CN113592573A - Information recommendation device, information recommendation method, and storage medium - Google Patents

Abstract

The invention provides an information recommendation device, an information recommendation method and a storage medium, which can recommend information corresponding to the preference of a user and provide personalized purchase experience close to the user. The information recommendation device is provided with: an acquisition unit that acquires a movement history of a line of sight of a user with respect to a commodity and a purchase history of the commodity of the user; a calculation unit that calculates a preference degree indicating a preference degree of a user for a commodity based on the movement history and the purchase history; and a recommendation unit that recommends a recipe using at least one product having a preference degree greater than or equal to a predetermined value.

Description

Information recommendation device, information recommendation method, and storage medium

Technical Field

The invention relates to an information recommendation device, an information recommendation method and a storage medium.

Background

A technique is known in which recipes using products to be purchased by a user are recommended in stores such as retail stores.

For example, patent document 1 describes an information providing device capable of providing information that is valuable to shoppers.

Patent document 1: japanese laid-open patent publication No. 2012-168836

The preference of the goods is different for each user. Therefore, a technique capable of recommending recipes according to the preference of the user is desired.

Disclosure of Invention

An object of the present invention is to provide an information recommendation device, an information recommendation method, and a storage medium that can recommend information corresponding to user preferences and provide a personalized purchase experience close to the user.

An information recommendation device according to an aspect of the present invention includes: an acquisition unit that acquires a movement history of a line of sight of a user with respect to a commodity and a purchase history of the commodity of the user; a calculation unit that calculates a preference degree indicating a preference degree of the user for a product based on the movement history and the purchase history; and a recommendation unit configured to recommend a recipe using at least one product having the preference degree equal to or higher than a predetermined value.

An information recommendation method according to an aspect of the present invention includes the steps of: acquiring the movement history of the sight of a user to a commodity and the purchase history of the commodity of the user; calculating a preference degree indicating a preference degree of the user for the commodity based on the movement history and the purchase history; and recommending a recipe using at least one product having the preference degree of at least a predetermined value.

A storage medium according to an aspect of the present invention stores a program for causing a computer to execute: acquiring the movement history of the sight of a user to a commodity and the purchase history of the commodity of the user; calculating a preference degree indicating a preference degree of the user for the commodity based on the movement history and the purchase history; and recommending a recipe using at least one product having the preference degree of at least a predetermined value.

Effects of the invention

According to the invention, information corresponding to the preference of the user can be recommended, and personalized purchasing experience close to the user can be improved.

Drawings

Fig. 1 is a diagram showing a configuration example of an information recommendation system according to a first embodiment.

Fig. 2 is a block diagram showing a configuration example of the information recommendation device according to the first embodiment.

Fig. 3 is a diagram showing an example of installation of the information recommendation apparatus according to the first embodiment.

Fig. 4 is a block diagram showing a configuration example of the server device according to the first embodiment.

Fig. 5 is a flowchart showing an example of the flow of the recipe recommendation processing according to the first embodiment.

Fig. 6A is a diagram for explaining a method of calculating the preference degree based on the accumulated gaze time.

Fig. 6B is a diagram for explaining a method of calculating the preference based on the number of times of shopping at which attention is paid.

Fig. 6C is a diagram for explaining a method of calculating the preference based on the ratio of the number of times of shopping at which attention is paid to the predetermined number of times of shopping.

Fig. 6D is a diagram for explaining a method of calculating the degree of attention.

Fig. 6E is a diagram showing a relationship between the degree of attention and the number of times of shopping.

Fig. 7 is a diagram showing an example of a recipe display screen.

Fig. 8 is a diagram showing an example of a recipe detail screen.

Fig. 9 is a flowchart showing an example of the flow of the recipe recommendation processing according to the second embodiment.

Fig. 10 is a flowchart showing an example of the flow of the recipe recommendation processing according to the third embodiment.

Fig. 11 is a diagram showing an example of a recipe display screen.

Fig. 12 is a flowchart showing an example of the flow of the recipe recommendation processing according to the fourth embodiment.

Fig. 13 is a block diagram showing a configuration example of an information recommendation device according to the fifth embodiment.

Fig. 14 is a flowchart showing an example of the flow of the recipe recommendation processing according to the fifth embodiment.

Fig. 15 is a diagram showing a configuration example of an information recommendation system according to a sixth embodiment.

Fig. 16 is a block diagram showing a configuration example of an information recommendation device according to the sixth embodiment.

Fig. 17 is a flowchart showing an example of the flow of the recipe recommendation processing according to the sixth embodiment.

Fig. 18 is a flowchart showing an example of the flow of the route guidance processing to the product.

Fig. 19 is a diagram showing an example of a suggested product display screen.

Description of the reference symbols

1. 1A information recommendation system

100. 100A, 100B information recommendation device

110 camera

120 operating part

130 display part

140. 210 communication unit

150. 220 storage part

151 line of sight history information

152 purchase history information

153 recipe information

160. 230 control part

161. 161A acquisition unit

162 calculating part

163. 163A recommendation part

164 line of sight detection unit

165 commodity recognition unit

166 user identification part

167 guide part

200 server device

600 shop server device

Detailed Description

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that the present invention should not be limited to this embodiment, and when there are a plurality of embodiments, the present invention also includes an embodiment configured by combining the respective embodiments. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description thereof is omitted.

[ first embodiment ]

[ information recommendation System ]

The configuration of the information recommendation system according to the first embodiment will be described with reference to fig. 1. Fig. 1 is a diagram showing a configuration example of an information recommendation system according to a first embodiment.

As shown in fig. 1, the information recommendation system 1 includes an information recommendation device 100 and a server device 200. The information recommendation device 100 and the server device 200 are connected to each other so as to be able to communicate with each other via a wireless network N, for example. The information recommendation system 1 may include a plurality of information recommendation devices 100 and a plurality of server devices 200.

The information recommendation apparatus 100 performs processing for recommending various recipes to the user. The information recommendation device 100 recommends recipes to the user based on line-of-sight history information including the movement history of the line of sight of the user with respect to the product and purchase history information including the purchase history of the product of the user. The server apparatus 200 stores sight line history information and purchase history information of a plurality of users. The information recommendation device 100 transmits and receives various information related to the recipe of the user to and from the server device 200.

[ information recommendation device ]

The configuration of the information recommendation device according to the first embodiment will be described with reference to fig. 2 and 3. Fig. 2 is a block diagram showing a configuration example of the information recommendation device according to the first embodiment. Fig. 3 is a diagram showing an example of installation of the information recommendation apparatus according to the first embodiment.

As shown in fig. 2, the information recommendation device 100 includes a camera 110, an operation unit 120, a display unit 130, a communication unit 140, a storage unit 150, and a control unit 160. As shown in fig. 3, the information recommendation device 100 is disposed in a shopping cart C, for example. The information recommendation device 100 is configured to be able to photograph the items and the user U in the shopping cart C. The information recommendation apparatus 100 recommends recipes based on, for example, line-of-sight history information and purchase history information of the user U as a shopping guest. The information recommendation device 100 may be provided in, for example, a shopping basket or the like in which a product is temporarily placed until the product is purchased in a store.

The camera 110 captures various subjects. The camera 110 photographs, for example, an article that the user U intends to purchase. The items scheduled for purchase are, for example, items in the shopping cart C. The camera 110 photographs, for example, the face of the user U. The camera 110 photographs, for example, clothing of the user U. For example, a plurality of cameras 110 may be included, and the items in the shopping cart C and the user U may be photographed by the plurality of cameras 110.

The operation unit 120 receives various operations for the information recommendation device 100. The operation unit 120 receives, for example, an operation of selecting a recommended recipe by the user U. The operation unit 120 receives, for example, an operation for displaying the details of a recipe or an operation for not displaying a recommended recipe. The operation unit 120 receives an operation of the user U to input favorite food, unpleasant food, and sensitive food, for example. The operation unit 120 receives, for example, an operation of the user U inputting the degree of cooking by the user U indicating the frequency of cooking by the user U and the cooking skill. The operation unit 120 can be realized by, for example, a button, a switch, or a touch panel.

The display unit 130 displays various images. The display unit 130 displays, for example, recipes. The Display unit 130 is a Display panel including, for example, a Liquid Crystal Display (LCD) or an organic EL (Electro-Luminescence) Display. When the operation unit 120 includes a touch panel, the display unit 130 is integrally configured with the touch panel.

The communication unit 140 wirelessly communicates with an external device such as the server device 200 via the network N. The communication unit 140 is realized by, for example, an NIC (Network Interface Card) or the like. The network N may be a public communication network such as the internet or a telephone line network. The Network N may be a communication Network such as a Local Area Network (LAN) provided in a limited Area (for example, in a store).

The storage unit 150 stores various information. The storage unit 150 stores various programs, settings, and the like, for example. The storage unit 150 is implemented by, for example, a semiconductor Memory element such as a RAM (Random Access Memory) or a Flash Memory, or a storage device such as a hard disk or an optical disk. The information stored in the storage unit 150 includes line-of-sight history information 151, purchase history information 152, and recipe information 153.

The line-of-sight history information 151 includes information related to the history of the line of sight of the user U to the commodity. The sight line history information 151 includes information related to the history of movement of the user U's sight line toward the commodity. The line-of-sight history information 151 includes, for example, information related to the time at which the user U gazes at a predetermined product (for example, product a). The line-of-sight history information 151 includes, for example, information related to the number of times the user U has looked at the article a for a predetermined time or longer. The line-of-sight history information 151 includes, for example, information related to the accumulated gaze time of the user U for the article a.

The purchase history information 152 includes information related to the purchase history of the commodities of the user U.

The purchase history information 152 includes, for example, information related to the number of times of purchase of the article a by the user U. The purchase history information 152 includes, for example, information related to the number of purchases of the product a by the user U. The purchase history information 152 includes, for example, information related to the price of the item purchased by the user U.

The recipe information 153 includes various information related to recipes. The recipe information 153 includes information on a desired food material, seasoning, and the like, for example. The recipe information 153 includes information related to cooking tools, cooking steps, and the like, for example.

The line of sight history information 151 and the purchase history information 152 may be stored in a terminal device such as a smartphone owned by the user U, for example, via the communication unit 140.

The control Unit 160 is realized by causing a program (for example, a program according to the present invention) stored in a storage Unit (not shown) to be executed as a work area, such as a RAM, by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, for example. The control unit 160 is a controller, and is implemented by an Integrated Circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 160 may be implemented by a combination of software and hardware.

The control unit 160 includes an acquisition unit 161, a calculation unit 162, a recommendation unit 163, a line-of-sight detection unit 164, a product identification unit 165, and a user identification unit 166.

The acquisition section 161 acquires various information. The acquisition unit 161 acquires line-of-sight history information 151 including a history of movement of the line of sight of the user U with respect to the product from the storage unit 150. The acquisition unit 161 acquires the purchase history information 152 including the purchase history of the product of the user U from the storage unit 150. The acquisition unit 161 acquires the recipe information 153 from the storage unit 150. The acquisition unit 161 may acquire the line-of-sight history information, the purchase history information, and the recipe information from the server apparatus 200 via the communication unit 140.

The calculation unit 162 calculates various information. The calculation unit 162 calculates a preference degree indicating a preference degree of the user U for the product based on the line-of-sight history information and the purchase history information. The calculation unit 162 calculates the preference degree of the product with longer fixation time based on the sight line history information. The calculation unit 162 calculates the preference degree of the product having a larger number of fixation times based on the line-of-sight history information. The calculation unit 162 calculates the preference degree of the product having the larger number of purchases based on the purchase history information. The calculation unit 162 calculates the preference degrees in 10-level numerical values, such as "1", "2", "3", "4", "5", "6", "7", "8", "9", and "10", for example. In this case, the higher the value, the higher the preference for the product. For example, it means that the item having the preference degree exceeding "5" is a favorite item of the user U, and the item having the preference degree below "5" is a favorite item of the user U. The calculation unit 162 may calculate the preference degree by a method different from numerical values, such as "favorite", "general", and "unpleasant".

The calculation unit 162 calculates the degree of attention based on the line of sight of the user U to the product being purchased, which is detected by the line of sight detection unit 164. The calculation unit 162 calculates the degree of attention so that the longer the attention of the product is, for example. The calculation unit 162 calculates the higher the attention of the product with a larger number of attentions. The calculation unit 162 calculates the attention degree in 10-degree numerical values, such as "1", "2", "3", "4", "5", "6", "7", "8", "9", and "10", for example. In this case, the higher the value, the higher the attention to the product. For example, it means that a product having a degree of attention exceeding "5" is a product in which the user U is interested, and a product having a degree of attention lower than "5" is a product in which the user U is not interested. The calculation unit 162 may calculate the attention degree by a method different from numerical values, such as "interested", "general", and "uninteresting".

The calculation unit 162 may calculate the user preference and attention for each season and temperature, for example. The calculation unit 162 may calculate the preference and the attention of the same product during spring, summer, autumn, and winter, for example. The calculation unit 162 may calculate the preference and the attention at the air temperatures of 10 ℃, 15 ℃, 20 ℃ and 25 ℃ for the same product, for example. In other words, the calculation unit 162 may calculate the change of the preference and the attention with respect to the change of the season and the temperature for the same product.

The calculation unit 162 calculates a representative value of the purchase price of the product in a predetermined period based on the purchase history information. As the representative value, for example, statistical values such as an average value, a median value, a mode, a maximum value, and a minimum value are exemplified. The calculation unit 162 calculates the total purchase price of each product in a predetermined period based on the purchase history information. The calculation unit 162 calculates the number of purchases of each product in a predetermined period based on the purchase history information.

The recommendation unit 163 recommends various information. The recommendation unit 163 recommends, for example, a recipe using at least one product having a preference degree equal to or higher than a predetermined value. The recommendation unit 163 recommends, for example, a recipe using at least one product having a preference degree of not less than a predetermined degree and at least one product having an attention degree of not less than a predetermined degree. The recommendation unit 163 recommends, for example, a recipe using at least one product identified by the product identification unit 165 and at least one product having a preference degree equal to or higher than a predetermined value. The recommendation unit 163 recommends a recipe using at least one product identified by the product identification unit 165, at least one product having a preference degree of not less than a predetermined degree, and at least one product having an attention degree of not less than a predetermined degree, for example. The recommending unit 163 recommends, for example, a recipe using at least one product having a preference degree equal to or higher than a predetermined value and having a selling price lower than the representative value. The recommending unit 163 may recommend a preset normal recipe (e.g., curry) or may not recommend a recipe when the line-of-sight history information and the purchase history information do not exist. The recommending unit 163 may recommend a recipe corresponding to the food input by the user when the user U inputs a favorite food, a disliked food, and an allergic food to the operation unit. The recommending unit 163 may change the recommended recipe according to the degree of cooking when the user U inputs the degree of cooking to the operating unit 120.

The line-of-sight detecting unit 164 detects the line of sight of the user U. The line-of-sight detecting unit 164 detects the direction of the line of sight of the user U based on, for example, image data of the face of the user U captured by the camera 110. The line-of-sight detecting unit 164 detects that the user U is looking at a predetermined product. The line-of-sight detecting unit 164 detects a time when the user U watches a predetermined product. The line-of-sight detecting unit 164 may detect the line of sight of the user U based on image data of the user U and the product captured by a camera provided in the store, for example. The line-of-sight detecting unit 164 stores the detected various information in the storage unit 150 as line-of-sight history information 151.

The article recognition unit 165 recognizes various articles. The product recognition unit 165 recognizes a product to be purchased by the user U by performing object recognition processing using dictionary data, not shown, on image data of the product to be purchased of the user U captured by the camera 110, for example. The product recognition unit 165 stores, for example, information on the history of products purchased by the user U in the storage unit 150 as the purchase history information 152. The purchase history information 152 may be acquired from, for example, a POS (Point Of Sale) terminal device or the like used at the time Of product settlement.

The user identification unit 166 identifies the user U who uses the information recommendation device 100. The user recognition unit 166 recognizes the user U based on, for example, a predetermined operation (for example, input of a password) received from the user U by the operation unit 120. The user recognition unit 166 may also perform a known face authentication process based on image data of the face of the user U acquired by the camera 110, for example, to recognize the user U. The user identification unit 166 may identify the user U based on identification information received by the communication unit 140 from a terminal device of the user U, an RFID (Radio Frequency Identifier), or the like, for example.

[ Server device ]

The configuration of the server device according to the first embodiment will be described with reference to fig. 4. Fig. 4 is a block diagram showing a configuration example of the server device according to the first embodiment.

As shown in fig. 4, the server device 200 includes a communication unit 210, a storage unit 220, and a control unit 230.

The communication unit 210 wirelessly communicates with an external device such as the information recommendation device 100 via the network N. The communication unit 140 is implemented by, for example, a NIC.

The storage unit 220 stores various information. The storage unit 220 stores various programs, settings, and the like, for example. The storage unit 220 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 220 includes a line-of-sight history information database 221, a purchase history information database 222, and recipe information 223.

The line-of-sight history information database 221 includes information relating to histories of line-of-sight of a plurality of users with respect to commodities. The sight line history information database 221 includes, for example, information related to the history of movement of the sight lines of the plurality of users toward the commodity. The line-of-sight history information database 221 includes, for example, information related to times at which a plurality of users gazed at the article a. The line-of-sight history information database 221 includes, for example, information related to the number of times that a plurality of users gaze at the product a for a predetermined time or longer. The line-of-sight history information database 221 includes, for example, information related to cumulative gaze times of a plurality of users for the article a.

The purchase history information database 222 includes information related to the purchase history of the commodities of the plurality of users. The purchase history information database 222 includes, for example, information related to the number of purchases of the commodities of the plurality of users. The purchase history information database 222 includes information relating to the number of purchases of the article a by a plurality of users, for example.

The recipe information 223 includes various information related to recipes. The recipe information 223 includes information on a desired food material, seasoning, and the like, for example. The recipe information 223 includes, for example, information related to cooking tools, cooking steps, and the like.

The control unit 230 is realized by executing a program stored in a storage unit, not shown, with a RAM or the like as a work area by a CPU, an MPU, or the like, for example. The control unit 230 is a controller, and may be implemented by an integrated circuit such as an ASIC or an FPGA. The control unit 230 may be implemented by a combination of software and hardware.

The control unit 230 acquires the line-of-sight history information 151 and the purchase history information 152 of the user U from the information recommendation device 100 via the communication unit 210. The control unit 230 stores the line of sight history information 151 in the line of sight history information database 221. Control unit 230 stores purchase history information 152 in purchase history information database 222. The control section 230 acquires line-of-sight history information and purchase history information of a plurality of users via the communication section 210. The control unit 230 stores the line-of-sight history information of a plurality of users in the line-of-sight history information database 221. The control unit 230 stores purchase history information of a plurality of users in the purchase history information database 222.

The control unit 230 acquires the line-of-sight history information of a predetermined user from the line-of-sight history information database 221. The control unit 230 acquires purchase history information of a predetermined user from the purchase history information database 222.

The control unit 230 calculates the preference degree for a specific product based on predetermined user's sight line history information and purchase history information. The control unit 230 recommends a recipe using at least one product having a preference degree equal to or higher than a predetermined value. That is, the control unit 230 has the same function as the control unit 160 of the information recommendation device 100. Therefore, in the present embodiment, the information recommendation device 100 may perform the process of recommending recipes to the user, or the server device 200 may perform the process of recommending recipes to the user. In the following, the information recommendation device 100 will be described as executing each process, but the server device 200 may execute each process.

[ treatment of the first embodiment ]

The recipe recommendation processing according to the first embodiment will be described with reference to fig. 5. Fig. 5 is a flowchart showing an example of the flow of the recipe recommendation processing according to the first embodiment.

The control unit 160 recognizes the user U (step S100). Specifically, the user recognition unit 166 recognizes the user U based on a predetermined operation from the user U. Then, the process proceeds to step S110.

The control unit 160 acquires the line-of-sight history information and the purchase history information (step S110). Specifically, the acquisition unit 161 acquires the line-of-sight history information and the purchase history information of the user U recognized by the user recognition unit 166. Then, the process proceeds to step S120.

The control section 160 calculates the preference degree of the user U (step S120). Specifically, the calculation unit 162 calculates the preference of the user U based on the line-of-sight history information and the purchase history information acquired by the acquisition unit 161. The calculation unit 162 calculates the preference degree based on, for example, the cumulative watching time for a predetermined product, the number of times of shopping watched, and the ratio of the number of times of shopping in which the product is watched among the number of times of shopping in a predetermined period.

Fig. 6A is a diagram for explaining a method of calculating the preference degree based on the accumulated gaze time. As shown in fig. 6A, the calculation unit 162 calculates the preference of the product based on the predetermined cumulative fixation time of the product. The calculation unit 162 calculates the preference degree of the product having the cumulative fixation time of "t 1 or more and less than" t2 "as" a1 ", for example. The calculation unit 162 calculates the preference degree of the product having the cumulative fixation time of "t 2 or more and less than t 3" as "a 2", for example. The calculation unit 162 calculates the preference degree of the product having the cumulative fixation time of "t 3 or more and less than t 4" as "a 3", for example. In fig. 6A, the cumulative gaze time is schematically shown like t1, t2, t3, and t4, but is actually shown numerically. In fig. 6A, the preference degrees are schematically shown as a1, a2, and a3, but actually the preference degrees are shown as numerical values. In this case, the values of a1, a2, and a3 become larger in order. That is, the calculation unit 162 calculates the preference degree to be higher as the cumulative fixation time is longer.

Fig. 6B is a diagram for explaining a method of calculating the preference based on the number of times of shopping at which attention is paid. As shown in fig. 6B, the calculation unit 162 calculates the preference of the product based on the number of times of shopping at which attention is paid. The number of times of shopping observed as shown in fig. 6B is counted as 1 even when the product is watched once during shopping, for example. The calculation unit 162 calculates the preference degree of a product that has been watched for the number of shopping times of "x 1" as "a 11", for example. The calculation unit 162 calculates the preference degree of the product in the case where the number of times of shopping at which attention is paid is "x 2" as "a 12", for example. The calculation unit 162 calculates the preference degree when the number of times of shopping at which attention is paid is "x 3" as "a 13", for example. In fig. 6B, the number of times of shopping watched is schematically shown as x1, x2, and x3, but is actually shown numerically. Specifically, the values of x1, x2, and x3 become larger in order. In fig. 6B, the preference degrees are schematically shown as a11, a12, and a13, but actually, the preference degrees are shown as numerical values. In this case, the values of a11, a12, and a13 become larger in order. That is, the calculation unit 162 calculates the preference degree to be higher as the number of times of shopping at which attention is paid is larger.

Fig. 6C is a diagram for explaining a method of calculating the preference based on the ratio of the number of times of shopping at which attention is paid to the predetermined number of times of shopping. As shown in fig. 6C, the calculation unit 162 calculates the preference of the product based on the ratio of the number of times of shopping (e.g., x11, x12, and x13) on which attention is paid out among the predetermined number of times of shopping (e.g., y times). The method of counting the number of times of shopping at attention is the same as the case of fig. 6B. The calculation unit 162 calculates the preference degree of the case where the ratio of the number of times of shopping observed among the predetermined number of times of shopping is "x 11/y" as "a 21", for example. The calculation unit 162 calculates the preference degree of the case where the ratio of the number of times of shopping observed among the predetermined number of times of shopping is "x 12/y" as "a 22", for example. The calculation unit 162 calculates the preference degree of the case where the ratio of the number of times of shopping observed among the predetermined number of times of shopping is "x 13/y" as "a 23", for example. In fig. 6C, the ratio of the number of paid attention purchases in the predetermined number of purchases is schematically shown as x11/y, x12/y, and x13/y, but actually the ratio of the number of paid attention purchases in the predetermined number of purchases is numerically shown. Specifically, when the values of x11, x12 and x13 are sequentially increased, the values of x11/y, x12/y and x13/y are sequentially increased. In fig. 6C, the preference degrees are schematically shown as a21, a22, and a23, but actually, the preference degrees are shown as numerical values. In this case, the values of a21, a22, and a23 become larger in order. That is, the calculation unit 162 calculates the preference degree so that the greater the proportion of the number of times of shopping at which attention is paid out among the predetermined number of times of shopping, the greater the preference degree.

The calculation unit 162 may calculate the preference degree by combining the fixation time of a predetermined product and the number of times of shopping fixation. In this case, the calculation unit 162 may calculate the degree of attention indicating the degree of attention time from the attention time, for example.

Fig. 6D is a diagram for explaining a method of calculating the degree of attention. As shown in fig. 6D, the calculation unit 162 calculates the degree of attention based on the attention time for a predetermined product. The calculation unit 162 calculates the degree of fixation in the case where the fixation time is "t 11 or more and less than t 12" as "b 1", for example. The calculation unit 162 calculates the degree of fixation in the case where the fixation time is "t 12 or more and less than t 13" as "b 2", for example. The calculation unit 162 calculates the degree of fixation in the case where the fixation time is "t 13 or more and less than t 14" as "b 3", for example. In fig. 6D, the gaze time is schematically shown as t11, t12, t13, and t14, but is actually shown numerically. Specifically, the values of t11 or more and less than t12, t12 or more and less than t13, and t13 or more and less than t14 become larger in order. In fig. 6D, the degree of fixation is schematically shown as b1, b2, and b3, but actually is shown numerically. In this case, the values of b1, b2, and b3 become larger in order. That is, the calculation unit 162 calculates the degree of attention so that the degree of attention becomes higher as the attention time becomes longer.

Fig. 6E is a diagram showing a relationship between the degree of attention and the number of times of shopping. As shown in fig. 6E, the number of times of shopping with the degree of attention "b 1" for a predetermined product is "c 1", the number of times of shopping with the degree of attention "b 2" is "c 2", and the number of times of shopping with the degree of attention "b 3" is "c 3". In fig. 6E, the number of purchases is schematically shown like c1, c2, and c3, but actually the number of purchases is numerically shown. In the case of the example shown in fig. 6E, the calculation unit 162 calculates the preference of the predetermined product as "b 1 × c1+ b2 × c2+ b3 × c3+ ·.

The calculation unit 162 may calculate the preference degree based on whether or not the user U actually purchases the product. Specifically, the calculation unit 162 may add a weight to the preference calculated based on the line-of-sight history information when the product is purchased. For example, the preference degree calculated based on the visual line history information of a certain product is set to "d". In this case, the calculation unit 162 calculates the preference degree as "d + f" when the product is purchased, for example. The calculation unit 162 calculates the preference degree as "d × e" when the product is purchased, for example. d. f, e are actually shown as numerical values. f and e are sometimes also referred to as purchase addition coefficients. The purchase addition coefficient is not particularly limited as long as it is a numerical value that makes "d + f" and "d × e" larger than d.

Returning to fig. 5. The control unit 160 recommends a recipe based on the calculated preference (step S130). Specifically, the recommendation unit 163 recommends a recipe using at least one product having a preference degree equal to or higher than a predetermined value, based on the recipe information 153. The recommendation unit 163 displays the recipe on the display unit 130, for example.

Fig. 7 is a diagram showing an example of a recipe display screen recommended by the recommendation unit 163. As shown in fig. 7, the recipe display screen 300 includes a total amount display area 310, a purchase history display area 320, and a recipe display area 330.

The total amount display area 310 is an area showing the total amount of the commodities to be purchased by the user U. The total amount display area 310 displays, for example, the total amount of the items in the shopping cart C.

The purchase history display area 320 is an area showing the commodity purchase history of the user U. The purchase history display area 320 includes a purchase item display area 321(321a, 321b, 321c,) that displays a purchase item for each date on which shopping has been performed. A purchase product list purchased on day 10/4/2020 is displayed in the purchase product display area 321 a. A purchase product list purchased on day 4, month 5 of 2020 is displayed in the purchase product display area 321 b. A purchase product list purchased on 1/4/2020/year is displayed in the purchase product display area 321 c.

The recipe display area 330 is an area where a recipe is displayed. The recipe display area 330 includes, for each recipe, a recipe summary display area 331(331a, 331b · · and a recipe image display area 332(332a, 332b · · ·).

The recipe summary display area 331a is an area for displaying the summary of the recipe a. For example, information on materials necessary for creating the recipe a and information on the amount of money necessary for preparing the materials are displayed in the recipe summary display area 331 a. The recipe image display area 332a is an area where an image of the recipe a is displayed. Similarly, the recipe summary display area 331B is an area for displaying the summary of the recipe B, and the recipe image display area 332B is an area for displaying the image of the recipe B.

Returning to fig. 5. The control unit 160 determines whether or not the recipe is selected by the user U (step S140). Specifically, the recommendation unit 163 determines whether or not any one of the recipes displayed in step S130 is selected by the user U via the operation unit 120. If it is determined that the recipe is selected (yes in step S140), the process proceeds to step S150. If it is determined that the recipe is not selected (no in step S140), the process proceeds to step S160.

If it is determined as yes in step S140, the control unit 160 displays details of the selected recipe on the display unit 130 (step S150). Specifically, the recommendation unit 163 displays details of the selected recipe on the display unit 130.

Fig. 8 is a diagram showing an example of a recipe detail screen. The recipe detail screen 400 includes a recipe name display area 410, a recipe image display area 420, a material display area 430, and a cooking step display area 440.

The recipe name display area 410 is an area for displaying the recipe name, the amount of money required to prepare materials for preparing the recipe, and the like.

The recipe image display area 420 is an area where an image of the selected recipe is displayed. In the example shown in fig. 8, a photograph of "home taste, hot potato and beef stew" is displayed in the recipe image display area 420.

The material display area 430 displays details of the materials needed to make the selected recipe. Specifically, materials including seasonings such as beef, potato, and white sugar are displayed together with the components in the material display area 430.

The cooking step display area 440 displays details of the cooking step of the selected recipe. The cooking step display area 440 displays the selected recipe in detail, for example, as the first cooking step and the second cooking step. In fig. 8, the cooking step display area 440 schematically shows the first cooking step and the second cooking step, but actually shows specific steps.

Returning to fig. 5. The control unit 160 determines whether or not the recipe recommendation process is ended (step S160). Specifically, the control unit 160 determines that the recipe recommendation processing is ended when the operation to end the recipe recommendation processing is accepted and when the operation to turn off the power supply is accepted. If it is determined that the recipe recommendation process is ended (step S160; yes), the process of fig. 5 is ended. If it is determined that the recipe recommendation process is not to be ended (no in step S160), the process proceeds to step S130.

As described above, the first embodiment recommends recipes to the user U based on the line-of-sight history information and the purchase history information of the user U. Thus, the first embodiment can recommend a recipe using a product having a high user U preference.

In step S100, the user recognition unit 166 may execute a process of recognizing a plurality of users in addition to the user U. The user identification unit 166 may identify a plurality of users by the same method as the method of identifying the user U. Thus, for example, if information relating to the history of the line of sight of each user and information relating to the purchase history are stored in the server apparatus 200, the preference of each user can be calculated. Thus, for example, when friends gather and cook, recipes according to the preference of each user can be recommended.

[ treatment of the second embodiment ]

The recipe recommendation processing according to the second embodiment will be described with reference to fig. 9. Fig. 9 is a flowchart showing an example of the flow of the recipe recommendation processing according to the second embodiment. The configuration of the information recommendation device of the second embodiment is the same as that of the information recommendation device 100 illustrated in fig. 2, and therefore, the description thereof is omitted.

The processing of steps S200 to S220 is the same as the processing of steps S100 to S120 shown in fig. 5, and therefore, the description thereof is omitted.

The control unit 160 detects a line of sight to the product (step S230). Specifically, the line-of-sight detecting unit 164 detects the line of sight of the user U to the product in real time based on the image data of the face of the user U. Then, the process proceeds to step S240.

The control unit 160 calculates the degree of attention of the user U to the product (step S240). Specifically, the calculation unit 162 calculates the degree of attention of the product based on the detection result of the line of sight by the line of sight detection unit 164. For example, the calculation unit 162 calculates the higher the attention degree as the gaze time to the product is longer, based on the detection result of the line of sight by the line of sight detection unit 164.

The control unit 160 recommends a recipe based on the calculated preference degree and attention degree (step S250). Specifically, the recommendation unit 163 recommends a recipe using at least one product having a preference degree equal to or higher than a predetermined degree and at least one product having an attention degree equal to or higher than a predetermined degree, based on the recipe information 153. The recommendation unit 163 displays the recipe on the display unit 130, for example. Then, the process proceeds to step S260.

The processing of steps S260 to S280 is the same as the processing of steps S140 to S160 shown in fig. 5, and therefore, the description thereof is omitted.

As described above, the second embodiment recommends recipes to the user U based on the movement of the line of sight of the user U who is shopping in addition to the line of sight history information and purchase history information of the user U. Thus, the second embodiment can recommend recipes using products having high preference and attention of the user U.

[ treatment of the third embodiment ]

The recipe recommendation processing according to the third embodiment will be described with reference to fig. 10. Fig. 10 is a flowchart showing an example of the flow of the recipe recommendation processing according to the third embodiment. The configuration of the information recommendation device of the third embodiment is the same as that of the information recommendation device 100 illustrated in fig. 2, and therefore, the description thereof is omitted.

The processing of steps S300 to S320 is the same as the processing of steps S100 to S120 shown in fig. 5, and therefore, the description thereof is omitted.

The control section 160 identifies the product that the user U intends to purchase (step S330). Specifically, the product recognizing unit 165 recognizes a product which the user U intends to purchase by performing a known object recognition process on the image data of the product placed in the shopping cart C captured by the camera 110. Then, the process proceeds to step S340.

The control section 160 recommends a recipe based on the calculated preference and a product scheduled for purchase (step S340). Specifically, the recommendation unit 163 recommends a recipe using at least one product scheduled for purchase and at least one product having a preference degree equal to or higher than a predetermined value, based on the recipe information 153. The recommendation unit 163 displays the recipe on the display unit 130, for example.

Fig. 11 is a diagram showing an example of a recipe display screen recommended by the recommendation unit 163. As shown in fig. 11, the recipe display screen 500 includes a selected material display area 510, a recipe number display area 520, and a recipe display area 530.

The selected material display area 510 is an area displaying materials selected as recipe materials. Specifically, a product selected as a recipe material from among a product having a high preference degree, a product scheduled to be purchased, a product purchased in the past, and the like is displayed in the selected material display area 510. In the example shown in fig. 11, "apple" is displayed as a highly preferred product. "turmeric" is displayed as a commodity scheduled for purchase. "flour" is displayed as a commodity purchased in the past.

The recipe number display area 520 is an area for displaying the number of recipes that can be produced using the selected material.

The recipe display area 530 is an area where a recipe is displayed. In the example shown in fig. 11, a recipe in which "apple", "turmeric" and "flour" are used is displayed in the recipe display area 530. The recipe display area 530 includes, for each recipe, a recipe summary display area 531(531a, 531b · · and a recipe image display area 532(532a, 532b · ·).

The recipe summary display area 531a is an area that displays a summary of "full apple curry in sufficient quantity". For example, information on the material required to produce "full apple curry in a sufficient amount" and information on the amount of money required to prepare the material are displayed in the recipe summary display area 531 a. The recipe image display area 532a is an area displaying an image of "sufficient amount of apple curry" full. Similarly, the recipe summary display area 531b is an area for displaying the summary of "american apple pie with fragrance", and the recipe image display area 532b is an area for displaying the image of "american apple pie with fragrance".

Returning to fig. 10. The processing of steps S350 to S370 is the same as the processing of steps S140 to S160 shown in fig. 5, and therefore, the description thereof is omitted.

As described above, the third embodiment recommends recipes to the user U based on the product to be purchased by the user U in addition to the line-of-sight history information and the purchase history information of the user U. Thus, the third embodiment can recommend a recipe using a product that is highly preferred by the user U and is to be purchased.

Further, the recommendation part 163 may sort and recommend recipes based on the purchase history information and the purchase-scheduled products identified in step S330. For example, when the user U continuously purchases products of the same manufacturer, food materials of the same origin, and the like, the recommending unit 163 may provide a change in the taste of the recipe when products of different manufacturers and food materials of different origins are used. Specifically, the recommendation unit 163 may present information that such a distinction is made between the taste, flavor, and the like when the products of different manufacturers and the food materials of different origins are used, and information that the recipe is expanded in this manner.

[ treatment of the fourth embodiment ]

The recipe recommendation processing according to the fourth embodiment will be described with reference to fig. 12. Fig. 12 is a flowchart showing an example of the flow of the recipe recommendation processing according to the fourth embodiment. The configuration of the information recommendation device according to the fourth embodiment is the same as that of the information recommendation device 100 illustrated in fig. 2, and therefore, the description thereof is omitted.

The processing of steps S400 to S440 is the same as the processing of steps S200 to S240 shown in fig. 9, and therefore, the description thereof is omitted. The processing of step S450 is the same as the processing of step S340 shown in fig. 10, and therefore, the description thereof is omitted.

The control unit 160 recommends a recipe based on the calculated preference degree and attention degree and a product scheduled to be purchased (step S460). Specifically, the recommendation unit 163 recommends a recipe using at least one product scheduled to be purchased, at least one product having a preference degree equal to or higher than a predetermined degree, and at least one product having an attention degree equal to or higher than a predetermined degree. Then, the process proceeds to step S470.

The processing of steps S470 to S490 is the same as the processing of steps S140 to S160 shown in fig. 5, and therefore, the description thereof is omitted.

As described above, the fourth embodiment recommends recipes to the user U based on the sight line history information of the user U, the purchase history information, the movement of the sight line of the user U who is shopping, and the product to be purchased by the user U. Thus, the fourth embodiment can recommend a recipe using a product that is highly preferred and highly focused by the user U and that the user U wants to purchase.

[ fifth embodiment ]

[ information recommendation device ]

An information recommendation apparatus according to a fifth embodiment will be described with reference to fig. 13. Fig. 13 is a block diagram showing a configuration example of an information recommendation device according to the fifth embodiment.

As shown in fig. 13, the information recommendation device 100A is different from the information recommendation device 100 shown in fig. 2 in that it includes a sensor 170. The information recommendation apparatus 100A adds environmental information including the air temperature to recommend recipes to the user U.

The sensor 170 detects environmental information around the information recommendation device 100A. The sensor 170 includes, for example, a temperature sensor that detects the temperature around the information recommendation device 100A. The sensor 170 includes, for example, a humidity sensor that detects humidity around the information recommendation device 100A. The sensors 170 may include sensors that acquire other information related to the environment.

The acquisition unit 161A acquires various environmental information from the sensor 170. The acquisition unit 161A acquires, for example, temperature information relating to temperature and humidity information relating to humidity from the sensor 170. The acquisition unit 161A may acquire temperature information, humidity information, and weather information from an external server or the like that distributes weather information via the communication unit 140, for example.

The recommending unit 163A recommends a recipe based on the environment information acquired by the acquiring unit 161A. The recommendation unit 163A recommends recipes based on, for example, the environment information and the preference degree of the product acquired by the acquisition unit 161A. The recommendation unit 163A recommends recipes based on, for example, the environment information acquired by the acquisition unit 161A, the preference of the product, and the product scheduled to be purchased.

[ treatment of the fifth embodiment ]

The recipe recommendation processing according to the fifth embodiment will be described with reference to fig. 14. Fig. 14 is a flowchart showing an example of the flow of the recipe recommendation processing according to the fifth embodiment.

The processing of steps S500 to S520 is the same as the processing of steps S100 to S120 shown in fig. 5, and therefore, the description thereof is omitted.

The control section 160A acquires the environmental information (step S530). Specifically, the acquisition unit 161A acquires real-time environmental information such as temperature information from the sensor 170 and an external server device. The acquisition unit 161A may acquire the expected environmental information at the predetermined cooking time when the predetermined cooking time is set in advance. Then, the process proceeds to step S540.

The processing of step S540 is the same as the processing of step S330 shown in fig. 10, and therefore, the description thereof is omitted.

The control unit 160A recommends a recipe based on the calculated preference degree, environmental information, and a product scheduled for purchase (step S550). Specifically, the recommendation unit 163A recommends recipes based on at least one product whose taste is equal to or higher than a predetermined value, at least one product scheduled to be purchased, and the environment information. For example, the calculation unit 162 calculates the preference of a specific spicy seasoning to be a predetermined value or more. The product recognition unit 165 recognizes bean curd as a product to be purchased. The acquisition unit 161A acquires a low temperature equal to or higher than a predetermined temperature. In this case, the recommendation unit 163A is likely to be preferred by the user U for spicy food, and the product to be purchased includes bean curd and has a low temperature, so that, for example, "korean stockpot" or the like is recommended. Then, the process proceeds to step S560.

The processing of step S560 to step S580 is the same as the processing of step S140 to step S160 shown in fig. 5, and therefore, the description thereof is omitted.

As described above, the fifth embodiment recommends recipes to the user U based on the line-of-sight history information, purchase history information, environment information of the user U, and a product to be purchased by the user U. Thus, the fifth embodiment can recommend a recipe corresponding to the current temperature using a product that is highly preferred and highly focused by the user U and is to be purchased by the user U.

[ sixth embodiment ]

[ information recommendation System ]

The configuration of the information recommendation system according to the sixth embodiment will be described with reference to fig. 15. Fig. 15 is a diagram showing a configuration example of an information recommendation system according to a sixth embodiment.

As shown in fig. 15, the information recommendation system 1A includes an information recommendation device 100B, a server device 200, and a store server device 600. The information recommendation system 1A is different from the information recommendation system 1 shown in fig. 1 in that it includes the store server device 600. The store server device 600 is a server device disposed in a store such as a retail store using the information recommendation device 100B. The store server device 600 is connected to the information recommendation device 100B so as to be able to communicate with each other.

The store server device 600 stores various store information related to a store to be arranged, for example. The store server 600 stores map information of the counter of the store, for example. The map information on the counter includes position information of the product related to the position where the product is displayed. The store server device 600 stores product information related to a product. The commodity information may include information related to special commodities and information related to time-limited special offers.

[ information recommendation device ]

The configuration of the information recommendation device according to the sixth embodiment will be described with reference to fig. 16. Fig. 16 is a block diagram showing a configuration example of an information recommendation device according to the sixth embodiment.

As shown in fig. 16, the information recommendation device 100B is different from the information recommendation device 100 shown in fig. 2 in that the control unit 160B includes the guide unit 167. The information recommendation device 100B calculates a representative value of the purchase price of the product based on the purchase history. The information recommendation device 100B acquires price information of a product sold in a store, and recommends a recipe using a product cheaper than the representative value of the purchase price. The information recommendation device 100B guides the user U to a position where the product selected by the user U is displayed. Hereinafter, an example will be described in which the information recommendation apparatus 100B recommends a recipe using a product that is cheaper than the representative value of the purchase price of the product, but the present invention is not limited to this. For example, the information recommendation apparatus 100B may recommend a recipe in which the sales price of the product is within a predetermined range from the representative value of the purchase price of the product. Here, the predetermined range is, for example, about 10% of the representative value of the purchase price of the product, but is not limited thereto.

The acquisition unit 161B acquires the store information from the store server device 600 via the communication unit 140. The acquisition unit 161B acquires, for example, map information and product information of a store from the store server device 600. The commodity information acquired by the acquisition section 161B may contain price information relating to the price of the commodity.

The calculation unit 162B calculates a representative value of the purchase price for each product based on the purchase history information 152. The recommending unit 163B recommends a recipe using at least one product whose selling price is lower than the representative value of the purchase price among the products whose taste is equal to or higher than a predetermined value.

The recommendation unit 163B recommends a suggested product based on the product information acquired by the acquisition unit 161B. For example, when the time of the limited time special sale is reached by a predetermined time (for example, 10 minutes ago), the recommendation unit 163B displays the product of the limited time special sale on the display unit 130. The recommending unit 163B may acquire the current time from, for example, a not-shown time counting unit that counts time. The recommendation unit 163B may display the special price item on the display unit 130, for example. The recommendation unit 163 may display special offer information of a product having a high preference degree equal to or higher than a predetermined value on the display unit 130.

The guide 167 guides the product to a position where the product desired by the user U is displayed in the store. The guide unit 167 guides the product to the position where the product is displayed, for example, based on the map information acquired by the acquisition unit 161B. The guide unit 167 guides, for example, the position of the product selected by the user U among the products displayed on the display unit 130 by the recommendation unit 163B. The guide unit 167 may acquire the current position, the position of the product, and the like based on beacons and the like transmitted from access points arranged at a plurality of points in the counter of the store, for example. The guide unit 167 may acquire the current position, the position of the product, and the like based on a GNSS signal acquired by a GNSS (Global Navigation Satellite System) receiver (not shown).

[ treatment of sixth embodiment ]

The recipe recommendation processing according to the sixth embodiment will be described with reference to fig. 17. Fig. 17 is a flowchart showing an example of the flow of the recipe recommendation processing according to the sixth embodiment.

The processing of steps S600 to S620 is the same as the processing of steps S100 to S120 shown in fig. 5, and therefore, the description thereof is omitted.

The control unit 160B calculates a representative value of the purchase price of the product (step S630). Specifically, the calculation unit 162B calculates a representative value of the purchase price for each product based on the purchase history information 152. Then, the process proceeds to step S640.

The control unit 160B acquires product information (step S640). Specifically, the recommendation unit 163B acquires product information including price information from the store server device 600. Then, the process proceeds to step S650.

The control unit 160B determines whether or not there is a product whose price is lower than the representative value (step S650). Specifically, the recommending unit 163B compares the representative value with the prices of the products in the stores to determine whether or not there is a product having a price lower than the representative value. If it is determined that there is a product whose price is lower than the representative value (step S650; yes), the process proceeds to step S660. If it is determined that there is no product whose price is lower than the representative value (step S650; no), the process proceeds to step S670.

If it is determined to be yes in step S650, the control unit 160B recommends a recipe using a product whose price is lower than the representative value (step S660). Specifically, the recommending unit 163B recommends a recipe using at least one product whose price is lower than the representative value. Then, the process proceeds to step S680.

The processing of step S670 to step S700 is the same as the processing of step S130 to step S160 illustrated in fig. 5, and therefore, the description thereof is omitted.

As described above, the sixth embodiment recommends recipes to the user U based on the purchase history information and price information of the user U. Thus, the sixth embodiment can recommend a recipe using a product whose price is lower than the representative value, and therefore can recommend a product whose cost is not wasted.

[ guide processing ]

The route guidance processing to the product will be described with reference to fig. 18. Fig. 18 is a flowchart showing an example of the flow of the route guidance processing to the product.

The processing of steps S800 to S820 is the same as the processing of steps S100 to S120 shown in fig. 5, and therefore, the description thereof is omitted.

The control unit 160B acquires the store information (step S830). Specifically, the acquisition unit 161B acquires the store information including the map information of the store from the store server device 600. Then, the process proceeds to step S840.

The control unit 160B acquires product information on products sold in the store (step S840). Specifically, the acquisition unit 161B acquires product information including price information of a product and display position information from the store server device 600. Then, the process proceeds to step S850.

The control unit 160B displays the proposed product (step S850). Specifically, the recommendation unit 163B displays the recommended product on the display unit 130 based on the product information.

Fig. 19 is a diagram showing an example of the recommended product display screen displayed by the recommendation unit 163. As shown in fig. 19, the suggested article display screen 700 includes a suggested article display area 710, a route guidance start button 720, and a cancel button 730.

The suggested article display area 710 is an area where the suggested article is displayed. The suggested article display area 710 includes an illustration display area 711 and a suggested article image display area 712. The description display area 711 displays the origin, the product name, the amount of money, the detailed information, and the like of the recommended item. An image of the recommended item is displayed in the recommended article image display area 712.

The route guidance start button 720 is a button for displaying a route to a recommended item. In a case where the user U desires to purchase a recommended article, if the route guidance start button 720 is pressed, the route guidance to the recommended article is started by the guide section 167.

The cancel button 730 is a button for canceling the display of the advice. When the user U does not desire to purchase the recommended article, the user U cancels the display of the recommended article by the recommending unit 163B by pressing the cancel button 730. In this case, the next item of advice may be displayed, or the display of the item of advice may be terminated.

Returning to fig. 18. The control unit 160B determines whether or not the start route guidance is selected (step S860). If it is determined that the start route guidance is selected (yes in step S860), the process proceeds to step S870. If it is determined that the start route guidance is not selected (no in step S860), the process proceeds to step S880.

If yes is determined in step S860, control unit 160B starts route guidance (step S870). Specifically, the guide 167 guides the user to the route of the recommended product by displaying the display 130. Then, the process proceeds to step S880.

The control unit 160B determines whether or not to end the route guidance process (step S880). Specifically, the control unit 160B determines that the route guidance processing is ended when no commodity is suggested, when an operation to end the route guidance processing is accepted, and when an operation to cut off the power supply is accepted. If it is determined to end the route guidance processing (step S880; yes), the processing of fig. 18 is ended. If it is determined that the route guidance processing is not to be ended (step S880; no), the process proceeds to step S850.

As described above, the sixth embodiment performs route guidance to an article that the user U desires to purchase. This allows the user U to purchase the recommended product smoothly, while being tired of purchasing the product.

In the sixth embodiment, the description has been given of the processing of displaying the recommended product and guiding the route, but the present invention is not limited to this. For example, route guidance to a product required for a recipe may be performed on the recipe detail screen 400 shown in fig. 8. Specifically, it is also possible to select a material displayed in the material display area 430 of the recipe detail screen 400 and perform route guidance to the product selected in the material display area 430.

The embodiments of the present invention have been described above, but the present invention should not be limited to the contents of these embodiments. The above-described components include components that can be easily conceived by those skilled in the art, substantially the same components, and so-called equivalent ranges. Further, the above-described constituent elements can be appropriately combined. Further, various omissions, substitutions, and changes in the constituent elements can be made without departing from the spirit of the embodiments described above.

Claims (6)

1. An information recommendation device is provided with:

an acquisition unit that acquires line-of-sight history information including a history of movement of a line of sight of a user with respect to a commodity and purchase history information including a purchase history of the commodity of the user;

a calculation unit that calculates a preference degree indicating a preference degree of the user for a commodity based on the sight line history information and the purchase history information; and

and a recommendation unit that recommends a recipe using at least one product having the preference degree equal to or higher than a predetermined value.

2. The information recommendation device of claim 1,

the information recommendation device is provided with a sight line detection unit for detecting the sight line of the user to the commodity,

the calculation unit calculates a degree of attention indicating a degree of interest in the commodity based on the line of sight detected by the line of sight detection unit,

the recommendation unit recommends a recipe using at least one product having the preference degree of at least one predetermined product and at least one product having the attention degree of at least one predetermined product.

3. The information recommendation apparatus according to claim 1 or 2,

the information recommendation device is provided with a commodity identification part for identifying commodities which are scheduled to be purchased by the user,

the recommendation unit recommends a recipe that also uses at least one product identified by the product identification unit.

4. The information recommendation apparatus according to any one of claims 1 to 3,

the acquisition section acquires price information relating to a selling price of the commodity,

the calculation section calculates a representative value of purchase prices of the commodities based on the purchase history,

the recommendation unit recommends a recipe using a product whose sales price falls within a predetermined range with respect to the representative value of the purchase price, among the products whose liking degree is equal to or higher than a predetermined value.

5. An information recommendation method, comprising the steps of:

acquiring the movement history of the sight of a user to a commodity and the purchase history of the commodity of the user;

calculating a preference degree indicating a preference degree of the user for the commodity based on the movement history and the purchase history; and

a recipe using at least one product having the preference degree not less than the predetermined value is recommended.

6. A storage medium storing a program that causes a computer to execute the steps of:

acquiring the movement history of the sight of a user to a commodity and the purchase history of the commodity of the user;

calculating a preference degree indicating a preference degree of the user for the commodity based on the movement history and the purchase history; and

a recipe using at least one product having the preference degree not less than the predetermined value is recommended.

Images