Impression evaluation device, impression evaluation method, and impression evaluation program

Abstract

According to the present invention, related structure data of the degree of satisfaction and psychological value with respect to an evaluation object is acquired using analysis by causal inference on questionnaire data, and a related structure diagram of the degree of satisfaction and psychological value is displayed on the basis of the related structure data.

Description

Impression evaluation device, impression evaluation method, and impression evaluation program

[0001] The present invention relates to an impression evaluation device, an impression evaluation method, and an impression evaluation program.

[0002] Patent Document 1 discloses a technology for more appropriately evaluating the impact on the impression of ingredients contained in food that are released in the environment in which the food is consumed, taking into account the actual consumption environment.

[0003] International Publication No. 2021 / 246489

[0004] However, in conventional inventions, the impact on the impression of food is evaluated by analyzing the components released from the food, and there was a problem in that the psychological value of a product such as food could not be evaluated from the results of a questionnaire about the product.

[0005] The present invention has been made in consideration of the above-mentioned problems, and aims to provide an impression evaluation device, an impression evaluation method, and an impression evaluation program that can extract psychological values ​​that lead to satisfaction with an evaluation target, such as purchase intention or use intention, based on the results of a questionnaire about the evaluation target, such as a product.

[0006] In order to solve the above-mentioned problems and achieve the object, an impression evaluation device is provided which comprises a memory unit and a control unit, wherein the memory unit comprises an evaluation object storage means for storing questionnaire data which sets the satisfaction level of the evaluation object and the selection results for each psychological value of the evaluation object, and the control unit comprises a causal inference analysis means for acquiring relational structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference, and a result output means for displaying a relational structure diagram between the satisfaction level and the psychological value based on the relational structure data.

[0007] In addition, the impression evaluation device of the present invention is an impression evaluation device comprising a memory unit and a control unit, wherein the memory unit comprises an evaluation object storage means for storing questionnaire data in which selection results for each psychological value of each evaluation object are set, and the control unit comprises a dimension reduction means for acquiring dimension reduction data in which relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized by reducing the dimension of the questionnaire data, and a result output means for displaying a dimension reduction output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduction data.

[0008] In addition, in the impression evaluation device of the present invention, the control unit further comprises a sensitivity analysis means for acquiring sensitivity data that sets a sensitivity indicating the contribution of each psychological value to the satisfaction level of the evaluation object by sensitivity analysis of the related structure data, and a selection rate acquisition means for acquiring a selection rate of each psychological value based on the questionnaire data, and the result output means further displays sensitivity analysis output data for the evaluation object based on the sensitivity data and the selection rate.

[0009] In addition, in the impression evaluation device of the present invention, the control unit is characterized in that it further includes a survey registration means that displays the satisfaction level of the evaluation object and each of the psychological values ​​of the evaluation object in a selectable manner, and when the satisfaction level and each of the psychological values ​​are selected, acquires the selection result and registers the survey data setting the selection result in the evaluation object storage means.

[0010] Furthermore, in the impression evaluation device according to the present invention, the questionnaire registration means acquires free descriptions using a questioning method such as a word association method, a sentence completion method, a third-person method, or a video presentation method, and acquires a term list through analysis including text mining, and based on the term list, displays the satisfaction level of the evaluation target and each of the psychological values ​​of the evaluation target in a selectable manner, and when the satisfaction level and each of the psychological values ​​are selected, acquires the selection result and registers the questionnaire data in which the selection result is set in the evaluation target storage means.

[0011] In addition, in the impression evaluation device according to the present invention, the control unit displays the impression of the evaluation object so that it can be input as text, and when text is input, acquires the text data, objectively and quantitatively analyzes the text data by text mining to extract the psychological value derived from the text data, and registers the questionnaire data in which the selection result corresponding to the extracted result of the psychological value is set in the evaluation object storage means.

[0012] In the impression evaluation device according to the present invention, the text mining includes morphological analysis and / or syntactic analysis.

[0013] In the impression evaluation device according to the present invention, the causal inference is a probabilistic inference.

[0014] In the impression evaluation device according to the present invention, the probabilistic inference is a Bayesian network.

[0015] In addition, in the impression evaluation device of the present invention, the evaluation object is food, clothing, daily necessities, home appliances, cars, real estate, health foods, supplements, or an application such as a product, brand, service, exercise, sleep, health care, health, or cooking.

[0016] In addition, in the impression evaluation device according to the present invention, the psychological value is the degree of satisfaction with the product, the perceived health benefits, or the enjoyment or ease of cooking.

[0017] In addition, in the impression evaluation device of the present invention, the control unit further includes a cluster analysis means that classifies the evaluation object and the psychological value into a plurality of clusters by hierarchical cluster analysis of the position coordinates based on the dimension reduction data and acquires cluster analysis data in which the clusters are set, and the result output means displays the dimension reduction output diagram in which the boundaries of the clusters are identifiable based on the dimension reduction data and the cluster analysis data.

[0018] In the impression evaluation device according to the present invention, the result output means further displays hierarchical cluster analysis output data indicating a hierarchical structure of each of the clusters based on the cluster analysis data.

[0019] In addition, in the impression evaluation device of the present invention, the control unit further includes a significance testing means for acquiring the selection rate of the psychological value for each evaluation object based on the questionnaire data and acquiring a significance probability for each selection rate by a significance test for the selection rate, and the dimension reduction means identifies the psychological value for the selection rate whose significance probability is smaller than a predetermined significance level, and acquires the dimension reduced data by the dimension reduction, in which the relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized.

[0020] In addition, in the impression evaluation device of the present invention, the control unit is characterized in that it further includes a questionnaire registration means that displays each of the psychological values ​​of the evaluation object in a selectable manner, and when each of the psychological values ​​is selected, acquires the selection result and registers the questionnaire data in which the selection result is set in the evaluation object storage means.

[0021] In addition, in the impression evaluation device of the present invention, the questionnaire registration means obtains free descriptions using a questioning method such as word association, sentence completion, third-person method, or video presentation method, and obtains a term list by analysis including text mining, displays each of the psychological values ​​of the evaluation target in a selectable manner based on the term list, and when each of the psychological values ​​is selected, obtains the selection result and registers the questionnaire data with the selection result set in the evaluation target storage means.

[0022] In the impression evaluation device according to the present invention, the video presentation method is a cooking video presentation method, a concept video presentation method, or an image video presentation method.

[0023] In addition, in the impression evaluation device of the present invention, the satisfaction level is a purchase intention for the evaluation object, and the psychological value is the value of the evaluation object for consumers and the characteristics of the evaluation object.

[0024] In addition, in the impression evaluation device of the present invention, the satisfaction level is the intention to continue using the evaluation object, the intention to purchase, the favorability rating, or the perceived effectiveness of the evaluation object, and the psychological value is the value of the evaluation object to the consumer at each stage from before the consumer uses the evaluation object to after the consumer uses it.

[0025] In addition, in the impression evaluation device of the present invention, the stages include at least one of a recognition stage in which the trigger for using the evaluation object is recognized, an imagination stage in which the user imagines what it would be like to use the evaluation object, a planning stage in which the user plans to use the evaluation object, an implementation stage in which the user uses the evaluation object, an impression stage in which the user obtains impressions of using the evaluation object, and a realization stage in which the user realizes the effects of the evaluation object.

[0026] Furthermore, the impression evaluation method according to the present invention is an impression evaluation method to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit has evaluation object storage means for storing questionnaire data setting the satisfaction level of the evaluation object and the selection results for each psychological value of the evaluation object, and is characterized by including a causal inference analysis step executed by the control unit for acquiring correlation structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference, and a result output step for displaying a correlation structure diagram between the satisfaction level and the psychological value based on the correlation structure data.

[0027] Furthermore, the impression evaluation method according to the present invention is an impression evaluation method to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises an evaluation object storage means for storing questionnaire data in which selection results for each psychological value of each evaluation object are set, and the method includes a dimension reduction step executed by the control unit to acquire dimension reduced data in which relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized by dimensional reduction of the questionnaire data, and a result output step to display a dimension reduced output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduced data.

[0028] Furthermore, the impression evaluation program of the present invention is an impression evaluation program to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises an evaluation object storage means for storing questionnaire data that sets the satisfaction level of the evaluation object and the selection results for each psychological value of the evaluation object, and the control unit executes a causal inference analysis step of acquiring correlation structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference, and a result output step of displaying a correlation structure diagram between the satisfaction level and the psychological value based on the correlation structure data.

[0029] In addition, the impression evaluation program of the present invention is an impression evaluation program to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit has an evaluation object storage means for storing questionnaire data that sets selection results for each psychological value of each evaluation object, and the control unit executes a dimension reduction step of acquiring dimension reduced data that sets relative position coordinates of the evaluation object and the psychological value by reducing the dimension of the questionnaire data so that the correlation between the evaluation object and the psychological value is maximized, and a result output step of displaying a dimension reduced output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduced data.

[0030] The present invention has the advantage of extracting psychological values ​​that lead to product satisfaction and utilizing them in concept design and communication strategy hypotheses. Furthermore, the present invention has the advantage of utilizing the extracted psychological values ​​in forming hypotheses about preferred quality when grasping the current situation before setting quality targets. Furthermore, the present invention has the advantage of identifying psychological values ​​that directly or indirectly affect product satisfaction. Furthermore, the present invention has the advantage of identifying the impressions (values) that motivate consumers to purchase a product, brand, or service by calculating an index of how likely a consumer is to purchase the product when given a certain impression. Furthermore, the present invention has the advantage of extracting the psychological values ​​of products, brands, and services using terms used by consumers. Furthermore, the present invention has the advantage of clarifying the psychological values ​​that consumers hold toward products, brands, and services, enabling the formation of product, brand, and service concept hypotheses based on grasping the current situation. Furthermore, the present invention has the advantage of confirming that there are statistically significant differences in psychological values ​​between products, brands, and services. Furthermore, the present invention has the advantage of mapping products, brands, services, and psychological values ​​based on psychological values. The present invention also has the effect of enabling classification of products, brands, services, and psychological values ​​based on the actual feelings of consumers.The present invention also has the effect of enabling clarification and classification of the psychological values ​​of evaluation targets from the consumer's perspective based on the results of a questionnaire survey on evaluation targets such as products.

[0031] FIG. 1 is a diagram showing an example of psychological value term extraction processing in this embodiment. FIG. 2 is a diagram showing an example of input data in this embodiment. FIG. 3 is a diagram showing an example of output data in this embodiment. FIG. 4 is a block diagram showing an example of the configuration of an impression assessment device in this embodiment. FIG. 5 is a flowchart showing an example of impression assessment processing in this embodiment. FIG. 6 is a diagram showing an example of survey raw data in this embodiment. FIG. 7 is a diagram showing an example of psychological value classification in this embodiment. FIG. 8 is a diagram showing an example of survey raw data in this embodiment. FIG. 9 is a diagram showing an example of a relationship structure diagram between usage intention and psychological value using Bayesian network analysis in this embodiment. FIG. 10 is a diagram showing an example of sensitivity analysis output in this embodiment. FIG. 11 is a diagram showing an example of input in this embodiment. FIG. 12 is a diagram showing an example of survey raw data in this embodiment. FIG. 13 is a diagram showing an example of summary table data in this embodiment. FIG. 14 is a diagram showing an example of analysis output of the Cochran Q test in this embodiment. FIG. 15 is a diagram showing an example of dimensionality reduction output in this embodiment. FIG. 16 is a diagram showing an example of cluster analysis output in this embodiment. FIG. 17 is a diagram showing an example of dimensionality reduction output in this embodiment. FIG. 18 is a diagram showing an example of a survey method in this embodiment. FIG. 19 is a diagram showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment. FIG. 20 is a diagram showing an example of a research method in this embodiment. FIG. 21 is a diagram showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment. FIG. 22 is a diagram showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment. FIG. 23 is a diagram showing an example of a research method in this embodiment. FIG. 24 is a diagram showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment. FIG. 25 is a diagram showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment.

[0032] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to this embodiment.

[0033] [1. Overview] First, an overview of the present invention will be described with reference to Fig. 1 to Fig. 3. Fig. 1 is a diagram showing an example of psychological value term extraction processing in this embodiment. Fig. 2 is a diagram showing an example of input data in this embodiment. Fig. 3 is a diagram showing an example of output data in this embodiment.

[0034] First, as shown in FIG. 1, this embodiment provides a system for extracting terms that represent psychological value perceived by consumers through text analysis of a free-form online questionnaire targeted at consumers.

[0035] In this embodiment, this system can be used when you want to extract the brand, product image, ideal quality, and issues that consumers have, when you want to extract the characteristics of the psychological value of each product in a variety of products, when you want to set evaluation terms for psychological value, when you want to extract the issues that consumers have when cooking and when they use a product, and when you want to form hypotheses about the psychological value of new product ideas (what consumers want to be and what they want to achieve).

[0036] Furthermore, in this embodiment, a system is provided in which input data is collected from a survey of 100 or more, and preferably 300 or more, product users (consumers) per product regarding their satisfaction with the product and the psychological value of the product as perceived by consumers, and output data is displayed based on the structuring of product satisfaction and psychological value and the extraction of factors that lead to product satisfaction.

[0037] In this embodiment, this system can be used when you want to know the concept elements that lead to satisfaction with a product, brand, or service, when you want to narrow down the elements that should be strengthened from multiple psychological values, when you want to verify a hypothesis about the psychological value of a product, brand, or service, when you want to determine the direction of a psychological value hypothesis for quality goal design, and when you want to know the direction of a communication strategy for a product, brand, or service.

[0038] In addition, in this embodiment, as shown in Figure 2, a system is provided in which input data is a survey of each product's users (consumers) on the psychological value of the product as perceived by consumers, conducted with 50 or more, and preferably 100 or more, people per product, and output data is displayed based on positioning based on psychological value and classification of the product and psychological value, as shown in Figure 3.

[0039] In this embodiment, this system can be used when you want to know the position of products, including products that represent the market, products that make up the market, products that are in the market, existing product groups, etc.; when you want to know the characteristics of the psychological value of each product among multiple products developed in the same brand or category; when you have a hypothesis about the psychological value of a product; when you want to decide the direction of the psychological value hypothesis for quality target design; and when you want to know the direction of the product's communication strategy.

[0040] 2. Configuration of the impression evaluation device 100 The impression evaluation device 100 according to this embodiment can be configured by functionally or physically distributing or integrating any unit (either as a stand-alone type or a system type). In this embodiment, an example of the configuration of the impression evaluation device 100 will be described with reference to Fig. 4. Fig. 4 is a block diagram showing an example of the configuration of the impression evaluation device 100 according to this embodiment.

[0041] 4, the impression evaluation device 100 may be an information processing device such as a personal computer or a workstation. The impression evaluation device 100 includes a control unit 102, a storage unit 106, and an input / output unit 112, and the units included in the impression evaluation device 100 are communicably connected via any communication path. The impression evaluation device 100 is communicably connected to other devices via a network 300.

[0042] The input / output unit 112 may have a function for inputting and outputting data (I / O). Here, the input / output unit 112 may be, for example, a key input unit, a touch panel, a control pad (e.g., a touch pad, a game pad, etc.), a mouse, a keyboard, a microphone, etc. The input / output unit 112 may also be a display unit (e.g., a display, monitor, and touch panel made of liquid crystal or organic electroluminescence, etc.) that displays (input / output) information of application software, etc. The input / output unit 112 may also be an audio output unit (e.g., a speaker, etc.) that outputs audio information as audio. The input / output unit 112 may also be an image input unit (e.g., a camera, etc.) that records images (still images and videos) captured by an imaging element such as a CCD image sensor or a CMOS image sensor as digital data. The input / output unit 112 may also be a fingerprint sensor, a camera (e.g., an infrared camera, etc.) that can be used for iris authentication or face authentication, etc., and / or a biometric sensor such as a vein sensor.

[0043] The storage unit 106 stores various databases, tables, and / or files. The storage unit 106 stores computer programs that cooperate with an operating system (OS) to issue commands to a central processing unit (CPU) to perform various processes. The storage unit 106 may be, for example, a random access memory (RAM), a read-only memory (ROM), a hard disk drive (HDD), and / or a solid state drive (SSD). The storage unit 106 may store image data recorded by the input / output unit 112, data received via the network 300, and / or input data input via the input / output unit 112. The storage unit 106 conceptually includes an evaluation target database 106a.

[0044] The evaluation target database 106a stores evaluation target data including psychological value data for the evaluation target. Here, the evaluation target database 106a may store survey data setting the satisfaction level of the evaluation target and selection results for each psychological value of the evaluation target. The evaluation target database 106a may also store survey data setting the selection results for each psychological value of each evaluation target. The psychological value data may also include association structure data, association structure diagrams, sensitivity data, sensitivity analysis output data, text data, dimensionality reduction data, dimensionality reduction output diagrams, cluster analysis data, and survey raw data. The evaluation target may be a product, brand, service, exercise, sleep, healthcare, health, or cooking, such as food, clothing, daily necessities, home appliances, cars, real estate, health foods, supplements, or an application. Here, the psychological value may be satisfaction with the product, perceived health benefits, the enjoyment of cooking, or ease of cooking.

[0045] Furthermore, satisfaction may be an intention to continue using the evaluation object, an intention to purchase, a favorable impression, or a perceived effect, etc. Furthermore, psychological value may be the value of the evaluation object for the consumer and the characteristics of the evaluation object. Furthermore, psychological value may be the value of the evaluation object for the consumer at each stage from before the consumer uses the evaluation object to after the consumer uses it. Here, the stages may include at least one of the following: a recognition stage in which the consumer recognizes the trigger for using the evaluation object, an imagination stage in which the consumer imagines what it would be like to use the evaluation object, a planning stage in which the consumer plans to use the evaluation object, an implementation stage in which the consumer uses the evaluation object, an impression stage in which the consumer obtains impressions of using the evaluation object, and a realization stage in which the consumer realizes the effect of the evaluation object. Furthermore, the stage of analysis using causal inference may be one stage or multiple stages.

[0046] The control unit 102 is a CPU or the like that comprehensively controls the impression evaluation device 100. The control unit 102 has an internal memory for storing control programs such as an OS, programs that define various processing procedures, required data, etc., and executes various information processing based on these stored programs. Functionally, the control unit 102 conceptually includes a questionnaire registration unit 102a, a causal inference analysis unit 102b, a sensitivity analysis unit 102c, a selection rate acquisition unit 102d, a significance test unit 102e, a dimensionality reduction unit 102f, a cluster analysis unit 102g, and a result output unit 102h.

[0047] The questionnaire registration unit 102a registers questionnaire data for the evaluation target. Here, the questionnaire registration unit 102a may selectably display the satisfaction level of the evaluation target and each psychological value of the evaluation target. When satisfaction level and each psychological value are selected, the questionnaire registration unit 102a may acquire a selection result and register the questionnaire data setting the selection result in the evaluation target database 106a. Alternatively, the questionnaire registration unit 102a may acquire free-form responses using a question method such as a word association method, a sentence completion method, a third-party method, or a video presentation method, acquire a term list through analysis including text mining, selectably display the satisfaction level of the evaluation target and each psychological value of the evaluation target based on the term list. When satisfaction level and each psychological value are selected, the questionnaire registration unit 102a may acquire a selection result and register the questionnaire data setting the selection result in the evaluation target database 106a. Alternatively, the questionnaire registration unit 102a may display an impression of the evaluation target so that text can be input. When text is input, the questionnaire registration unit 102a may acquire text data, objectively and quantitatively analyze the text data using text mining to extract psychological values ​​derived from the text data, and register questionnaire data setting a selection result corresponding to the extracted psychological value in the evaluation target database 106a. Here, text mining may include morphological analysis and / or syntactic analysis. The questionnaire registration unit 102a may selectably display each psychological value of the evaluation target, and when each psychological value is selected, obtain a selection result and register the selection result in the evaluation target database 106a. The questionnaire registration unit 102a may obtain free-form responses using a questioning method such as a word association method, a sentence completion method, a third-party method, or a video presentation method, and then obtain a term list through analysis including text mining. Based on the term list, the questionnaire registration unit 102a may selectably display each psychological value of the evaluation target, and when each psychological value is selected, obtain a selection result and register the selection result in the evaluation target database 106a. The video presentation method may be a cooking video presentation method, a concept video presentation method, or an image video presentation method.

[0048] The causal inference analysis unit 102b performs an analysis using causal inference. Here, the causal inference analysis unit 102b may acquire association structure data between satisfaction with the evaluation target and psychological value by analyzing the questionnaire data using causal inference. Furthermore, the causal inference may be probabilistic inference. Here, the probabilistic inference may be a Bayesian network.

[0049] The sensitivity analysis unit 102c performs a sensitivity analysis. Here, the sensitivity analysis unit 102c may acquire sensitivity data in which a sensitivity indicating the contribution of each psychological value to the satisfaction level of the evaluation target is set by performing a sensitivity analysis on the related structure data.

[0050] The selection rate acquisition unit 102d acquires the selection rate of each psychological value. Here, the selection rate acquisition unit 102d may acquire the selection rate of each psychological value based on questionnaire data.

[0051] The significant difference test unit 102e executes a significant difference test to determine whether there is a statistically significant difference. Here, the significant difference test unit 102e may acquire a selection rate of the psychological value for each evaluation target based on the questionnaire data, and perform a significant difference test on the selection rate to acquire a significance probability for each selection rate.

[0052] The dimension reduction unit 102f performs dimension reduction on the questionnaire data. Here, the dimension reduction unit 102f may acquire dimension-reduced data in which relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized by reducing the dimension of the questionnaire data. Alternatively, the dimension reduction unit 102f may identify a psychological value having a selection rate whose significance probability is smaller than a predetermined significance level, and acquire dimension-reduced data in which relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized by reducing the dimension.

[0053] The cluster analysis unit 102g performs cluster analysis. Here, the cluster analysis unit 102g may classify the evaluation objects and psychological values ​​into a plurality of clusters by hierarchical cluster analysis of the position coordinates based on the dimension-reduced data, and obtain cluster analysis data in which the clusters are set.

[0054] The result output unit 102h outputs the analysis results of the psychological value of the evaluation object. Here, the result output unit 102h may display a relational structure diagram between satisfaction and psychological value based on the relational structure data. The result output unit 102h may also display sensitivity analysis output data for the evaluation object based on the sensitivity data and the selectivity. The result output unit 102h may also display a dimension reduction output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduction data. The result output unit 102h may also display a dimension reduction output diagram in which cluster boundaries are distinguishable based on the dimension reduction data and the cluster analysis data. The result output unit 102h may also display hierarchical cluster analysis output data in which the hierarchical structure of each cluster is indicated based on the cluster analysis data.

[0055] 3. Impression Evaluation Process An example of the impression evaluation process according to this embodiment will be described with reference to Fig. 5 to Fig. 25. Fig. 5 is a flowchart showing an example of the impression evaluation process according to this embodiment.

[0056] As shown in FIG. 5, the questionnaire registration unit 102a displays the satisfaction level of the product and each psychological value of the product in a selectable manner on the input / output unit 112, and when the user selects the satisfaction level and each psychological value via the input / output unit 112, obtains the selection result and registers the questionnaire data setting the selection result in the evaluation target database 106a, displays the impression of the product in the input / output unit 112 so that it can be entered as text, and when the user enters text via the input / output unit 112, obtains the text data, objectively and quantitatively analyzes the text data using text mining to extract psychological values ​​derived from the text data, and registers the questionnaire data setting the selection result corresponding to the extracted psychological value in the evaluation target database 106a (step SA-1).

[0057] The significant difference testing unit 102e then obtains the selection rate of the psychological value for each product based on the questionnaire data, and performs a significant difference test on the selection rates to obtain a significant probability for each selection rate (step SA-2).

[0058] Then, the dimension reduction unit 102f identifies psychological values ​​with selection rates whose significance probability is smaller than a predetermined significance level, and through dimension reduction, obtains dimension-reduced data in which the relative position coordinates of the product and the psychological value are set so that the correlation between the product and the psychological value is maximized (step SA-3).

[0059] Then, the cluster analysis unit 102g classifies the products and psychological values ​​into multiple clusters by hierarchical cluster analysis of the position coordinates based on the dimension-reduced data, and obtains cluster analysis data in which the clusters are set (step SA-4).

[0060] Then, the causal inference analysis unit 102b obtains association structure data between the degree of satisfaction with the product and the psychological value through causal inference analysis of the questionnaire data (step SA-5).

[0061] The sensitivity analysis unit 102c then performs a sensitivity analysis on the related structure data to obtain sensitivity data that sets a sensitivity indicating the contribution of each psychological value to product satisfaction, and the selection rate acquisition unit 102d obtains the selection rate of each psychological value based on the questionnaire data (step SA-6). Here, the processing in steps SA-3 and SA-4 and the processing in steps SA-5 and SA-6 may be performed in parallel, or either processing may be performed first.

[0062] Then, based on the relational structure data, sensitivity data, selectivity rate, dimensionality reduction data, and cluster analysis data, the result output unit 102h causes the input / output unit 112 to display a relational structure diagram between satisfaction and psychological value, sensitivity analysis output data for the product, a dimensionality reduction output diagram in which each product and each psychological value is mapped, a dimensionality reduction output diagram in which the boundaries of the clusters are identifiable, and / or hierarchical cluster analysis output data showing the hierarchical structure of each cluster (step SA-7), and then the processing ends.

[0063] [Psychological Value Term Extraction Process] Here, a specific example of the psychological value term extraction process in this embodiment will be described with reference to Figures 6 and 7. Figure 6 is a diagram showing an example of survey raw data in this embodiment. Figure 7 is a diagram showing an example of psychological value classification in this embodiment.

[0064] First, in this embodiment, in the evaluation sample panel selection procedure, the comparison range is set by clarifying the range of psychological value to be extracted and the target audience to be interviewed, and multiple products and target audiences (users, non-users, attributes, etc.) are set to enable comparison and to grasp the characteristics of each. The survey targets not only specific products and services but also the image of a summer breakfast (for example, a summer breakfast of "cold soup" is set as a "winter breakfast" and the value desired for "winter breakfast" is clarified). That is, in this embodiment, target products and survey target audiences are selected within the range of psychological value to be compared (for example, when considering multiple new product concepts, the psychological value of each proposed product is extracted, or the characteristics of the psychological value held by users and non-users toward a product are extracted). Furthermore, in this embodiment, the evaluation situation is set by setting the concept, packaging, and point in consumer memory at which value to be compared.

[0065] In this embodiment, as a requirement for the survey, the number of survey subjects is set to 50 or more, preferably 100 or more per product or group of subjects, and as for the order in which questions are presented, if a "word association method" is used, that question is set first, and if multiple products are targeted and all survey subjects respond about multiple products, the order in which the products are presented is set to a random order (equal allocation) taking into account contrast effects, order effects, etc.

[0066] In this embodiment, a questioning method appropriate for the purpose is selected, utilizing psychological techniques that effectively draw out difficult-to-answer questions and extracting the psychological values ​​of consumers. That is, in the question design in this embodiment, multiple questions are set for one issue in different ways to incorporate questions from multiple perspectives, allowing for a multifaceted understanding and deeper exploration of the issue, and questions are set so that answers are prompted by product images, concept sheets, etc. When it is desired to grasp the characteristics of a product or service, questions are set so that the target products are ranked and the reasons for their ranking are provided (for example, in evaluating chilled noodles at a convenience store (CVS), product images of products that are expected to be competitors (kakiage soba, kakiage udon, Neapolitan, tonkotsu soy sauce ramen) may be presented, and the consumer may be asked to select the one they most want to eat and explain the reason, and then repeatedly asked to select the second, third, and final remaining menu items and the reasons for their selection).

[0067] Then, as shown in FIG. 6, in this embodiment, survey raw data including text data input by the user is registered.

[0068] In this embodiment, the text data is subjected to text analysis including morphological analysis and syntactic analysis to obtain an analysis result.

[0069] In this embodiment, the psychological value terms are classified as shown in Fig. 7. As shown in Fig. 7, in this embodiment, when selecting evaluation terms for the next quantitative survey based on the extracted psychological value terms, the extracted psychological value terms can be classified into 12 categories based on psychological value, and by classifying the psychological value terms, it is possible to check whether the terms are comprehensive and whether the survey purpose or product features and appeal elements are reflected.

[0070] In addition, in this embodiment, the questions may include images or videos, and the subject's spontaneous responses to them may be used.

[0071] [Bayesian Network Analysis Processing] Here, a specific example of the Bayesian network analysis processing in this embodiment will be described with reference to Figs. 8 to 10. Fig. 8 is a diagram showing an example of survey raw data in this embodiment. Fig. 9 is a diagram showing an example of a structural diagram of the relationship between usage intention and psychological value obtained by Bayesian network analysis in this embodiment. Fig. 10 is a diagram showing an example of sensitivity analysis output in this embodiment.

[0072] First, in this embodiment, in the evaluation term selection procedure, a candidate list of psychological value terms is set up by extracting terms that represent the concept of products within the range to be compared, psychological value terms used in past benchmark surveys, etc., and terms that represent new concept elements that the product wishes to promote to consumers. This list of approximately 20-40 words is then set up. The psychological value terms are selected by deleting duplicate terms, adding important terms that succinctly express the product's characteristics, deleting expressions that are difficult for consumers to understand, and modifying them to make them easier to understand. A third party then checks for any unclear expressions, and if any are found, they are discussed and modified, ultimately completing a term list of up to approximately 30 words. For example, in this embodiment, two words that appear to have similar concepts but are used as different psychological value terms, such as "seems to have good nutritional balance" and "seems to be nutritious," could be adopted, and the confusing expression "seems to go well with staple food" could be changed to "seems like something you'd want to eat with bread or rice."

[0073] In this embodiment, as requirements for the survey, the number of survey subjects is set to 100 or more per product, preferably 300 or more; target attributes are recruited (heavy users / new trial, etc.); when it is desired to compare segments such as users / non-users, gender, and age, the number of survey subjects in each segment is set to 100 or more per product, preferably 300 or more; with regard to the order in which psychological evaluation terms are presented, since options set (arranged) first in the survey are more likely to be selected, the psychological evaluation terms are always set in random order for each survey subject; since there is a possibility that a subject will respond that all of the presented options do not apply to them, "Other (free description)" or "None of the above apply" is set at the end of the options; and with regard to the method of presenting questions, data is entered using a rating system, such as a five-point system ranging from "not at all applicable" to "very applicable" regarding the degree to which each psychological evaluation term is considered applicable, and the ratings are set to be reclassified into two levels of "applicable / not applicable" during analysis. For example, in this embodiment, the method of presenting the questions may be set to "Please select all that apply to your image of the product (you can select as many as you like)."

[0074] In this embodiment, the user selects a product for which the user wishes to understand the product's satisfaction and psychological value, and then uses terms related to the product's intention to use and satisfaction to select up to 30 terms that represent the psychological value that consumers have of the product, and is asked to select one.

[0075] In this embodiment, raw survey data including the selection results selected by the user is registered as shown in Fig. 8. Here, as shown in Fig. 8, when product satisfaction is input using the rating system, high product satisfaction is classified as "1" or low product satisfaction as "0" based on the original rating, and when psychological value is input, if each psychological value applies to each sample, it is entered as "1", and if it does not, it is entered as "0".

[0076] As shown in Figure 9, in this embodiment, product satisfaction and psychological value are structured by Bayesian network analysis, and output data is displayed that allows the relationship between product satisfaction and psychological value in the acquired data to be understood.

[0077] As shown in Figure 10, in this embodiment, the degree of influence based on the structure is calculated by calculating the probability of contributing to product satisfaction through sensitivity analysis based on a structural diagram obtained through Bayesian network analysis, extracting elements that should be prioritized based on the level of sensitivity, and simultaneously comparing the selection rate of psychological value and the sensitivity analysis to display output data that allows one to understand whether the value that contributes to usage intention is a value that is already felt by many people or not.

[0078] In this embodiment, the impression (value) that makes consumers want to purchase a product or brand is identified by calculating an index of how much they want to purchase when they sense a certain image. That is, in this embodiment, based on the purchase intention and image selection results for each product or brand, psychological values ​​that directly or indirectly influence purchase intention are structured using Bayesian network analysis, an analytical method that visualizes the causal relationships between events that occur in a chain reaction, and then the probability that they will contribute to purchase intention is calculated using sensitivity analysis, and the impression (value) that makes consumers want to purchase is extracted from the level of sensitivity.

[0079] In addition, this embodiment may include automatic collection of data related to experiences and usage that is automatically acquired by engines, including logs on the Internet.

[0080] [Dimension Reduction Processing] A specific example of dimension reduction processing in this embodiment will be described with reference to Figs. 11 to 17. Fig. 11 is a diagram showing an example of input in this embodiment. Fig. 12 is a diagram showing an example of survey raw data in this embodiment. Fig. 13 is a diagram showing an example of summary table data in this embodiment. Fig. 14 is a diagram showing an example of analysis output of the Cochran Q test in this embodiment. Figs. 15 and 17 are diagrams showing examples of dimension reduction output in this embodiment. Fig. 16 is a diagram showing an example of cluster analysis output in this embodiment.

[0081] First, in this embodiment, in the evaluation sample selection procedure, the range of comparison is set by clarifying the range of comparison in psychological value (for example, a comparison of each variety of our company's cold soup, a comparison of each variety of packaged soup including competitors' products, a comparison between brands in the area of ​​combined condiments, or a comparison of our company's products with other product categories for summer breakfast occasions, etc.), and for product / brand selection, representative products, brands, products, or varieties within the set range are selected (for example, all varieties of our company's products, competitors' products and all varieties of our company's products, competitors' brands and our company's combined condiment brands, or representative breakfast menu items such as yogurt, salad, or coffee, etc.), and for presentation method setting, it is decided at which point in time value is to be compared: concept, packaging, actual eating, consumer memory, etc., and settings are made, for example, by presenting both package images and actual food, presenting images of several varieties of each brand, or consumer memory (no images, etc.).

[0082] In this embodiment, the evaluation term selection procedure involves extracting terms that represent the concepts of products within the range to be compared, psychological value terms used in past benchmark surveys, and terms that represent new concept elements that the product wishes to promote to consumers, and setting up a candidate list of approximately 30-50 words. The psychological value terms are selected by deleting duplicate terms, adding important terms that succinctly express the product's characteristics, deleting expressions that are difficult for consumers to understand, and modifying them to make them easier to understand. A third party is then asked to confirm whether there are any difficult expressions, and if there are, they are discussed and modified, ultimately completing a term list of approximately 30 words. For example, in this embodiment, two words that appear to have similar concepts but are used as different psychological value terms, such as "seems to have good nutritional balance" and "seems to be nutritious," could be adopted, and the difficult-to-understand expression "seems to go well with staple food" could be changed to "seems like it would go well with bread or rice."

[0083] In this embodiment, as a requirement for the survey, the number of survey subjects is set to 100 or more per product, target attributes are recruited (heavy users / new trial, etc.), and when it is desired to compare segments such as users / non-users, gender, and age, it is recommended to set the number of survey subjects in each segment to 100 or more and have all survey subjects evaluate all samples. However, when comparing the image that users of each product have of each product, different subjects are set for each product, and the order of presentation of the evaluation samples is set to a random order (equal allocation) taking into account contrast effects, order effects, etc., and when tasting of the evaluation samples is involved, it is recommended to set the number of survey subjects to 100 or more per product. The tasting order is set to a random order, and the order in which the psychological evaluation terms are presented is set to a random order for each survey subject, since options set (arranged) first in the survey are more likely to be selected. When the same survey subject evaluates multiple evaluation samples, the same order in which the evaluation terms are presented is set for all evaluation samples to avoid placing too much of a burden on the evaluation. Regarding the question presentation method, data entered using a rating system ranging from "not at all applicable" to "very applicable" to determine how applicable each psychological evaluation term is is reclassified into two levels of "applicable / not applicable" during analysis. For example, in this embodiment, the question presentation method may be set to "Please select all that apply to your image of the product (you can select as many as you like)."

[0084] As shown in FIG. 11, in this embodiment, target products within the range for which psychological values ​​are to be compared are selected, and up to 30 terms representing the psychological values ​​that consumers have for the products are selected and the user is allowed to select one.

[0085] In this embodiment, survey raw data including the selection results selected by the user is registered as shown in Fig. 12. As shown in Fig. 12, for the psychological values, if each psychological value applies to each sample, "1" is entered, and if it does not apply, "0" is entered.

[0086] 13, in this embodiment, the survey raw data is aggregated to create summary table data for analysis. Note that in this embodiment, analysis can be applied to past survey data for which there is no survey raw data, as long as there is summary table data.

[0087] 14, in this embodiment, a significant difference test (for example, a Cochran Q test) is performed on the selection rate of psychological value for each product to determine whether the acquired data differs between products and can be classified. This makes it possible to confirm that there is a statistically significant difference in psychological value between products.

[0088] As shown in Figure 15, in this embodiment, as a mapping based on psychological value, the ratings are statistically replaced by dimension reduction to maximize the correlation between the product and psychological value, and the differences in positioning are visualized by converting them into scores that can be plotted on the same plane. Here, in this embodiment, the closer the distance between the product and psychological value is plotted, the stronger the correlation between them. In other words, in this embodiment, products and psychological value can be mapped based on psychological value.

[0089] 16, in this embodiment, the coordinate values ​​obtained by dimension reduction are classified into samples and psychological values ​​using cluster analysis. That is, in this embodiment, products and psychological values ​​can be classified based on the actual feelings of consumers.

[0090] 17, in this embodiment, the value of each product can be clarified based on the psychological value that consumers have for the product, and a hypothesis can be formed for the value that should be strengthened. That is, in this embodiment, a concept hypothesis can be formed after the psychological value of the product is clarified.

[0091] Furthermore, in this embodiment, important values ​​may be extracted when purchasing items other than food, such as clothing, daily necessities, home appliances, cars, and real estate; values ​​that increase satisfaction with experiences during use may be identified; effects may be identified for health foods, supplements, exercise, sleep, and healthcare, as well as the use of apps and services; and values ​​may be identified to increase satisfaction with experiences in entertainment (theme parks and movies), travel (resorts, hotels, hot springs, and business hotels), and education (libraries). Furthermore, in this embodiment, in order to eliminate negative experiences, user experience evaluations of UI (User Interface) / UX (User Experience) may be performed (elements that increase satisfaction with both the device itself and the experience of using it) and experiences that may be implemented in the future (for example, satisfaction with automatic daily menu suggestions, dining together in VR, dining together with an avatar, etc.) may also be evaluated and analyzed.

[0092] Example 1 Example 1 will be described with reference to Fig. 18 and Fig. 19. Fig. 18 is a diagram showing an example of a research method in this embodiment. Fig. 19 is a diagram showing an example of an association structure diagram by Bayesian network analysis in this embodiment.

[0093] In this embodiment, questionnaire data on the evaluation target is obtained using the questions shown in Figure 18, and by performing Bayesian network analysis on the questionnaire data, a structural diagram of the relationship between product features, consumer values, and purchase intentions can be displayed, as shown in Figure 19.

[0094] Here, as shown in Fig. 18, in this embodiment, only the TOP BOX out of the five-level selection for "purchase intention" may be set to "intention to purchase," 27 items may be selected for "consumer values," and 27 items may be selected for "product features." Also, as shown in Fig. 19, the relational structure diagram shows only edges with a sensitivity of 0.1 or more, which is the value obtained by subtracting the "probability that a person who 'feels' about each item (node) at the origin of the arrow is predicted to feel the item at the destination of the arrow" from the "probability that a person who 'feels' about each item (node) at the origin of the arrow is predicted to feel the item at the destination of the arrow."

[0095] In this embodiment, the top three currently recognized consumer values ​​are "easy to eat," "healthy," and "tasty," and the top three product features are "provides beans," "provides vegetables," and "provides dietary fiber." Also, as shown in FIG. 19 , the consumer values ​​that motivate consumers to purchase this product are "never get tired of eating it" and "suitable for me," and "never get tired of eating it" is strongly associated with the consumer values ​​of "healthy for the body" and "suitable for me." Also, as shown in FIG. 19 , the product features that stimulate consumer values ​​that motivate consumers to purchase this product are "utilizes the ingredients," "good color," "provides beans," "good quality," "provides vegetables," "provides protein," "easy to reheat," and "thick."

[0096] Therefore, as shown in Figure 19, in the product development of ingredient-containing retort soups in this embodiment, it is desirable to have quality design, such as good color and moderate thickness, so that consumers will feel that the soup is suitable for them. Also, as shown in Figure 19, in the product development of ingredient-containing retort soups in this embodiment, it is desirable to have product design that provides vegetables and protein and is easy to heat, so that consumers will feel that the soup warms their body. Therefore, as shown in Figure 19, in the product development of ingredient-containing retort soups in this embodiment, it is necessary to appeal to the image that the ingredients are being used to their full potential, that the soup is high quality, contains beans and vegetables, and is healthy for the body, so that consumers will feel that they will never tire of eating it. Suggestions are obtained for product design and the design of consumer value through the product.

[0097] In this way, this embodiment can identify consumer values ​​that lead to purchases and indicate related product features. Furthermore, this embodiment can grasp the "consumer values" that directly or indirectly affect purchase intentions and the "product features" that affect them by tracing the connections in the Bayesian network structure.

[0098] Example 2 will be described with reference to Fig. 20 to Fig. 22. Fig. 20 is a diagram showing an example of a research method in this embodiment. Figs. 21 and 22 are diagrams showing an example of an association structure diagram obtained by Bayesian network analysis in this embodiment.

[0099] In this embodiment, the survey method shown in Fig. 20 is used to obtain questionnaire data on the subject to be evaluated, and a Bayesian network analysis of the questionnaire data can be used to display a structural diagram of the relationship between the psychological value of each step of the plan step, implementation step, and impression step from before to after a consumer starts dieting, weight loss, or slimming, and the perceived effect in the realization step, as shown in Fig. 21 and Fig. 22. Note that Fig. 21 and Fig. 22 only show edges with a sensitivity of 0.1 or greater.

[0100] As shown in Figure 21, in the case of women, those who place importance on "losing weight in a healthy way" are more likely to "review their diet" and "walk more actively and use the stairs" and feel that they have "lost weight and body fat," and to feel that they have achieved results. On the other hand, those who choose "stopping snacking" or "reducing meals" as their diet method are more likely to feel that "it is difficult to continue" and not to feel that they have achieved results.

[0101] Furthermore, as shown in Figure 22, it is suggested that in the case of men, those who choose the diet method of "reducing the amount of food they eat" are more likely to feel that they have "lost weight and body fat" and to feel that they have achieved results.

[0102] In this way, in this embodiment, it is possible to grasp the transition of consumer values ​​that lead to satisfaction, perceived effects, and intention to continue in the customer journey for food and health. Furthermore, in this embodiment, consumer values ​​are set for each touchpoint of a product or service, and the "consumer values" that directly or indirectly affect purchase intention, intention to continue, and perceived effects can be grasped by tracing the connections in the Bayesian network structure.

[0103] Example 3 will be described with reference to Fig. 23 to Fig. 25. Fig. 23 is a diagram showing an example of a research method in this embodiment. Figs. 24 and 25 are diagrams showing examples of a relational structure diagram obtained by Bayesian network analysis in this embodiment.

[0104] In this embodiment, the survey method shown in Figure 23 is used to obtain questionnaire data on the subject to be evaluated, and by performing Bayesian network analysis on the questionnaire data, it is possible to display a structural diagram of the relationship between expectations for the product, usage experiences, and intention to continue using the product, as shown in Figure 24.

[0105] As a result, as shown in Figure 25, in this embodiment, by examining the thoughts, feelings, and actions of health-conscious consumers through all of the touch points between a product or service and the consumer, it is possible to learn about competitors that are not limited to food products and to grasp the elements that allow consumers to feel the effects, and therefore it is possible to identify the transition of experiences that are valuable to consumers and use this in product concept design.

[0106] [4. Other Embodiments] In addition to the above-described embodiments, the present invention may be implemented in various different embodiments within the scope of the technical concept described in the claims.

[0107] For example, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods.

[0108] Furthermore, the processing procedures, control procedures, specific names, information including parameters such as registered data and search conditions for each process, screen examples, and database configurations shown in this specification and drawings can be changed as desired unless otherwise specified.

[0109] Furthermore, with regard to the impression evaluation device 100 and the like, the components shown in the drawings are functional concepts, and do not necessarily have to be physically configured as shown in the drawings.

[0110] For example, all or any part of the processing functions of the impression evaluation device 100, particularly the processing functions performed by the control unit, may be implemented by a CPU and a program interpreted and executed by the CPU, or may be implemented as hardware using wired logic. The program is recorded on a non-transitory computer-readable recording medium containing programmed instructions for causing the information processing device to execute the processes described in this embodiment, and is mechanically read as needed. That is, a computer program for providing instructions to the CPU in cooperation with the OS and performing various processes is recorded in a storage unit such as a ROM or HDD (hard disk drive). This computer program is executed by being loaded into RAM and cooperates with the CPU to form the control unit.

[0111] In addition, this computer program may be stored in an application program server connected to the impression evaluation device 100, etc. via any network 300, and it is also possible to download all or part of it as needed.

[0112] Furthermore, the program for executing the processes described in this embodiment may be stored in a non-transitory computer-readable recording medium, or may be configured as a program product. Here, this "recording medium" includes memory cards, USB (Universal Serial Bus) memories, SD (Secure Digital) cards, flexible disks, magneto-optical disks, ROMs, EPROMs (Erasable Programmable Read Only Memory), EEPROMs (registered trademark) (Electrically Erasable and Programmable Read Only Memory), CD-ROMs (Compact Disk Read Only Memory), MOs (Magneto-Optical disks), DVDs (Digital Versatile Disks), and more. This includes any "portable physical medium" such as a Blu-ray Disc, a DVD player, a DVD player, a Blu-ray Disc, etc.

[0113] Furthermore, a "program" is a data processing method written in any language or description method, and does not matter whether it is in the form of source code or binary code. Note that a "program" is not necessarily limited to a single structure, but also includes a structure that is distributed as multiple modules or libraries, or a structure that achieves its function by cooperating with a separate program, such as an OS. Note that the specific configuration and reading procedure for reading a recording medium in each device shown in this embodiment, as well as the installation procedure after reading, can use well-known configurations and procedures.

[0114] The various databases stored in the memory unit are storage means such as memory devices such as RAM and ROM, fixed disk devices such as hard disks, flexible disks, and optical disks, and store various programs, tables, databases, and web page files used for various processes and providing websites.

[0115] The impression evaluation device 100 may be configured as an information processing device such as a known personal computer or workstation, or may be configured as the information processing device to which any peripheral device is connected. The impression evaluation device 100 may be realized by installing software (including programs or data) that causes the device to perform the processing described in this embodiment.

[0116] Furthermore, the specific form of distribution and integration of the devices is not limited to that shown in the drawings, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various additions or functional loads. In other words, the above-mentioned embodiments can be implemented in any combination, or embodiments can be implemented selectively.

[0117] The present invention is useful in a variety of industries, including the food industry and the information processing industry.

[0118] REFERENCE SIGNS LIST 100 impression evaluation device 102 control unit 102a questionnaire registration unit 102b causal inference analysis unit 102c sensitivity analysis unit 102d selection rate acquisition unit 102e significance test unit 102f dimension reduction unit 102g cluster analysis unit 102h result output unit 106 storage unit 106a evaluation target database 112 input / output unit 300 network

Claims

1. An impression evaluation device comprising a memory unit and a control unit, wherein the memory unit comprises: evaluation object storage means for storing questionnaire data setting the satisfaction level of the evaluation object and the selection results for each psychological value of the evaluation object; and the control unit comprises: causal inference analysis means for acquiring association structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference; and result output means for displaying an association structure diagram between the satisfaction level and the psychological value based on the association structure data.

2. An impression evaluation device comprising a memory unit and a control unit, wherein the memory unit comprises: an evaluation object storage means for storing questionnaire data setting selection results for each psychological value of each evaluation object; and the control unit comprises: a dimension reduction means for acquiring dimension reduced data setting relative position coordinates of the evaluation object and the psychological value so as to maximize the correlation between the evaluation object and the psychological value by reducing the dimension of the questionnaire data; and a result output means for displaying a dimension reduced output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduced data.

3. The control unit further comprises: a sensitivity analysis means for acquiring sensitivity data in which a sensitivity indicating the contribution of each psychological value to the satisfaction level of the evaluation target is set by sensitivity analysis of the related structure data; and a selection rate acquisition means for acquiring a selection rate of each psychological value based on the questionnaire data, and the result output means further displays sensitivity analysis output data for the evaluation target based on the sensitivity data and the selection rate. The impression evaluation device described in claim 1, characterized in that the control unit further comprises: a sensitivity analysis means for acquiring sensitivity data in which a sensitivity indicating the contribution of each psychological value to the satisfaction level of the evaluation target is set by sensitivity analysis of the related structure data; and a selection rate acquisition means for acquiring a selection rate of each psychological value based on the questionnaire data.

4. The impression evaluation device described in claim 1, further comprising a questionnaire registration means for selectively displaying the satisfaction level of the evaluation target and each of the psychological values ​​of the evaluation target, and, when the satisfaction level and each of the psychological values ​​are selected, acquiring the selection result and registering the questionnaire data setting the selection result in the evaluation target storage means.

5. The impression evaluation device described in claim 4, characterized in that the questionnaire registration means obtains free-form descriptions using a questioning method such as word association, sentence completion, third-party questioning, or video presentation method, obtains a term list by analysis including text mining, displays the satisfaction level of the evaluation target and each of the psychological values ​​of the evaluation target in a selectable manner based on the term list, and when the satisfaction level and each of the psychological values ​​are selected, obtains the selection result, and registers the questionnaire data with the selection result set in the evaluation target storage means.

6. The impression evaluation device according to claim 1 or 2, further comprising a questionnaire registration means for displaying an impression of the evaluation object so that it can be input as text, and when text is input, acquiring the text data, objectively and quantitatively analyzing the text data by text mining to extract the psychological value derived from the text data, and registering the questionnaire data in which the selection result corresponding to the extraction result of the psychological value is set in the evaluation object storage means.

7. The impression evaluation device according to claim 6, wherein the text mining includes morphological analysis and / or syntactic analysis.

8. The impression evaluation device according to claim 1, characterized in that the causal inference is a probabilistic inference.

9. The impression evaluation device according to claim 8, wherein the probabilistic inference is a Bayesian network.

10. The impression evaluation device according to claim 1 or 2, characterized in that the object of evaluation is a product, brand, service, exercise, sleep, healthcare, health, or cooking, which is food, clothing, daily necessities, home appliances, cars, real estate, health foods, supplements, or an application.

11. The impression evaluation device according to claim 10, characterized in that the psychological value is satisfaction with the product, a sense of the health benefits, or the enjoyment or ease of cooking.

12. The impression evaluation device described in claim 2, further comprising a cluster analysis means for classifying the evaluation object and the psychological value into a plurality of clusters by hierarchical cluster analysis of the position coordinates based on the dimension reduction data and obtaining cluster analysis data in which the clusters are set, and the result output means for displaying the dimension reduction output diagram in which the boundaries of the clusters are identifiable based on the dimension reduction data and the cluster analysis data.

13. The impression evaluation device according to claim 12, characterized in that said result output means further displays hierarchical cluster analysis output data showing a hierarchical structure of each of said clusters based on said cluster analysis data.

14. The control unit further comprises a significance testing means for obtaining a selection rate of the psychological value for each of the evaluation objects based on the questionnaire data, and obtaining a significance probability for each of the selection rates by a significance test for the selection rates; and the dimension reduction means identifies the psychological value of the selection rate whose significance probability is smaller than a predetermined significance level, and obtains, by the dimension reduction, the dimension reduced data in which the relative position coordinates of the evaluation object and the psychological value are set so that the correlation between the evaluation object and the psychological value is maximized. This is characterized by the impression evaluation device described in claim 2.

15. The impression evaluation device described in claim 2, characterized in that the control unit further comprises a questionnaire registration means for displaying each of the psychological values ​​of the evaluation objects in a selectable manner, and, when each of the psychological values ​​is selected, acquiring the selection result and registering the questionnaire data in which the selection result is set in the evaluation object storage means.

16. The impression evaluation device described in claim 15, characterized in that the questionnaire registration means obtains free-form descriptions using a questioning method such as a word association method, a sentence completion method, a third-party method, or a video presentation method, obtains a term list by analysis including text mining, displays each of the psychological values ​​of the evaluation target in a selectable manner based on the term list, and when each of the psychological values ​​is selected, obtains the selection result, and registers the questionnaire data with the selection result set in the evaluation target storage means.

17. The impression evaluation device according to claim 5 or 16, characterized in that the video presentation method is a cooking video presentation method, a concept video presentation method, or an image video presentation method.

18. The impression evaluation device described in claim 1, characterized in that the satisfaction level is a purchasing intention for the object to be evaluated, and the psychological value is the value of the object to be evaluated for consumers and the characteristics of the object to be evaluated.

19. The impression evaluation device described in claim 1, characterized in that the satisfaction level is the intention to continue using the evaluation object, the intention to purchase, the favorable impression, or the sense of effectiveness, and the psychological value is the value of the evaluation object to the consumer at each stage from before to after the consumer uses the evaluation object.

20. The impression evaluation device as described in claim 19, characterized in that the stages include at least one of a recognition stage for recognizing the trigger for using the evaluation object, an imagination stage for imagining what it would be like to use the evaluation object, a planning stage for planning the use of the evaluation object, an implementation stage for using the evaluation object, an impression stage for obtaining impressions of using the evaluation object, and a realization stage for realizing the effects of the evaluation object.

21. An impression evaluation method to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises: an evaluation object storage means for storing questionnaire data setting the satisfaction level of the evaluation object and a selection result for each psychological value of the evaluation object; and the impression evaluation method includes: a causal inference analysis step executed in the control unit, for acquiring association structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference; and a result output step for displaying an association structure diagram between the satisfaction level and the psychological value based on the association structure data.

22. An impression evaluation method to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises: evaluation object storage means for storing questionnaire data setting selection results for each psychological value of each evaluation object; and the impression evaluation method includes: a dimension reduction step executed in the control unit, for acquiring dimension reduced data setting relative position coordinates of the evaluation object and the psychological value by reducing the dimension of the questionnaire data so that the correlation between the evaluation object and the psychological value is maximized; and a result output step for displaying a dimension reduced output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduced data.

23. An impression evaluation program to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises: an evaluation object storage means for storing questionnaire data setting the satisfaction level of the evaluation object and the selection results for each psychological value of the evaluation object; and in the control unit, a causal inference analysis step for acquiring association structure data between the satisfaction level and the psychological value for the evaluation object by analyzing the questionnaire data using causal inference; and a result output step for displaying an association structure diagram between the satisfaction level and the psychological value based on the association structure data.

24. An impression evaluation program to be executed by an impression evaluation device having a memory unit and a control unit, wherein the memory unit comprises: an evaluation object storage means for storing questionnaire data setting selection results for each psychological value of each evaluation object; and in the control unit, a dimension reduction step for acquiring dimension reduced data setting relative position coordinates of the evaluation object and the psychological value that maximizes the correlation between the evaluation object and the psychological value by reducing the dimension of the questionnaire data; and a result output step for displaying a dimension reduced output diagram in which each evaluation object and each psychological value is mapped based on the dimension reduced data.

Images