WO2022208718A1 - 商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体 - Google Patents

商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体 Download PDF

Info

Publication number
WO2022208718A1
WO2022208718A1 PCT/JP2021/013818 JP2021013818W WO2022208718A1 WO 2022208718 A1 WO2022208718 A1 WO 2022208718A1 JP 2021013818 W JP2021013818 W JP 2021013818W WO 2022208718 A1 WO2022208718 A1 WO 2022208718A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
product
design
target
person
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/013818
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
涼 都丸
亮 高本
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to PCT/JP2021/013818 priority Critical patent/WO2022208718A1/ja
Priority to US18/274,657 priority patent/US20240095798A1/en
Priority to JP2023510013A priority patent/JP7485203B2/ja
Publication of WO2022208718A1 publication Critical patent/WO2022208718A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0621—Electronic shopping [e-shopping] by configuring or customising goods or services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a technology for providing information on how people feel about product designs.
  • the product design may be decided by referring to the results of a venue survey (CLT (Central Location Test)) from among multiple design candidates.
  • CLT Central Location Test
  • a site survey is a survey method in which survey subjects (monitors) are gathered at a predetermined site and questionnaires (including interviews) are conducted. For example, in an on-site survey on product design, a monitor asks a monitor whether or not a candidate for a product design is wanted to purchase. In addition, the monitor is requested to comment on product design candidates.
  • Patent Document 1 International Publication No. 2021/009880
  • a product is designed by combining design elements related to a plurality of parts (parts) constituting a product such as shoes and clothing
  • the user's perception of the product is described.
  • Techniques for estimating impressions are presented.
  • Patent Document 2 International Publication No. 2020/144820 discloses a technique for estimating a user's evaluation result for a product by focusing on the attributes of the product.
  • Site surveys on product designs provide information such as the purchase intentions and comments of monitors (in other words, consumers) who see product design candidates. It is useful information when making decisions.
  • the main purpose of the present invention is to provide a technology that can suitably support product design (generation).
  • an acquisition unit that acquires a design image related to the design of the target product; an estimation unit for estimating line-of-sight information and opinion information of a target person with respect to the design of the target product using the design image and the estimation model; an output unit that outputs the line-of-sight information and the view information;
  • the estimation model includes product information for learning including product design images and attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information for learning the person for the design of the product. It is a model that has learned the relationship between the view information of
  • the product design generation support method by computer, Acquire a design image related to the design of the target product, estimating gaze information and opinion information of the target person with respect to the design of the target product using the design image and the estimation model; outputting the line-of-sight information and the view information;
  • the estimation model includes product information for learning including a design image of a product, attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information on the person for the design of the product for learning. It is a model that has learned the relationship between opinion information for learning.
  • the estimation model includes product information for learning including a design image of a product, attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information on the person for the design of the product for learning. It is a model that has learned the relationship between opinion information for learning.
  • product design generation
  • product design generation
  • FIG. 4 is a diagram showing an example of a graph (knowledge graph) used for generating an estimation model; It is a figure explaining an example of an estimation model. It is a figure explaining another example of an estimation model.
  • FIG. 10 is a diagram illustrating another example of input of an estimation model; It is a figure showing the example of a display of line-of-sight information and opinion information. 4 is a flow chart explaining an example of the operation of the product design generation support device according to the first embodiment; It is a figure explaining an example of the estimation model used by 2nd Embodiment.
  • FIG. 4 is a diagram showing an example of a graph (knowledge graph) used for generating an estimation model; It is a figure explaining an example of an estimation model. It is a figure explaining another example of an estimation model.
  • FIG. 10 is a diagram illustrating another example of input of an estimation model; It is a figure showing the example of a display of line-of-sight information and opinion information. 4 is a flow chart explaining an example of the operation
  • FIG. 11 is a diagram illustrating another example of an estimation model used in the second embodiment;
  • FIG. FIG. 11 is a diagram showing an example of a graph (knowledge graph) used to generate an estimation model in the second embodiment; It is a figure showing the example of a display of line-of-sight information and opinion information. It is a figure showing the example of a display of line-of-sight information, opinion information, and presumed reason. It is a figure showing the state where the goods are displayed on the shelf.
  • FIG. 10 is a diagram of a display example showing the ranking of designs; It is a figure explaining other examples of an estimation model. It is a figure explaining the structure of the product design generation assistance apparatus in other embodiment. It is a flow chart explaining an example of operation of a goods design generation support device in other embodiments.
  • FIG. 1 is a diagram illustrating the configuration of a product design generation support device according to the first embodiment of the present invention.
  • the product design generation support device 1 of the first embodiment has a function of, when a product design image is input, estimating the line-of-sight information and opinion information of the target person with respect to the product design, and outputting the estimated line-of-sight information and opinion information. It has In the following description, the product design generation support device will be abbreviated as a support device.
  • Products include not only tangible items such as food, toys, miscellaneous goods, furniture, home appliances, and clothing, but also intangible items such as services and information, but the products here are tangible items.
  • a design is a product's shape, pattern, color, or a combination thereof.
  • the product design includes the design of the product itself, the design of the package of the product, or a combination thereof.
  • contents such as food, toys, miscellaneous goods, etc. are contained in a package.
  • the design of the product targeted by the support device 1 may be the design of only one of the package and its contents, or the design of each of the package and the contents. Or it may be a combination design.
  • the support device 1 can be adapted to any such design. explain.
  • the design image of the product to be input to the support device 1 is an image representing the design of the product, such as a photographed image of the product or an illustration image in which the product is drawn.
  • Line-of-sight information is information about the target person's line of sight to the design of the product.
  • the target person here is a person who has seen the product, and an example thereof is a target person (hereinafter also referred to as a monitor) of the site survey.
  • the target person is not limited to the target person (monitor) of the venue survey, but in the following description, the target person is the target person (monitor) of the venue survey.
  • Line-of-sight information is, for example, viewing time, number of times of viewing, visibility rate, etc., but is not limited to these as long as it is information related to line of sight.
  • a site survey site survey site
  • a plurality of products including the survey target product are arranged as shown in FIG.
  • FIG. 2 is a diagram showing an example of the state of a research site where a site survey on beverage package design is being conducted.
  • a plurality of commodities 30 with different package designs are lined up, and some or all of the commodities 30 are survey target commodities.
  • a product to be researched is a product for which it is desired to investigate what kind of opinion the monitor 40 shows about the product, and here, it is a product having a package design candidate that may be adopted as the package of the product.
  • the product under investigation is also referred to herein as the target product.
  • the target product when products other than the survey target are arranged, the products other than the survey target are used for comparison with the survey target product.
  • the plurality of packages in FIG. 2 have shapes, patterns (including patterns and lettering (fonts and sizes of characters used for design), and their arrangement positions), colors, and materials (for example, PET bottles, cans, bottles, etc., are different from each other, but one of them may be common.
  • the term "commercial products” includes prototypes and comparative products that are not actually sold as commercial products.
  • the viewing time is the time during which the monitor 40 is viewing a certain target product.
  • the number of viewing times is the number of times the monitor 40 has seen a certain target product in a situation where a plurality of products 30 are lined up.
  • the visibility rate is the ratio of the time that the monitor 40 looks at a certain target product to the time that the monitor 40 looks at the lined up products 30, or the total number of times the monitor 40 looks at each of the multiple products 30. It is the ratio of the number of times that a certain target product was seen to the
  • the line-of-sight information output by the support device 1 is information related to the line of sight including at least one of the above-described viewing time, number of times of viewing, and visibility rate.
  • Opinion information is information that represents the opinion of the monitor 40 on the design of the target product obtained from, for example, a questionnaire regarding the design of the product.
  • the opinion of the monitor 40 regarding the design (package) of the target product is an opinion indicating whether or not the target product was viewed and the user wanted to purchase the target product (in the following description, it is also referred to as purchase intention). is called).
  • the product design generation support device 1 of the first embodiment is a computer (for example, a server located in a data center), and as shown in FIG. It is connectable via a network.
  • the terminal device 3 is a PC (Personal Computer), tablet, smart phone, wearable terminal, or the like.
  • the design image of the target product is transmitted from the terminal device 3 to the support device 1 .
  • the support device 1 includes an arithmetic device 10 and a storage device 20 .
  • the storage device 20 has a configuration for storing various data and a computer program (hereinafter also referred to as a program) 21 that controls the operation of the support device 1.
  • the storage device 20 is configured by a storage medium such as a hard disk device or a semiconductor memory.
  • the storage device provided in the support device 1 is not limited to one, and a plurality of types of storage devices may be provided in the support device 1. In this case, the plurality of storage devices are collectively referred to as a storage device 20. .
  • the storage device 20 further stores an estimation model 22 .
  • the estimation model 22 is a model that receives a design image of a target product as an input and outputs gaze information and opinion information of a target person regarding the design of the target product, and is generated by machine learning using deep learning, for example.
  • the product information for learning including the design image representing the design of the first product, the attribute information for learning of the first person who saw the design of the first product, and the first
  • the relationship between the learning view information representing the purchase intention of the first person who saw the design of the product and the line-of-sight information for learning of the first person who saw the design of the first product is the relationship between the first product and the first person are variously changed and learned.
  • the first product is the product 30 including prototypes and comparative products arranged as shown in FIG.
  • product information includes, for example, the name of the product, the type of flavor, the amount of content, the price, the place of origin, the name of the ingredients, the place of origin of the ingredients, additives, nutritional ingredients, and functionality.
  • product information includes the alcohol content (alcohol content) in addition to the product information described above.
  • Product information other than the design image used to generate the estimation model 22 is appropriately selected in consideration of the type of product.
  • the first person is, for example, a monitor of research on product design that was conducted prior to generating the estimation model 22 .
  • various information about the first person shall be used to generate the estimation model 22 .
  • attribute information of a person examples include age, lifestyle information (e.g., information on meals such as number of meals per day and meal times, amount of exercise in a week, sleep time, wake-up time, bedtime, etc.). commuting time), preference information, and hobbies.
  • the learning attribute information of a person used to generate the estimation model 22 is appropriately selected in consideration of the type of product. Also, the learning attribute information of a person that is used to generate the estimation model 22 can be obtained from a questionnaire at a survey site or the like. Furthermore, when the monitor 40 is, for example, a person selected from among people whose attribute information has been registered in advance as described above, the person's attribute information for learning can be obtained from the registered information. can be done.
  • Information on a person's purchase intention which is view information for learning to be learned when the estimation model 22 is generated, and line-of-sight information for learning of the person are information obtained before the estimation model 22 is generated.
  • the line-of-sight information of a person (monitor 40) can be obtained as follows. For example, at the survey site, at least the face of the monitor 40 looking at the products 30 lined up as shown in FIG. Forty line-of-sight information is obtained.
  • the analysis of the photographed image it is possible to acquire the viewing time, the number of viewing times, and the visibility rate regarding the target product for the person (monitor 40) who is viewing the design of the target product. Further, by analyzing the photographed image, as line-of-sight information, the trajectory of the line-of-sight when looking at a plurality of products 30 lined up, the trajectory of the line-of-sight to the product 30 when looking at one product 30, and the line of sight. Partial information can also be acquired.
  • the estimation model 22 is generated by machine learning using graph-based relational learning. For example, based on the information acquired by the site survey, the person (monitor) 40 and the product 30 (package 31) as shown in FIG. A graph (also referred to as a knowledge graph) is generated with edges at the intentions. Then, graph AI (Artificial Intelligence) technology is used to vectorize the nodes and edges of the graph. That is, nodes and edges in the graph are converted into vector representations (embedding vectors). The estimation model 22 is generated by deep learning using the feature vectors of the nodes thus obtained. As shown in FIG.
  • graph AI Artificial Intelligence
  • the estimation model 22 is composed of a model that outputs line-of-sight information and opinion information (purchase intention) in response to input of a design image, and as shown in FIG. In some cases, it is composed of two types of models that respectively output line-of-sight information and opinion information (purchase intention) by inputting an image.
  • the support device 1 may be connected to an external storage device 25 as indicated by the dotted line in FIG. 1, and the estimation model 22 is stored in the storage device 25 instead of the internal storage device 20. may be In this case, the support device 1 can use the estimation model 22 by communicating with the storage device 25 by wire or wirelessly.
  • the computing device 10 of the support device 1 shown in FIG. 1 is composed of a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).
  • the arithmetic device 10 can have various functions by executing a program 21 stored in the storage device 20 by the processor.
  • the arithmetic unit 10 includes an acquisition unit 11, an estimation unit 12, and an output unit 13 as functional units.
  • the acquisition unit 11 acquires the design image of the target product output from the terminal device 3.
  • This acquired design image is, for example, an image representing one candidate for a new package design for a new product or renewed product.
  • the estimation unit 12 uses the design image acquired by the acquisition unit 11 and the estimation model 22 of the storage device 20 to estimate the target person's gaze information and opinion information (purchase intention) with respect to the design of the target product.
  • the estimating unit 12 estimates the design of the target product, which is estimated to be obtained when the target product having, for example, a package design represented in the design image acquired by the acquiring unit 11 is subjected to a site survey. Estimates line-of-sight information and view information of the monitor 40 with respect to .
  • estimation unit 12 stores not only the design image in the estimation model 22, but also node feature vector information obtained from a graph such as that shown in FIG. Result information) may also be input as shown in FIG. This configuration can increase the certainty of estimating line-of-sight information and view information.
  • the output unit 13 outputs line-of-sight information (hereinafter also referred to as estimated line-of-sight information) and opinion information (hereinafter also referred to as estimated opinion information) estimated by the estimation unit 12 .
  • the estimated line-of-sight information estimated by the estimation unit 12 and output by the output unit 13 includes, for example, estimated viewing time information such that the average viewing time for the monitor to view the target product is estimated to be 12 seconds.
  • the estimated line-of-sight information may include information on the estimated number of times of visual recognition, such as the estimated number of times of visual recognition that the target product is viewed by the monitor three times on average.
  • the estimated line-of-sight information may include estimated visibility information, such as an estimated visibility rate of 28% on average.
  • the estimated line-of-sight information may include information representing the groups of the highest number preset in descending order of estimated visual recognition time for viewing the target product, and the estimated visual recognition time for each group.
  • the estimated line-of-sight information shows that the group with the longest estimated visual recognition time is the group that likes fruits, whose estimated visual recognition time is 20 seconds, and the group with the second longest estimated visual recognition time is in their early twenties. It may contain information that it is a group and that its estimated viewing time is about 18 seconds.
  • the estimated line-of-sight information includes, for example, information representing a group of the highest number set in advance in descending order of numerical values. good too. Note that the groups as described above are generated, for example, by the estimation model 22 based on the attribute information and line-of-sight information of the person (monitor 40).
  • two or all of the estimated visual recognition time, the estimated number of visual recognitions, and the estimated visual recognition rate may be included in the estimated line-of-sight information.
  • reference information may be included in the estimated line-of-sight information together with at least one of the estimated viewing time, the estimated number of times of viewing, and the estimated viewing rate.
  • the reference information is information that serves as a reference when a designer or the like evaluates (analyzes) the design of the target product based on the estimated line-of-sight information.
  • the reference information is not particularly limited, but as an example, information representing the average viewing time, the number of times of viewing, and the viewing rate for one product 30 is the average number of samples of the products 30 lined up at the survey site. The information represented with is considered.
  • 35% of the monitors 40 responded that they This is information on estimated purchase intentions such that 25% of the respondents answered that they did not want to purchase the product.
  • 43% of the group who likes fruits have the intention to purchase 43% of the group who likes fruits have the intention to purchase, and 10% of the group who likes alcoholic beverages with an alcohol content of 7% or more are estimated to have the intention to purchase. It may be information.
  • various modes are assumed for the estimated opinion information, and the mode is not limited as long as it includes information on purchase intention based on the design of the target product.
  • FIG. 7 is a diagram showing a display example of estimated line-of-sight information and estimated opinion information on a display device.
  • the design image 38 of the target product is displayed on the screen 37 of the display device along with the estimated line-of-sight information, the estimated opinion information, and the reference information.
  • the estimated line-of-sight information the visual recognition time and information representing the group corresponding to the visual recognition time are displayed in descending order of the visual recognition time from first to third.
  • information of estimated opinion information purchase intention
  • information of purchase intention is displayed by graph for each group.
  • reference information information on the average visual recognition time for one product 30 is displayed.
  • FIG. 8 is a flow chart showing an example of an operation related to estimation of line-of-sight information and opinion information in the computing device 10. As shown in FIG.
  • the acquisition unit 11 of the arithmetic device 10 acquires the design image of the target product (step 101).
  • the estimating unit 12 uses the acquired design image and the estimation model 22 to estimate the target person's line-of-sight information and opinion information regarding the design of the target product (step 102).
  • the output unit 13 outputs the estimated line-of-sight information (estimated line-of-sight information) and opinion information (estimated opinion information) (step 103).
  • the support device 1 uses the design image and the estimation model 22 to obtain the target person's line-of-sight information and opinion regarding the design of the target product. It has a function to estimate information (purchase intention). Since the estimated line-of-sight information and opinion information are information presumed to be obtained when surveys such as venue surveys are conducted, the support device 1 can There is an effect that it is possible to provide information presumed to be obtained from surveys such as site surveys.
  • the support device 1 By using the line-of-sight information and opinion information provided by the support device 1, it is possible to eliminate the need to conduct surveys such as venue surveys, so that the product design (for example, package design) can be determined efficiently, and the product can be It is possible to shorten the time from development to release of new products. That is, the support device 1 according to the first embodiment can favorably support product design (generation).
  • the support device 1 can output line-of-sight information as described above. Since the product design greatly contributes to visually impressing the product, line-of-sight information is effective information for designing the product design.
  • the product design generation support device (support device) 1 of the second embodiment obtains the design image of the target product, and obtains the line-of-sight information and opinion information of the target person on the design of the target product. Estimate and output.
  • the support device 1 outputs not the information of the purchase intention but the text representing the comment on the design of the target product as the opinion information.
  • an estimation model 23 as shown in FIGS. 20 is stored. That is, for example, based on the information acquired by the venue survey, the person (monitor) 40 and the product 30 (package 31) as shown in FIG. A graph is generated with (comment) as an edge. Then, the nodes and edges of the generated graph are vectorized using graph AI technology. An estimation model 23 is generated by deep learning using the feature vectors of the nodes thus obtained. As with the estimation model 22, the estimation model 23 is composed of a model that outputs line-of-sight information and opinion information (comments) upon input of a design image, as shown in FIG.
  • the estimation model 23 is information that expresses comments, which are view information including text, by text, so for example, caption generation technology is used.
  • the estimating unit 12 uses the design image acquired by the acquiring unit 11 and the estimation model 23 in the storage device 20 to use the target person's line-of-sight information and opinion information (comment ).
  • the number of comments as opinion information estimated by the estimation unit 12 is not limited, and may be one or more. As presumed comments, for example, regarding the design of the target product, "The picture is cute”, “The picture matches the image of the taste", "It is difficult to understand whether it is an alcoholic drink or a non-alcoholic drink”. It is textual information.
  • the estimation unit 12 stores not only the design image in the estimation model 23, but also the nodes obtained from the graph shown in FIG. (that is, the information of the survey results) may also be input.
  • the output unit 13 outputs the estimated comment information represented by the text as described above as the estimated opinion information. That is, the output unit 13 outputs the estimated line-of-sight information from the estimation unit 12 and the estimated comment information, which is the estimated opinion information.
  • the estimated line-of-sight information and estimated opinion information output by the output unit 13 are transmitted to the terminal device 3 and displayed on the display device by the display control operation of the terminal device 3, for example, as in the first embodiment.
  • FIG. 12 is a diagram showing a display example of estimated line-of-sight information and estimated opinion information on a display device. In the example of FIG.
  • the screen 37 of the display device displays the design image 38 of the target product, as well as the estimated line-of-sight information, the estimated opinion information, and the reference information.
  • the estimated line-of-sight information the visibility rate and information representing groups corresponding to the visibility rate are displayed in descending order of visibility rate from first to third.
  • the estimated opinion information (estimated comment) information comments are displayed in text for each group.
  • reference information information on the average visibility rate for one product 30 is displayed.
  • the configuration of the support device 1 of the second embodiment other than the above is the same as that of the first embodiment.
  • the support device 1 of the second embodiment uses the design image and the estimation model 23 to obtain the line-of-sight information and opinion information (comment) of the target person on the design of the target product. It has a function to estimate. Since the estimated line-of-sight information and opinion information are information estimated to be obtained from surveys such as venue surveys, the support device 1 of the second embodiment can also It is possible to provide information presumed to be obtained from surveys such as venue surveys without actually conducting surveys. As a result, the support device 1 of the second embodiment can favorably support product design.
  • the product design generation support device (support device) 1 of the third embodiment has the configuration described below, and the rest of the configuration is the same as that of the support device 1 of the first or second embodiment.
  • the support device 1 of the third embodiment has a configuration for estimating and outputting line-of-sight information and opinion information regarding a target person more limited than those of the first and second embodiments.
  • the target person may be, for example, a venue survey monitor.
  • the specified person is a person in their twenties or a person who likes beer.
  • target person attribute information as information used for specifying such a target person is transmitted from the terminal device 3 to the support device 1, for example.
  • the acquisition unit 11 acquires target person attribute information in addition to the design image of the target product.
  • the target person attribute information is, as described above, information used to identify the target person, and an example of the target person attribute information is information representing the customer group (in other words, target group) to whom the target product is mainly sold. is mentioned.
  • the target person in the third embodiment is not limited to the target demographic, and may be, for example, a person in their twenties, a person who likes beer, or a person who has an attribute to be investigated. is.
  • the acquisition unit 11 acquires attribute information (that is, target person attribute information) specifying such a person to be investigated.
  • target person attribute information examples include age, lifestyle information (e.g., information on meals such as the number of meals per day and meal times, amount of exercise in a week, sleep time, wake-up time, and bedtime). , commuting time), preference information, and hobbies.
  • lifestyle information e.g., information on meals such as the number of meals per day and meal times, amount of exercise in a week, sleep time, wake-up time, and bedtime.
  • commuting time preference information
  • hobbies hobbies.
  • the estimation unit 12 estimates line-of-sight information and opinion information of the target person specified by the target person attribute information based on the acquired design image of the target product, the target person attribute information, and the estimation model 22 or the estimation model 23. do.
  • the output unit 13 outputs estimated line-of-sight information and estimated opinion information regarding the specified target person.
  • the support device 1 of the third embodiment like the support device 1 of the first or second embodiment, has a configuration capable of estimating and outputting line-of-sight information and opinion information of the target person with respect to the design of the target product. Therefore, the same effect as the support device 1 of the first or second embodiment is obtained.
  • the support device 1 of the third embodiment can output estimated line-of-sight information and estimated opinion information about a limited target person.
  • the support device 1 of the third embodiment can provide more effective information for product design (package design) for which the target demographic is determined.
  • a product design generation support device (support device) 1 according to the fourth embodiment further outputs an estimated reason for the estimated opinion information in addition to the support device 1 according to any one of the first to third embodiments. That is, in the fourth embodiment, the estimation unit 12 estimates line-of-sight information and opinion information, and further estimates an estimation reason for the estimated opinion information based on the line-of-sight information.
  • the presumed reason of the presumed view information is the reason (basis) for presuming the view indicated as the view information. For example, it is assumed that the result of estimation of line-of-sight information and opinion information by the estimation unit 12 is as follows. ⁇ Estimation result > ⁇ Gaze information: The visual recognition time of the group who likes fruits is 15 seconds, which is longer than the average visual recognition time.
  • the estimation unit 12 outputs the following reason for estimation, for example.
  • ⁇ Estimated reason > It is presumed that the reason why the fruit-loving group has a high purchase intention is that they liked the product design based on the fact that the viewing time was longer than the average viewing time.
  • the output unit 13 outputs the estimated line-of-sight information, the estimated opinion information, and the reason for the estimation by the estimation unit 12 .
  • the estimated line-of-sight information, the estimated opinion information, and the estimated reason output by the output unit 13 in this way are transmitted to the terminal device 3, for example, in the same manner as in the above-described embodiment, and displayed on the display device by the display control operation of the terminal device 3. Is displayed.
  • FIG. 13 is a diagram showing a display example of estimated line-of-sight information, estimated opinion information, and an estimated reason on a display device. In the example of FIG.
  • the design image 38 of the target product is displayed on the screen 37 of the display device, as well as the estimated line-of-sight information, the estimated opinion information, and the reference information, as in FIG. 7 described above. Furthermore, in the area where the opinion information is displayed, an estimated reason for the opinion designated by the pointer 39 is popped up.
  • the configuration of the support device 1 of the fourth embodiment other than the above is the same as that of the support device 1 of the first, second, or third embodiment.
  • the support device 1 of the fourth embodiment outputs an estimated reason in addition to the support device 1 of any one of the first to third embodiments.
  • the support device 1 of the fourth embodiment can achieve the same effects as those of the first to third embodiments, and can facilitate the interpretation of the estimated line-of-sight information and the estimated opinion information depending on the estimated reason. It has the effect of being able to As described above, the reason for the estimation is information that allows the estimated line-of-sight information and the estimated opinion information to be used more effectively because the estimated line-of-sight information and the estimated opinion information can be easily interpreted.
  • the product design generation support device (support device) 1 of the fifth embodiment estimates and outputs the line-of-sight information and opinion information of the target person with respect to the design of the target product.
  • the product information to be learned includes, for example, the information shown in FIG.
  • the information of the display position displayed on the shelf 35 is included.
  • the display position information is, for example, shelf position information expressed as the right end of the top shelf or the center of the third shelf from the top.
  • the input of the estimation models 22 and 23 includes, in addition to the design image of the target product, information on the display position of the shelf 35 where the target product is supposed to be placed as target product attribute information. . Further, the outputs of the estimation models 22 and 23 are the line-of-sight information and opinion information of the target person estimated with respect to the design of the target product also using the shelf position information of the target product.
  • the design image of the target product and the display position (shelf position information) of the target product on the shelf 35, which is the target product attribute information are transmitted from the terminal device 3 to the support device 1.
  • the acquisition unit 11 of the support device 1 acquires the design images of the target products and the target product attribute information.
  • the estimating unit 12 uses the acquired design image of the target product, the target product attribute information, and the estimation models 22 and 23 to estimate line-of-sight information and opinion information of the target person with respect to the design of the target product.
  • the estimated line-of-sight information includes, for example, an estimated viewing time such that the viewing time for the monitor to view the target product placed on the right end of the top row is estimated to be 8 seconds.
  • the estimated line-of-sight information includes at least one of an estimated viewing time, an estimated viewing count, and an estimated viewing rate.
  • purchase intention information such that 30% of the monitors 40 are estimated to answer that they would like to purchase the design of the target product placed on the right end of the top row.
  • information of a text comment such as "the color is sober and inconspicuous" is included.
  • the acquisition unit 11 limits the target person with the design image of the target product, the target product attribute information (shelf position information), and the target person. Acquire target person attribute information.
  • the estimating unit 12 uses the design image of the target product, the target product attribute information (shelf position information), the target person attribute information, and the estimation models 22 and 23 to estimate the limited target person for the design of the target product. Estimate gaze and view information.
  • the configuration of the support device 1 of the fifth embodiment other than the above is the same as those of the first to fourth embodiments.
  • the support device 1 of the fifth embodiment has effects similar to those of the first to fourth embodiments.
  • the support device 1 of the fifth embodiment having the configuration as described above, can output line-of-sight information and opinion information of the target person in consideration of the manner in which the target product is sold. Such information is also very effective information for designing the design of the target product.
  • the acquisition unit 11 acquires a plurality of design images representing different designs.
  • the plurality of design images may be images (candidate images) representing mutually different design candidates for the same target product (for example, the same canned beverage), or mutually different target products (for example, canned beverages with different tastes). There may be images representing different designs for each.
  • the estimation unit 12 estimates line-of-sight information and opinion information of the target person using estimation models 22 and 23 for each of a plurality of design images.
  • the estimation unit 12 further ranks the designs of the plurality of design images based on one or both of the estimated line-of-sight information and opinion information. For example, assume that the estimating unit 12 estimates line-of-sight information and opinion information (for example, purchase intention information) regarding design images representing 10 types of designs A to J, respectively. Based on the visibility rate of the estimated line-of-sight information, the designs A to J are ranked 1st to 10th in descending order of numerical value.
  • Designs A to J ranked 1st to 10th in descending order of numerical values (values representing ratios) representing estimated purchase intentions, such as 55% of monitors 40 answering that they would like to purchase. attached to. Furthermore, when the designs are ranked using both the estimated line-of-sight information and the estimated purchase intention, for example, the visibility rate of each of designs A to J is converted into a visibility score according to a predetermined visibility rate conversion method. be. Numerical values representing purchase intentions of designs A to J are converted into purchase intention scores based on a previously given purchase intention conversion method. Designs A to J are ranked 1st to 10th in descending order of the total score obtained by summing the visual recognition score and the purchase intention score, for example.
  • the output unit 13 outputs the estimated line-of-sight information and the estimated opinion information of the target person for the design represented in each of the plurality of design images acquired by the acquisition unit 11, and outputs either the estimated line-of-sight information or the estimated opinion information, or Output ranking information representing the ranking of the design based on both. That is, the output unit 13 may output ranking information including one or both of the ranking of designs based on the estimated line-of-sight information and the ranking of designs based on the estimated line-of-sight information. The ranking of designs based on both pieces of estimated opinion information may be output as ranking information.
  • FIG. 15 shows an example of the display on the display device by the display control operation of the terminal device 3 that has also received such design ranking information. In the example of FIG. 15, the design of the target product is displayed together with information on its ranking.
  • the support device 1 of the sixth embodiment has effects similar to those of the first to fifth embodiments.
  • the support device 1 of the sixth embodiment is provided with the above-described configuration, it is important for designing products such as line-of-sight information and opinion information of a target person regarding a plurality of designs to be compared. It can provide ranking information based on what to do.
  • the estimation unit 12 estimates one of purchase intention information and comment information as opinion information.
  • the estimation unit 12 may estimate opinion information including both purchase intention information and comment information by using an estimation model 24 as shown in FIG. .
  • the estimation model 24 is composed of three types of models that output line-of-sight information and purchase intention and comments, which are view information, respectively, by inputting a design image.
  • the package design is used as an example of product design, and the support device 1 is described.
  • the design is not limited, and may be, for example, a design of an object contained in a package, or a design of a product itself without a package.
  • the line-of-sight information and opinion information used to generate the estimation models 22 and 23 are obtained through site surveys. Alternatively, such line-of-sight information and opinion information may be obtained, for example, through a questionnaire survey on the street. In this case as well, the line-of-sight information of a person can be obtained from a photographed image (or a photographed moving image) of a person answering a questionnaire taken by the photographing device in the same manner as described above. Furthermore, in the first to sixth embodiments, line-of-sight information when a person directly looks at the product 30 and opinion information when the person directly looks at the product 30 are used.
  • line-of-sight information when the target person is looking at the product 30 listed in advertisements in newspapers, magazines, television and websites, advertisements in public transportation, and such advertisements Opinion information based on the target person's viewing of the product 30 listed in the article may be used.
  • the estimation models 22 and 23 may be generated using line-of-sight information and opinion information obtained when the product 30 is viewed directly and line-of-sight information and opinion information obtained by viewing the product 30 from advertisements, etc. good. In this way, acquisition of line-of-sight information and opinion information used to generate the estimation models 22 and 23 is not limited to venue surveys.
  • the support device 1 of the first to sixth embodiments may construct a product design generation support system together with the connected terminal device 3, for example.
  • FIG. 17 is a block diagram showing the minimum configuration of the product design generation support device.
  • This product design generation support device 50 includes an acquisition unit 51 , an estimation unit 52 and an output unit 53 .
  • the product design generation support device 50 is, for example, a computer device, and implements an acquisition unit 51, an estimation unit 52, and an output unit 53 as in the first to sixth embodiments.
  • the acquisition unit 51 acquires a design image related to the design of the target product.
  • the estimation unit 52 estimates line-of-sight information and opinion information of the target person with respect to the design of the target product using the design image and the estimation model.
  • the estimation model includes product information for learning including product design images, attribute information for learning of a person, line-of-sight information for learning a person for a product design, and view information for learning a person for a product design, It is a model that learns the relationship between
  • the output unit 53 outputs the line-of-sight information and opinion information estimated by the estimation unit 52 .
  • FIG. 18 is a flow chart explaining an example of the operation of the product design generation support device 50.
  • the acquisition unit 51 acquires a design image related to the design of the target product (step 201).
  • the estimation unit 52 estimates the target person's line-of-sight information and opinion information regarding the design of the target product using the design image and the estimation model (step 202).
  • the output unit 53 outputs the estimated line-of-sight information and opinion information (step 203).
  • the product design generation support device 50 has the effect of being able to efficiently generate and present information that is effective in designing and determining product designs.
  • (Appendix 1) Acquisition means for acquiring a design image related to the design of the target product; estimation means for estimating line-of-sight information and opinion information of a target person with respect to the design of the target product using the design image and the estimation model; output means for outputting the line-of-sight information and the view information; with
  • the estimation model includes product information for learning including product design images and attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information for learning the person for the design of the product.
  • Product design generation support device which is a model that has learned the relationship between the opinion information of (Appendix 2)
  • the estimating means further estimates a reason for estimating the opinion information based on the line-of-sight information
  • Appendix 3 2.
  • Appendix 4) 3.
  • the acquisition means further acquires target product attribute information about the target product and target person attribute information about the target person
  • the estimation means estimates the opinion information on the design of the target product using the design image, the target person attribute information, the target product attribute information, and the estimation model,
  • the product design generation support device according to any one of appendices 1 to 5, wherein the output means outputs the opinion information.
  • the target product is a product displayed on a shelf
  • the product design generation support device according to appendix 6, wherein the target product attribute information includes a display position of the target product on the shelf.
  • the target person attribute information is an attribute of a target person having a specific attribute
  • the product design generation support device according to appendix 6 or appendix 7, wherein the estimation means estimates the opinion information and the line-of-sight information on the design of the target product of the target person having the specific attribute.
  • the acquiring means acquires a plurality of design images representing designs different from each other, The estimating means estimates the view information and the line-of-sight information for the design represented in each of the plurality of design images, 9.
  • the product design generation support device according to any one of appendices 1 to 8, wherein the output means further outputs the order of the designs based on at least one of the opinion information and the line-of-sight information.
  • the estimation model includes product information for learning including product design images and attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information for learning the person for the design of the product.
  • product design generation support system which is a model that has learned the relationship between (Appendix 11) by computer, Acquire a design image related to the design of the target product, estimating gaze information and opinion information of the target person with respect to the design of the target product using the design image and the estimation model; outputting the line-of-sight information and the view information;
  • the estimation model includes product information for learning including a design image of a product, attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information on the person for the design of the product for learning.
  • a product design generation support method which is a model that has learned the relationship between opinion information for learning and.
  • (Appendix 12) A process of acquiring a design image related to the design of the target product; a process of estimating line-of-sight information and opinion information of a target person with respect to the design of the target product using the design image and the estimation model; storing a computer program that causes a computer to execute a process of outputting the line-of-sight information and the view information;
  • the estimation model includes product information for learning including a design image of a product, attribute information for learning of a person, line-of-sight information for learning of the person for the design of the product, and information on the person for the design of the product for learning.
  • a program storage medium that is a model that has learned the relationship between the view information for learning and.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2021/013818 2021-03-31 2021-03-31 商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体 Ceased WO2022208718A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2021/013818 WO2022208718A1 (ja) 2021-03-31 2021-03-31 商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体
US18/274,657 US20240095798A1 (en) 2021-03-31 2021-03-31 Product design generation support device, product design generation support method and computer readable medium
JP2023510013A JP7485203B2 (ja) 2021-03-31 2021-03-31 商品デザイン生成支援装置、商品デザイン生成支援方法およびコンピュータプログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/013818 WO2022208718A1 (ja) 2021-03-31 2021-03-31 商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体

Publications (1)

Publication Number Publication Date
WO2022208718A1 true WO2022208718A1 (ja) 2022-10-06

Family

ID=83458199

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/013818 Ceased WO2022208718A1 (ja) 2021-03-31 2021-03-31 商品デザイン生成支援装置、商品デザイン生成支援方法およびプログラム記憶媒体

Country Status (3)

Country Link
US (1) US20240095798A1 (https=)
JP (1) JP7485203B2 (https=)
WO (1) WO2022208718A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024083601A (ja) * 2019-06-18 2024-06-21 Ｔｏｐｐａｎホールディングス株式会社 検出支援装置、学習装置、検出支援方法、学習方法、及びプログラム

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015125541A (ja) * 2013-12-26 2015-07-06 スリーエム イノベイティブ プロパティズ カンパニー 視線予測システム、視線予測方法、および視線予測プログラム
JP2018136604A (ja) * 2017-02-20 2018-08-30 株式会社マクロミル 評価システム
WO2021009880A1 (ja) * 2019-07-17 2021-01-21 株式会社アシックス デザイン支援装置及びデザイン支援方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015125541A (ja) * 2013-12-26 2015-07-06 スリーエム イノベイティブ プロパティズ カンパニー 視線予測システム、視線予測方法、および視線予測プログラム
JP2018136604A (ja) * 2017-02-20 2018-08-30 株式会社マクロミル 評価システム
WO2021009880A1 (ja) * 2019-07-17 2021-01-21 株式会社アシックス デザイン支援装置及びデザイン支援方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024083601A (ja) * 2019-06-18 2024-06-21 Ｔｏｐｐａｎホールディングス株式会社 検出支援装置、学習装置、検出支援方法、学習方法、及びプログラム
JP7658493B2 (ja) 2019-06-18 2025-04-08 Ｔｏｐｐａｎホールディングス株式会社 検出支援装置、学習装置、検出支援方法、学習方法、及びプログラム

Also Published As

Publication number Publication date
JP7485203B2 (ja) 2024-05-16
US20240095798A1 (en) 2024-03-21
JPWO2022208718A1 (https=) 2022-10-06

Similar Documents

Publication Publication Date Title
dos Santos et al. Eye tracking in neuromarketing: a research agenda for marketing studies
US20100017265A1 (en) System and method for product purchase recommendation
US10354131B2 (en) Product information outputting method, control device, and computer-readable recording medium
Vergura et al. Product packaging and consumers’ emotional response. Does spatial representation influence product evaluation and choice?
US20250005868A1 (en) System and method for generating a virtual overlay in an xr environment
US20130046620A1 (en) Fast and Versatile Graphical Scoring Device and Method, and of Providing Advertising Based Thereon
Modi et al. An analysis of perfume packaging designs on consumer’s cognitive and emotional behavior using eye gaze tracking
Shin et al. What motivates US restaurant customers to choose plant-based meat alternative dishes?
Retamosa et al. Displaying ingredients on healthy snack packaging: A study on visual attention, choice, and purchase intention
JP7485203B2 (ja) 商品デザイン生成支援装置、商品デザイン生成支援方法およびコンピュータプログラム
Van De Sanden et al. Digital signage in the store atmosphere: balancing gains and pains
Kumar et al. Neuromarketing: a new agenda for marketing researches with particular reference to eye tracking
JP4886940B2 (ja) 因子データベースを用いたマッチング・システム、マッチング装置、およびそのシステムのための因子データベース作成方法
WO2015173872A1 (ja) 商品情報表示システム、制御装置、制御プログラムおよび制御方法
Katare et al. Novel approaches to analyze consumer behavior and policies to promote sustainable consumption
Peters et al. The role of dynamic digital menu boards in consumer decision making
Salehi et al. Application of eye-tracking in assessing the role of mediator variable (brand awareness) in the relation between packaging elements and customers' choice
Nasidi Luring the undecided: factors that influence purchasing behaviour
Qi Role of live e-commerce on consumer purchase intentions
JP7042787B2 (ja) 判定装置、判定方法、および判定プログラム
JP7552873B2 (ja) 商品デザイン生成支援装置、商品デザイン生成支援方法、商品デザイン生成支援システムおよびコンピュータプログラム
US20240095786A1 (en) Product design generation support device, product design generation support method, and program storage medium
Novak Ubiquitous computing and socially aware consumer support systems in the augmented supermarket
Sharma Consumer behavior and RTE: Market adaptability and Likeness preference terms
TWI886424B (zh) 電子看板分眾行銷方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21934887

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023510013

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 18274657

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21934887

Country of ref document: EP

Kind code of ref document: A1