning model capable of estimating individual differences in impressions. The learning system 1000 includes material properties of a sample product for building a learning model, data on the tactile stimulus of the tester (paneler) to the sample product, and the perception and the feeling when the panelist touches the sample product. Data representing impressions recollected by perception are used as input data, and teacher data is created using individual clusters representing types of individual differences in impressions as correct data. Learning system 1000 then executes machine learning using the teacher data. As a result, learning system 1000 can construct a learning model capable of estimating individuality clusters from at least a portion of the aforementioned input data.

FIG. 1 is a diagram showing an overview of a learning system 1000 according to this embodiment. Learning system 1000 includes at least information processing device 1 and sensor group 9 . The information processing device 1 and the sensor group 9 are connected by wire or wirelessly.

(Information processing device 1)
The information processing device 1 is a device for constructing the aforementioned learning model. The information processing device 1 can be realized by, for example, a personal computer (PC) or the like. The information processing apparatus 1 constructs a learning model based on physical property data, phenomenon data, and sensitivity data.

(Data used for building a learning model)
The physical property data are data indicating material physical properties of the sample product. The phenomenon data refers to data related to tactile stimuli that occur when the panelists touch the sample products. The sensibility data is data indicating the sensations felt by the panelists when they touched the sample products and the impressions recalled from the sensations.

Here, "perception" refers to tactile sensations recognized and sensed by the human brain receiving tactile stimulation. Here, the term "impression" refers to the impression that the sample product has or is recollected from the sample product through the sense of touch. More specifically, "perception" refers to sensations such as softness, warmth, and smoothness. Further, the "impression" indicates a sensation indirectly recalled from touch feeling, such as luxury, casual, beautiful, and good.

The method of acquiring these three types of data is not particularly limited, but unless otherwise specified, the information processing apparatus 1 according to this embodiment acquires these three types of data by the method described below. That is, the information processing apparatus 1 acquires the physical property data by reading the physical property data stored in advance in its own storage unit (storage unit 12 to be described later). The information processing device 1 also acquires measurement information from the sensor group 9 as phenomenon data. Further, the information processing apparatus 1 acquires sensitivity data via its own input unit (input unit 11 to be described later). For example, the information processing device 1 acquires the contents of a detailed questionnaire input by a panelist or an administrator of the learning system 1000 as sensitivity data.

The detailed questionnaire is a questionnaire asking the panelists about their perceptions and impressions when they touched the sample products. FIG. 1 shows an example in which the details of the detailed questionnaire filled in by the panelists are input to the information processing apparatus 1 later, but the answers to the detailed questionnaire may be directly input to the information processing apparatus 1 by the panelists. There are no particular restrictions on the categories of perception and impression when touching the sample product. For example, the perception may be the texture type of the sample product, such as "soft" or "hard." Further, for example, the impression may be a type of feeling indirectly recalled from touch, such as "beautiful", "luxury", and "intelligent".

(Sensor group 9)
The sensor group 9 is a sensor group for measuring phenomenon data. For example, phenomenon data includes pressure applied to an object (sample product in this embodiment), shear force of the object, coefficient of friction between a person's finger and the object, etc. may include data relating to physical effects occurring in Further, for example, the phenomenon data may include data relating to the physical properties of the finger of the person who touched the object, such as the length, thickness, and shape of the finger of the person. Further, for example, the phenomenon data may include data indicating the trajectory of a finger when a person touches an object, or the contact time with the object.

The type and number of sensors included in the sensor group 9 may be determined based on the type of phenomenon data required for construction of the learning model in the information processing device 1 . For example, sensor group 9 may include a pressure sensor for measuring the pressure exerted on the object. Further, the sensor group 9 may include a camera or the like for measuring the physical properties of human fingers and for measuring the trajectory of the fingers. Moreover, the sensor group 9 may include a timer for measuring the contact time between the finger and the object.

≪Main part composition≫
FIG. 2 is a block diagram showing the main configuration of the information processing device 1 included in the learning system 1000. As shown in FIG. In addition, in the figure, the sensor group 9 is also illustrated together. Information processing apparatus 1 includes at least control unit 10 , input unit 11 , and storage unit 12 .

(Input unit 11)
The input unit 11 is a user interface (UI) that receives various input operations. The input unit 11 is implemented by, for example, a physical keyboard, touch panel, mouse, or the like. Upon receiving an input operation, the input unit 11 notifies the input information acquisition unit 101 of the control unit 10 of the contents of the input operation. The input unit 11 according to this embodiment receives an input operation for inputting sensitivity data.

(control unit 10)
The control unit 10 comprehensively controls each unit included in the information processing apparatus 1 . The control unit 10 includes an input information acquisition unit 101 , a sensor information acquisition unit 102 , a database information acquisition unit 103 , a cluster identification unit 104 , a first input data generation unit 105 and a model construction unit 106 .

An input information acquisition unit (sensory data acquisition unit) 101 acquires input information indicating the content of an input operation received by the input unit 11 . For example, in this embodiment, the input information acquisition unit 101 acquires sensitivity data as input information. The input information acquisition unit 101 transmits the acquired sensitivity data to the cluster identification unit 104 and the first input data creation unit 105 . Further, for example, the input information acquisition unit 101 acquires, as input information, information specifying a sample product touched by a panelist. The input information acquisition unit 101 transmits the information to the DB information acquisition unit 103 .

A sensor information acquisition unit (phenomenon data acquisition unit) 102 acquires sensor information transmitted from the sensor group 9 . In this embodiment, the sensor information acquisition unit 102 acquires phenomenon data as sensor information. Sensor information acquisition unit 102 transmits the acquired phenomenon data to cluster identification unit 104 and first input data creation unit 105 .

A DB information acquisition unit (physical property data acquisition unit) 103 acquires physical property data of a product touched by a panelist from the product information 121 in the storage unit 12 . Information specifying the sample product touched by the panelist may be input via the input unit 11 by the panelist or an administrator of the learning system 1000 or the like. When acquiring the information specifying the sample product from the input information acquiring unit 101, the DB information acquiring unit 103 refers to the product information 121 in the storage unit 12 and reads physical property data corresponding to the sample product. The DB information acquisition unit 103 transmits the acquired physical property data to the first input data creation unit 105 .

The cluster identification unit 104 identifies individual clusters based on the received phenomenon data and sensitivity data. The cluster identification unit 104 transmits information indicating the identified individuality clusters to the model construction unit 106 .

Note that the method of identifying individual clusters is not particularly limited. For example, when the cluster identifying unit 104 identifies a panelist's individuality cluster, the panelist's sensibility data (that is, the perception and impression questionnaire results for the sample product) and the other multiple panelists for the same sample product It is desirable to identify a personality cluster based on the degree of similarity with the sensitivity data. This makes it possible to identify individuality clusters more accurately. Also, the cluster identification unit 104 may receive physical property data from the DB information acquisition unit 103 . Then, individual clusters may be specified in consideration of received physical property data.

The cluster identifying unit 104 may also identify a perceptual cluster indicating a type of correlation between the tactile stimulus and the perception, and a sensitivity cluster indicating a type of correlation between the perception and the impression. A personality cluster may also consist of a combination of a perceptual cluster and an affective cluster. In other words, the cluster identification unit 104 may indicate a personality cluster by combining the perception cluster and the sensitivity cluster. This makes it possible to identify individuality clusters in more detail. Therefore, it is possible to construct a learning model capable of estimating individual differences in impressions in more detail.

The first input data creation unit 105 creates first input data composed of the received physical property data, phenomenon data, and sensibility data. First input data creation unit 105 transmits the first input data to model construction unit 106 .

The model building unit 106 builds a learning model by machine-learning the correlation between the first input data received from the first input data creating unit 105 and the individual clusters indicated by the information from the cluster specifying unit 104 .

In addition, below, the model construction part 106 demonstrates the example which produces|generates the learning model of a neural network (NN:Neural Network). However, the model construction unit 106 may construct a learning model by applying another algorithm, as long as it can construct a learning model capable of estimating individuality clusters. Note that when constructing the NN learning model, the model building unit 106 preferably constructs a multilayer NN learning model that can be expected to have high specific accuracy.

For example, the model construction unit 106 reads the learning model 122 from the storage unit 12 . The learning model 122 is data indicating an algorithm of a learning model such as NN. The model construction unit 106 reads out the NN algorithm and various weighting coefficients stored as the learning model 122 from the storage unit 12 . The model building unit 106 creates teacher data using the first input data created by the first input data creating unit 105 as input data and the personality clusters specified by the cluster specifying unit 104 as correct data. Let the NN perform supervised machine learning. This allows the model construction unit 106 to optimize the NN weighting coefficients and the like.

The model construction unit 106 causes the storage unit 12 to store the learning model after machine learning (that is, the learned model). That is, the learning model 122 in the storage unit 12 is updated to a more advanced learning model. Then, the model construction unit 106 updates the learning model 122 in the storage unit 12 with the learning model after optimization (that is, after learning).

(storage unit 12)
The storage unit 12 is a storage device that stores information necessary for operating the information processing device 1 . For example, the storage unit 12 stores product information 121 and learning models 122 . The product information 121 is information in which identification information of a product is associated with data indicating material properties of each product, that is, physical property data of the product. The storage unit 12 stores product information 121 for each sample product tested by the panelists. The learning model 122 is data indicating an algorithm of the learning model. The learning model 122 is updated by the model construction unit 106 .

<<Learning model building process>>
FIG. 3 is a diagram showing the flow of processing (learning model building processing) for building a learning model by the information processing apparatus 1 . The information processing device 1 constructs a learning model that learns the correlation between the first input data and the individuality clusters by executing the processing described below at arbitrary timing.

In S101, the DB information acquisition unit 103 refers to the product information 121 and acquires physical property data. DB information acquisition unit 103 transmits physical property data to cluster identification unit 104 and first input data creation unit 105 . In S<b>102 , the sensor information acquisition unit 102 acquires phenomenon data from the sensor group 9 . Sensor information acquisition section 102 transmits the phenomenon data to cluster identification section 104 and first input data creation section 105 . In S<b>103 , the input information acquisition unit 101 acquires sensitivity data via the input unit 11 . The input information acquisition unit 101 transmits the sensitivity data to the cluster identification unit 104 and the first input data creation unit 105 . Note that the processes from S101 to S103 may be executed in no particular order.

In S104, the first input data creation unit 105 creates first input data composed of the received physical property data, phenomenon data, and sensibility data. First input data creation unit 105 transmits the first input data to model construction unit 106 . In S105, the cluster identification unit 104 identifies the individual clusters of the panelists. Cluster identification unit 104 transmits information indicating the identified individual cluster to model construction unit 106 .

The model building unit 106 creates teacher data from the first input data and the personality clusters. In S106, the model building unit 106 builds a learning model by machine-learning the correlation between the first input data and the personality clusters. In S<b>107 , the model building unit 106 stores the built learning model in the storage unit 12 . That is, the model construction unit 106 updates the learning model 122 .

Note that processing for preparing teacher data necessary for machine learning (S101 to S105) and processing for actually executing machine learning using the prepared teacher data and updating the learning model 122 (S106 to S105). S107) may be executed at a different timing.

For example, the information processing apparatus 1 may create a plurality of pieces of teacher data by executing the processes from S101 to S105 a plurality of times. Note that the model construction unit 106 may temporarily or non-temporarily store the created teacher data in the storage unit 12 .

Then, the model construction unit 106 may execute the processes shown in S106 and S107 at a predetermined timing or at the stage when a predetermined number of teaching data have been prepared.

According to the above processing, individual differences in impressions were categorized based on the material properties of the sample product, the data on the tactile stimuli of the panelists, and the data indicating the impressions of the panelists on the sample product. A learning model capable of estimating individual clusters, which are clusters, can be constructed.

[Embodiment 2]
Other embodiments of the invention are described below. For convenience of description, members having the same functions as those of the members described in the above embodiments are denoted by the same reference numerals, and description thereof will not be repeated.

≪Outline of prediction system≫
The estimation system 1100 according to one aspect of the present invention includes material properties of the product, data related to tactile stimulation when the user touches the product, perception that the user feels when touching the product, and from the perception A system for estimating individuality clusters from data representing at least one of recollected impressions. The estimation system 1100 estimates a personality cluster using a learning model obtained by machine-learning the correlation between the first input data and the personality cluster (that is, a machine-learned learning model).

FIG. 4 is a diagram showing an overview of the estimation system 1100 according to this embodiment. Estimation system 1100 includes at least information processing device 2 and sensor group 9 . The information processing device 2 and the sensor group 9 are connected by wire or wirelessly.

(Information processing device 2)
The information processing device 2 is a device for estimating a user's personality cluster using a machine-learned learning model. The information processing device 2 can be realized by a personal computer (PC) or the like, like the information processing device 1 . The information processing apparatus 2 inputs the physical property data for estimation of the product, the phenomenon data for estimation, and the sensitivity data for estimation of the user into the learning model, thereby estimating individual clusters. These data are detailed later.

(Sensor group 9)
The sensor group 9 is a sensor group for measuring phenomenon data for estimation. The phenomenon data for estimation is data comprising at least part of the information of the phenomenon data. That is, the sensor group 9 is a sensor group capable of measuring at least part of the measurement information of the sensor group 9 according to the first embodiment. The type and number of sensors included in sensor group 9 may be determined based on the type of estimation phenomenon data required for individual cluster estimation in information processing device 2 .

In the estimation system 1100 shown in FIG. 4, a simple questionnaire is administered to the user instead of the detailed questionnaire shown in FIG. A simple questionnaire is a questionnaire from which information similar to or a part of the detailed questionnaire can be obtained. As with the detailed questionnaire, the contents of the simple questionnaire may also be directly input to the information processing device 2 via the input unit 11 by the user. Although there are no particular restrictions on the classification of impressions when touching a product, it is desirable that the simple and detailed questionnaires are unified in the classification of perceptions and impressions.

≪Main part composition≫
FIG. 5 is a block diagram showing the main configuration of the information processing device 2 included in the estimation system 1100. As shown in FIG. In addition, in the figure, the sensor group 9 is also illustrated together. Information processing device 2 includes at least control unit 10 , input unit 11 , storage unit 12 , and display unit 13 .

The input unit 11 and the storage unit 12 have functions similar to those of the input unit 11 and the storage unit 12 in the first embodiment. The input information acquisition unit 101, the sensor information acquisition unit 102, and the DB information acquisition unit 103 of the control unit 10 also have the same functions as the similar members in the first embodiment. Note that the learning model 122 stored in the storage unit 12 is a machine-learned learning model.

Further, in the present embodiment, the input information acquisition unit (estimation sensitivity data acquisition unit) 101 may acquire at least part of information of the sensitivity data as estimation sensitivity data. For example, the input information acquisition unit 101 may acquire the result of the above-described simple questionnaire input by the user or system administrator as the sensitivity data for estimation.

Further, in the present embodiment, the sensor information acquisition unit (estimation phenomenon data acquisition unit) 102 may acquire at least part of the phenomenon data as estimation phenomenon data. For example, the sensor information acquisition unit 102 may acquire sensor information from the sensor group 9 as phenomenon data for estimation.

Further, in the present embodiment, the DB information acquisition unit (estimation physical property data acquisition unit) 103 may acquire at least part of the physical property data as the estimation physical property data. For example, if the DB information acquiring unit 103 acquires the minimum values necessary for estimating individual clusters in the estimating unit 108, which will be described later, among the values of various material properties included in the product information 121, as physical property data for estimation: good.

The second input data creation unit 107 creates second input data using the estimation physical property data, the estimation phenomenon data, and the estimation sensitivity data.

The estimation unit 108 uses the learning model 122 stored in the storage unit 12 to estimate the user's personality cluster from the second input data. That is, the estimation unit 108 inputs the second input data to the learning model 122 and estimates the personality cluster to which the user belongs based on the algorithm of the learning model 122 . The estimation unit 108 transmits the estimation result to the display control unit 109 .

The display control unit 109 causes the display unit 13 to display information related to the individuality cluster estimated by the estimation unit 108 .

The display unit 13 displays images according to instructions from the display control unit 109 . A specific configuration of the display unit 13 is not particularly limited. Moreover, the display unit 13 may be a touch panel display formed integrally with the input unit 11 .

<<Individual cluster estimation process>>
FIG. 6 is a diagram showing a flow of processing (personality cluster estimation processing) for estimating a user's personality cluster by the information processing device 2 . The information processing device 2 executes the processing described below when the input information acquisition unit 101 receives a predetermined input operation on the input unit 11 . For example, the information processing device 2 performs the following processes in response to an input operation by the user or an administrator of the estimation system 1100 to input answers to the customer questionnaire results or an input operation to instruct execution of the personality cluster estimation process. to run.

In S201, the DB information acquisition unit 103 refers to the product information 121 to acquire physical property data for estimation. The DB information acquisition unit 103 transmits the physical property data for estimation to the second input data creation unit 107 . In S<b>202 , the sensor information acquisition unit 102 acquires phenomenon data for estimation from the sensor group 9 . The sensor information acquisition unit 102 transmits the phenomenon data for estimation to the second input data creation unit 107 . In S<b>203 , the input information acquisition unit 101 acquires estimation sensitivity data via the input unit 11 . The input information acquisition unit 101 transmits the sensitivity data for estimation to the second input data creation unit 107 . Note that the processes from S201 to S203 may be executed in no particular order.

In S204, the second input data creation unit 107 creates second input data composed of the received physical property data for estimation, phenomenon data for estimation, and sensitivity data for estimation. Second input data creating section 107 transmits the second input data to estimating section 108 .

In S205, the estimation unit 108 reads the learning model 122 from the storage unit 12 and inputs the second input data to the learning model. Thereby, a personality cluster is estimated from the second input data based on the algorithm, coefficients, etc. defined in the learning model. The estimation unit 108 transmits the estimation result to the display control unit 109 .

In S206, the display control unit 109 causes the display unit 13 to display the estimation result, that is, information indicating the personality cluster to which the user belongs. Note that the processing of S<b>206 is not essential in the information processing device 2 .

According to the above processing, the user's individuality cluster is estimated based on the material physical properties of the product, the data on the user's tactile stimulus, and the data indicating the user's perception and impression of the product. be able to. Therefore, it is possible to predict the impression of the user when the user touches the product, even if the product is not touched by the user.

[Embodiment 3]
The learning system 1000 according to the first embodiment and the estimation system 1100 according to the second embodiment may be integrated. FIG. 7 is a block diagram showing the information processing device 3 according to this embodiment. The input information acquisition unit 101, the sensor information acquisition unit 102, and the DB information acquisition unit 103 have the functions described in the first and second embodiments. Other functional blocks of the information processing device 3 have functions as described in the first or second embodiment. Moreover, the sensor group 9 functions as both the sensor group 9 according to the first embodiment and the sensor group 9 according to the second embodiment. According to the configuration described above, the information processing device 3 has the same effect as the information processing devices 1 and 2 .

[Embodiment 4]
An information processing apparatus according to an aspect of the present invention provides a value of physical properties of a material (physical property value) or a value of physical action between a person and a product (effect value) when a person touches a product, and An impression map may be created to show the relationship between the impressions of the product and the relationship. Then, the information processing apparatus according to one aspect of the present invention may create a product impression map by mapping the coordinate position of each product in the impression map. Furthermore, the information processing apparatus according to an aspect of the present invention may specify, from the product impression map, an impression area designated by the user, that is, a product showing an impression desired by the user, and present the product to the user.

FIG. 8 is a diagram showing an overview of the processing of the information processing device 4 according to this embodiment. The information processing device 4 receives an input operation for designating a user's desired impression. For example, as shown in the figure, the user is asked to give a desired impression of the product in the form of a questionnaire or the like, and the user or the administrator of the information processing device 4 inputs the contents of the answer. Thereby, the information processing device 4 can specify the impression desired by the user.

The information processing device 4 identifies a product that can give the user that impression. Although the details will be described later, the information processing device 4 creates an impression map showing the correlation between the physical property values and action values of each product and the impression that the user is supposed to have, and displays the impression map of each product. By plotting physical property values and effect values, it is specified what kind of impression each product can have on the user. Then, the information processing device 4 recommends to the user a product that is estimated to give the user a desired impression. For example, in FIG. 8, the information processing device 4 recommends "product CCC" for the impression of "luxury" desired by the user.

≪Main part composition≫
FIG. 9 is a block diagram showing the main configuration of the information processing device 4. As shown in FIG. The information processing device 4 includes at least a control section 40 , an input section 41 , a storage section 42 and a display section 43 .

(Input unit 41)
The input section 41 has the same configuration and functions as the input section 11 described in the first to third embodiments. Upon receiving an input operation, the input unit 41 notifies the input information acquisition unit 401 of the control unit 40 of the contents of the input operation. The input unit 41 according to the present embodiment receives an input operation for inputting impression information.

(control unit 40)
The control unit 40 comprehensively controls each unit included in the information processing device 4 . The control unit 40 includes an input information acquisition unit 401 , an impression map creation unit 402 , a product impression map creation unit 403 , a product identification unit 404 and a display control unit 405 .

The input information acquisition unit 401 acquires input information indicating the content of the input operation received by the input unit 41 . In this embodiment, the input information acquisition unit 401 acquires designation of an impression area (described later) as input information. The input information acquisition unit 401 transmits the acquired impression information to the impression map creation unit 402 and the product identification unit 404 .

The impression map creation unit 402 creates an impression map based on the designation of the impression information received from the input information acquisition unit 401 and the impression area information 421 stored in the storage unit 42 . Details of the impression map will be described later. Impression map creation unit 402 transmits the created impression map to product impression map creation unit 403 .

Product impression map creation section 403 creates a product impression map based on the impression map received from impression map creation section 402 . Details of the product impression map will be described later. The product impression map creation unit 403 transmits the created product impression map to the product identification unit 404 .

The product identification unit 404 identifies the product plotted in the impression area designated by the input operation received by the input unit 41 in the product impression map created by the product impression map creation unit 403 . Hereinafter, the product specified by the product specifying unit 404 will be referred to as a recommended product. The product identification unit 404 reads information related to the recommended product from the product information 422 and transmits it to the display control unit 405 .

The display control unit (product information presentation unit) 405 causes the display unit 43 to display the information related to the recommended product received from the product identification unit 404 .

The display unit 43 displays information related to recommended products according to instructions from the display control unit 405 . A specific configuration of the display unit 43 is not particularly limited. Moreover, the display unit 43 may be a touch panel display formed integrally with the input unit 41 .

(storage unit 42)
The storage unit 42 is a storage device that stores information necessary for operating the information processing device 4 . For example, the storage unit 42 stores impression area information 421 and product information 422 .

The impression area information 421 is information that defines the range of physical property values or effect values indicated by each impression area. The impression area, physical property value, and effect value will be described in detail later.

The product information 422 is information in which the identification information of the product is associated with the physical property value and action value of each product. In addition, the physical property value may be the same as the physical property data in the product information 121 . The storage unit 42 stores product information 422 for each product.

(impression map and product impression map)
Here, the impression map and the product impression map will be explained in detail using FIG. FIG. 10 is a diagram showing an example of an impression map and a product impression map.

FIG. 10(a) shows an example of an impression map. An impression map is a type of graph represented by a multi-dimensional space, ie two or more axes. Each axis of the impression map represents different types of physical property values and effect values. Here, the physical property value is a value related to the physical property of the material of the object. Also, the action value is a value related to a physical action that occurs between the object and a human finger. In the example of (a) of FIG. 10, the impression map includes a physical property value axis of "roughness", a physical property value axis of "hardness and softness", and an action value axis of "coefficient of friction".

Impression regions are also mapped onto the impression map. The impression area is an area indicating the type of impression that humans have with respect to the physical property value or the action value indicated by each coordinate value in the multidimensional space. If the "impression type" indicated by the impression area is the same as the impression classification of the detailed questionnaire shown in the first embodiment and the impression classification of the simple questionnaire shown in the second embodiment, the classification method is It is not particularly limited. Also, the ranges of physical property values and effect values indicated by the respective impression regions may overlap.

The impression map creating unit 402 creates an impression map by mapping at least the impression area specified via the input unit 41 when creating the impression map. In the example of FIG. 10(a), impression areas α to γ are mapped in a multidimensional space. It is presumed that an object having coordinate values included in each impression area can give the user an impression indicated by the impression area.

FIG. 10(b) shows an example of the product impression map. The product impression map is a graph obtained by plotting coordinate values corresponding to the plurality of axes of each product on the impression map. Upon receiving the impression map from the impression map creating unit 402, the product impression map creating unit 403 reads the product information 422 and plots the physical property values and effect values of each product included in the product information 422 on the impression map. , to create a product impression map.

In the example of FIG. 10(b), the coordinate values of products AAA, BBB, CCC, and DDD are plotted. Here, the coordinate values of the product CCC are included in the impression area of "luxury". Therefore, it can be said that the product CCC is a product presumed to give the user a “luxury feeling” in this product impression map. Note that the product impression map creating unit 403 may plot only the coordinate values of some of the products included in the product information 422 . For example, the coordinate values of discontinued products, seasonal products, etc. may not be plotted on the product impression map.

≪Recommendation processing≫
FIG. 11 is a diagram showing a flow of processing (recommendation processing) in which the information processing apparatus 4 recommends to the user a product that can give the user a desired impression. The information processing device 4 executes the processing described below when the input information acquisition unit 401 receives a predetermined input operation on the input unit 41 . For example, the information processing device 4 executes the following processes in response to an input operation for designating an impression area (that is, an input operation for designating an impression desired by the user) by the user or an administrator of the information processing device 4. do.

In S401, the input information acquisition unit 401 receives an input operation for designating an impression area. Input information acquisition unit 401 transmits the designation to impression map creation unit 402 and product identification unit 404 .

In S402, the impression map creating unit 402 creates an impression map including the designated impression area. Impression map creation unit 402 transmits the created impression map to product impression map creation unit 403 . Note that the impression map creating unit 402 may temporarily or non-temporarily store the created impression map in the storage unit 42 . In S403, the product impression map creation unit 403 creates a product impression map by referring to the product information 422 and plotting the coordinate values of each product on the impression map. The product impression map creation unit 403 transmits the created product impression map to the product identification unit 404 . Note that the product impression map creation unit 403 may temporarily or non-temporarily store the created product impression map in the storage unit 42 .

In S404, the product identifying unit 404 identifies a product whose coordinate values are included in the specified impression area as a recommended product. In S405, the product identification unit 404 refers to the product information 422 of the storage unit 42 and reads out information related to recommended products. The product identification unit 404 transmits information on recommended products to the display control unit 405 . In S406, the display control unit 405 causes the display unit 43 to display information related to the recommended product.

According to the above processing, the information processing device 4 can recommend a product included in the impression area specified by the user, that is, a product having a physical property value or an effect value that can give the impression specified by the user. can be done.

Note that, when a plurality of recommended products are specified in S404, the product specifying unit 404 transmits to the display control unit 405 information about the recommended product whose coordinate values are plotted at a position closer to the center of the specified impression area. good too. Then, the display control unit 405 may preferentially present information about the recommended product whose coordinate values are plotted at a position closer to the center of the impression area. This makes it possible to recommend a product that is more likely to give the user the specified impression. Therefore, it is possible to recommend a more appropriate product to the user.

[Embodiment 5]
An information processing apparatus according to an aspect of the present invention provides a value of physical properties of a material (physical property value) or a value of physical action between a person and a product (effect value) when a person touches a product, and An impression map may be created to show the relationship between the impressions of the product and the relationship. Then, the information processing apparatus according to one aspect of the present invention may create a product impression map by mapping the coordinate position of each product in the impression map. Furthermore, the information processing apparatus according to an aspect of the present invention may specify, from the product impression map, an impression area designated by the user, that is, a product showing an impression desired by the user, and present the product to the user.

≪Main part composition≫
FIG. 12 is a block diagram showing the main configuration of the information processing device 5 according to this embodiment. The information processing device 5 includes at least a control section 50 , an input section 41 , a storage section 42 and a display section 43 . The input unit 41, the storage unit 42, and the display unit 43 have the same functions as the members with the same numbers in the fourth embodiment.

(control unit 50)
The control unit 50 comprehensively controls each unit included in the information processing device 5 . The control unit 50 includes an input information acquisition unit 401 , an impression map creation unit 402 , a range identification unit 503 and a display control unit 504 .

The input information acquisition unit 401 and the impression map creation unit 402 have the same functions as the members with the same numbers in the fourth embodiment. However, the impression map creation unit 402 transmits the created impression map to the range identification unit 503 .

The range specifying unit 503 specifies at least one of the range of physical property values and the range of action values indicated by the impression area specified by the operation content acquired by the input information acquiring unit 401 in the impression map. do. The range specifying unit 503 transmits the specified range of various values to the display control unit 504 .

The display control unit (range presentation unit) 504 causes the display unit 43 to display the range of various values received from the range identification unit 503 .

The display unit 43 displays information related to recommended products according to instructions from the display control unit 405 . A specific configuration of the display unit 43 is not particularly limited. Moreover, the display unit 43 may be a touch panel display formed integrally with the input unit 41 .

≪Range identification process≫
FIG. 13 is a diagram showing a flow of processing (range specifying processing) for specifying the range of at least one of the physical property value and the effect value of the impression area desired by the user by the information processing device 5 . The information processing device 5 executes the processing described below when the input information acquisition unit 401 receives a predetermined input operation on the input unit 41 . For example, the information processing device 5 executes the following processes in response to an input operation for designating an impression area (that is, an input operation for designating an impression desired by the user) by the user or an administrator of the information processing device 5. do.

In S501, the input information acquisition unit 401 receives an input operation for designating an impression area. The input information acquisition unit 401 transmits the designation to the impression map creation unit 402 . In S502, the impression map creating unit 402 creates an impression map including the designated impression area. The impression map creation unit 402 transmits the created impression map to the range identification unit 503 . Note that the impression map creating unit 402 may temporarily or non-temporarily store the created impression map in the storage unit 42 .

In S503, the range identifying unit 503 identifies the range of various values indicated by the designated impression area. The range identification unit 503 transmits the identified value range to the display control unit 504 . In S<b>504 , the display control unit 504 causes the display unit 43 to display the range of various values received from the range specifying unit 503 .

According to the above processing, the information processing device 5 can specify and present a range of physical property values or effect values that can give the user a desired impression. That is, it is possible to specify the properties of the product according to the user's preference.

[Embodiment 6]
The learning system 1000 according to the first embodiment, the estimation system 1100 according to the second embodiment, and the information processing device 4 according to the fourth embodiment may be integrated.

FIG. 14 is a block diagram showing the main configuration of the information processing device 6 according to this embodiment. The information processing device 6 is a device having the functions of both the information processing device 1 and the information processing device 4 . The information processing device 6 includes a control section 60 , an input section 61 and a storage section 62 . The input section 61 has the functions of both the input section 11 and the input section 41 . The storage unit 62 has the functions of both the storage unit 12 and the storage unit 42 . The display section 63 has the functions of both the display section 13 and the display section 43 . Each functional block inside the control unit 60 has the same function as the functional blocks denoted by the same reference numerals in the information processing device 3 or 4 . According to the above configuration, the information processing device 6 has the same effect as the information processing devices 1-4.

In the information processing device 6, the impression map creation unit 402 may create an impression map for each personality cluster. Alternatively, the impression map creation unit 402 may create an impression map corresponding to the personality clusters estimated by the estimation unit 108 . Then, the product impression map creation unit 403 may create a product impression map using an impression map corresponding to the individuality cluster estimated by the estimation unit 108 . As a result, it is possible to create an impression map and a product impression map in consideration of individual differences in impression when touching an object.

Then, the product identification unit 404 can identify the recommended product based on the product impression map that considers the individual differences. Therefore, a more suitable product can be recommended to the user.

Further, when at least one of the axes of the impression map is an axis indicating an effect value, the product impression map creation unit (product effect value calculation unit) 403 calculates the effect value of each product based on the phenomenon data for estimation. good too. Then, the product impression map creating unit 403 may create a product impression map by plotting the coordinate values including the calculated action value of each product.

For example, assume that one of the axes of the impression map is a value indicating the coefficient of friction applied to the product, and the sensor information acquisition unit 102 acquires information indicating the size of the user's finger as estimation phenomenon data. In this case, the product impression map creation unit 403 may correct the pressure value of each product read from the product information 422 according to the size of the user's finger and plot it on the impression map.

As a result, it is possible to create a product impression map and present a recommended product, taking into account individual differences such as how a user touches a product. Therefore, a more suitable product can be recommended to the user.

[Embodiment 7]
Further, the information processing device 4 according to the fourth embodiment and the information processing device 5 according to the fifth embodiment may be integrated. FIG. 15 is a block diagram showing the main configuration of the information processing device 7 according to this embodiment. The information processing device 7 is a device having the functions of both the information processing device 4 and the information processing device 5 . The information processing device 7 includes a control section 70 , an input section 71 and a storage section 72 . The input section 71 has the functions of both the input section 41 and the input section 51 . The storage unit 72 has the functions of both the storage unit 42 and the storage unit 52 . The display section 73 has the functions of both the display section 43 and the display section 53 . Each functional block inside the control unit 70 has the same function as the functional block with the same reference numeral in the information processing device 4 or 5 . According to the above configuration, the information processing device 7 has the same effect as the information processing devices 1, 2, and 4. FIG.

[Embodiment 8]
Further, the information processing device 1 according to the first embodiment and the information processing device 5 according to the fifth embodiment may be integrated. In this case, the information processing apparatus according to this embodiment is realized as an apparatus having the functions of both the information processing apparatuses 1 and 5. FIG. According to the information processing apparatus according to the present embodiment, the information processing apparatus 8 has the same effect as the information processing apparatuses 1 and 5 according to the above configuration.

[Modification]
Note that Embodiments 3 to 5 may be combined for implementation. In this case, the impression map creation section 402 may include an importance determination section that determines the importance of each of the plurality of impression maps created for each personality cluster. Then, the impression map creation unit 402 may integrate a plurality of impression maps created for each individuality cluster at a rate according to the importance.

Although the integration method is not particularly limited, the impression map creation unit 402 may integrate a plurality of impression maps by, for example, taking a weighted average of each impression map. Then, the range specifying unit 503 may specify at least one of the range of physical property values and the range of effect values indicated by the specified impression area in the integrated impression map.

Thus, impression maps can be integrated for each individual cluster, that is, after weighting the type of user's preference. The integrated impression map can then be used to identify ranges of product physical property values or effect values for obtaining the user's desired impression.

[Example of realization by software]
Each control block of the information processing apparatuses 1 to 7 may be implemented by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be implemented by software.

In the latter case, the information processing apparatuses 1 to 7 are provided with computers that execute instructions of programs, which are software for realizing each function. This computer includes, for example, one or more processors, and a computer-readable recording medium storing the program. In the computer, the processor reads the program from the recording medium and executes it, thereby achieving the object of the present invention. As the processor, for example, a CPU (Central Processing Unit) can be used. As the recording medium, a "non-temporary tangible medium" such as a ROM (Read Only Memory), a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, a RAM (Random Access Memory) for expanding the program may be further provided. Also, the program may be supplied to the computer via any transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. Note that one aspect of the present invention can also be implemented in the form of a data signal embedded in a carrier wave in which the program is embodied by electronic transmission.

The present invention is not limited to the above-described embodiments, but can be modified in various ways within the scope of the claims, and can be obtained by appropriately combining technical means disclosed in different embodiments. is also included in the technical scope of the present invention.

1, 2, 3, 4, 5, 6, 7 information processing device 9 sensor group 10, 20, 30, 40, 50, 60, 70 control section 11, 41, 51, 61, 71 input section 12, 42, 62 Storage unit 13, 43, 53, 63, 73 Display unit 101, 401 Input information acquisition unit 102 Sensor information acquisition unit 103 DB information acquisition unit 104 Cluster identification unit 105 First input data creation unit 106 Model construction unit 107 Second input data Creation unit 108 Estimation unit 109, 405, 504 Display control unit 402 Impression map creation unit 403 Product impression map creation unit 404 Product identification unit 503 Range identification unit

Claims (11)

a physical property data acquisition unit for acquiring physical property data indicating material properties of a product;
a phenomenon data acquisition unit that acquires phenomenon data that is data related to tactile stimulation when a person touches the product;
a sensory data acquisition unit that acquires sensory data indicating the perception that the person feels when touching the product and the impression that is recollected from the sensory perception;
a cluster identification unit that identifies a personality cluster indicating a type of correlation between the tactile stimulus and the impression based on the phenomenon data and the sensibility data;
and a model building unit that builds a learning model by machine-learning a correlation between first input data composed of the physical property data, the phenomenon data, and the sensitivity data, and the individual cluster. information processing device. The cluster identification unit
identifying a perceptual cluster indicating a type of correlation between the tactile stimulus and the perception, and a sensitivity cluster indicating a type of correlation between the perception and the impression;
2. The information processing apparatus according to claim 1, wherein said personality cluster is a combination of said perception cluster and said sensitivity cluster. 3. The information processing apparatus according to claim 1, wherein said cluster identification unit identifies said individual cluster based on similarities of said phenomenon data and said sensitivity data of a plurality of persons with respect to the same product. an estimation physical property data acquisition unit that acquires estimation physical property data;
an estimation phenomenon data acquisition unit that acquires estimation phenomenon data of a certain user;
an estimation sensitivity data acquisition unit that acquires the estimation sensitivity data of the certain user;
a second input data creation unit that creates second input data using the physical property data for estimation, the phenomenon data for estimation, and the sensitivity data for estimation;
Physical property data, which is data indicating the material properties of the product; phenomenon data, which is data related to tactile stimulation when a human touches the product; perception that a human feels when the product is touched; Using a learning model obtained by machine-learning the correlation between the first input data created using the sensitivity data indicating the impression to be recalled and the personality cluster indicating the type of correlation between the tactile stimulus and the impression. and an estimating unit that estimates the personality cluster of the user from the second input data,
The physical property data for estimation consists of at least part of information of the physical property data,
the phenomenon data for estimation consists of at least part of the information of the phenomenon data;
The information processing apparatus, wherein the estimating kansei data comprises at least part of the kansei data. 5. The information processing apparatus according to claim 4, wherein said phenomenon data and said estimation phenomenon data include data relating to physical properties of said user's fingers. 6. Information according to claim 4, wherein said phenomenon data and said phenomenon data for estimation include data relating to a physical action occurring between said product and said user's finger touching said product. processing equipment. An axis indicating a physical property value related to material properties of an object, or an axis indicating an action value, which is a value related to physical action occurring between the object and a human finger, wherein the physical property value or the An impression map obtained by mapping, in a multi-dimensional space composed of a plurality of axes representing action values, an impression area indicating the type of impression that a person has with respect to the physical property value indicated by each coordinate value in the multi-dimensional space or the action value, an impression map creating unit that creates for each personality cluster;
a product impression map creating unit for creating a product impression map by plotting coordinate values corresponding to the plurality of axes of each product on the impression map corresponding to the individuality cluster of the certain user estimated by the estimating unit;
an input information acquisition unit that acquires information indicating an input operation that specifies one of the impression regions;
a product identifying unit that identifies, as a recommended product, a product whose coordinate values are included in the impression area designated by the input operation on the product impression map;
7. The information processing apparatus according to any one of claims 4 to 6, further comprising a product information presentation unit for presenting information related to said recommended product. at least one of the plurality of axes of the impression map is an axis indicating the effect value;
The information processing device is
a product effect value calculation unit that calculates the effect value of each product based on the estimation phenomenon data acquired by the estimation phenomenon data acquisition unit;
8. The information processing apparatus according to claim 7, wherein said product impression map creation unit plots said coordinate values including said effect values of said respective products calculated by said product effect value calculation unit. the product identification unit identifies a plurality of the recommended products;
The product information presentation unit preferentially presents the recommended product plotted at a position closer to the center of the designated impression area on the product impression map among the information related to each of the plurality of recommended products. 9. An information processing apparatus according to claim 7 or 8. A control method for an information processing device,
a physical property data acquiring step of acquiring physical property data indicating material physical properties of the product;
a phenomenon data acquisition step of acquiring phenomenon data, which is data relating to tactile stimulation when a person touches the product;
a sensory data acquisition step of acquiring sensory data representing the perception that the person feels when touching the product and the impression evoked from the sensory perception;
a personality cluster identification step of identifying a personality cluster indicating a type of correlation between the tactile stimulus and the impression based on the phenomenon data and the sensibility data;
and a model construction step of constructing a learning model by machine-learning a correlation between first input data composed of the physical property data, the phenomenon data, and the sensitivity data, and the personality cluster. control method. A control method for an information processing device,
an estimation physical property data acquiring step of acquiring physical property data for estimation;
an estimation phenomenon data obtaining step of obtaining estimation phenomenon data of a certain user;
an estimation sensitivity data acquisition step of acquiring the estimation sensitivity data of the user;
a second input data creating step of creating second input data using the physical property data for estimation, the phenomenon data for estimation, and the sensitivity data for estimation;
Physical property data, which is data indicating the material properties of the product; phenomenon data, which is data related to tactile stimulation when a human touches the product; perception that a human feels when the product is touched; Using a learning model obtained by machine-learning the correlation between the first input data created using the sensitivity data indicating the impression to be recalled and the personality cluster indicating the type of correlation between the tactile stimulus and the impression. and an estimation step of estimating the personality cluster of the certain user from the second input data,
The physical property data for estimation consists of at least part of information of the physical property data,
the phenomenon data for estimation consists of at least part of the information of the phenomenon data;
The control method, wherein the estimated kansei data comprises at least part of information of the kansei data.

Images