Information processing system, information processing apparatus, information processing method, and program

Abstract

To associate consumer sensory information for meat with physicochemical analysis information.SOLUTION: An information processing apparatus comprises: a sensory information acquisition unit that acquires sensory information for meat; and a statistical unit that outputs physicochemical analysis information for meat by inputting the acquired sensory information for meat into a learning model that has learned the correspondence between at least the sensory information for meat and the physicochemical analysis information for meat.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] In recent years, consumers have become increasingly interested in the origin of meat, such as its place of production. For example, there is a demand for providing information on the place of production and producer of meat sold in stores. For example, Patent Document 1 discloses a technology for improving traceability by using an individual identification number for meat, in which production place information is provided using the individual identification number or certificate of the cow. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-118532 Summary of the Invention [Problem to be solved by the invention]

[0004] Meat research institutes conduct physicochemical analysis and sensory evaluation of meat, which are carried out with the origin of the cattle identified by their individual identification numbers and certificates. These sensory evaluations and meat quality grades may differ from consumer sensory perceptions. This is because meat quality grades are determined by marbling, meat color and luster, meat firmness and texture, and fat color and luster and quality, but flavor and texture cannot be determined by physicochemical analysis alone. However, until now, there has been no correspondence between consumer sensory information about meat and physicochemical analysis information of meat. Thus, there has been a problem in that it is not possible to correlate consumer sensory information about meat with physicochemical analysis information.

[0005] In view of the above-mentioned problems, an object of the present invention is to provide an information processing system, an information processing device, an information processing method, and a program that can associate sensory information about meat from consumers with physicochemical analysis information. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, an information processing system according to one aspect of the present invention is an information processing system including a sensory information acquisition unit that acquires sensory information about meat, and a statistical unit that obtains physicochemical analysis information about the meat as an output by inputting the acquired sensory information about the meat into a learning model that has learned the correspondence between at least the sensory information about the meat and physicochemical analysis information about the meat.

[0007] Furthermore, an information processing device according to one aspect of the present invention is an information processing device that includes a sensory information acquisition unit that acquires sensory information about meat, and a statistical unit that obtains physicochemical analysis information about the meat as an output by inputting the acquired sensory information about the meat into a learning model that has learned at least the correspondence between the sensory information about the meat and physicochemical analysis information about the meat.

[0008] Furthermore, an information processing method according to one aspect of the present invention is an information processing method executed by a computer of an information processing device, and includes a sensory information acquisition step of acquiring sensory information about meat, and a statistical step of obtaining physicochemical analysis information about the meat as an output by inputting the acquired sensory information about the meat into a learning model that has learned the correspondence between at least the sensory information about the meat and physicochemical analysis information about the meat.

[0009] Furthermore, a program according to one aspect of the present invention is a program for causing a computer of an information processing device to execute a sensory information acquisition step of acquiring sensory information about meat, and a statistical step of obtaining physicochemical analysis information about the meat as an output by inputting the acquired sensory information about the meat into a learning model that has learned the correspondence between at least the sensory information about the meat and physicochemical analysis information about the meat. [Effects of the Invention]

[0010] According to the present invention, it is possible to associate consumer sensory information about meat with physicochemical analysis information. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a schematic diagram illustrating an example of the configuration of an information processing system according to a first embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of a functional configuration of the information processing device according to the present embodiment. [Figure 3] FIG. 2 is a diagram showing an example of a meat image according to the present embodiment. [Figure 4] FIG. 10 is a diagram illustrating an example of analysis information according to the embodiment. [Figure 5] FIG. 4 is a diagram showing an example of image information according to the embodiment. [Figure 6] FIG. 10 is a diagram showing an example of green meat information according to the embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of sensory information according to the embodiment. [Figure 8] FIG. 10 is a diagram illustrating an example of statistical information according to the embodiment. [Figure 9] 10 is a flowchart illustrating an example of processing in the information processing device according to the embodiment. [Figure 10] FIG. 10 is a block diagram showing an example of a functional configuration of an information processing device according to a second embodiment. [Figure 11] FIG. 4 is a diagram illustrating an example of setting information according to the embodiment. [Figure 12] FIG. 10 is a diagram showing an example of order information according to the embodiment. [Figure 13] FIG. 10 is a diagram illustrating an example of additional information according to the embodiment. [Figure 14A] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 14B] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 14C] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 14D] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 15A] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 15B] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 15C] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 15D] FIG. 4 is a diagram showing an example of a display screen according to the present embodiment. [Figure 16] 10 is a flowchart illustrating an example of processing in the information processing device according to the present embodiment. [Figure 17] FIG. 10 is a block diagram showing an example of the configuration of an information processing device according to a third embodiment. [Figure 18] FIG. 10 is a diagram showing an example of green meat information according to the embodiment. [Figure 19] 10 is a flowchart illustrating an example of processing in the information processing device according to the present embodiment. [Figure 20] FIG. 10 is a block diagram showing an example of a functional configuration of an information processing device according to a fourth embodiment. [Figure 21] FIG. 10 is a diagram illustrating an example of statistical information according to the embodiment. [Figure 22] 10 is a flowchart illustrating an example of processing in the information processing device according to the present embodiment. [Figure 23] FIG. 2 is a block diagram showing an example of a hardware configuration of the information processing device according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] First Embodiment Hereinafter, a first embodiment of the present invention will be described in detail with reference to the drawings.

[0013] <Information Processing System> The assumed environment of this embodiment will be described with reference to FIG. FIG. 1 is a schematic diagram showing an example of the configuration of an information processing system according to this embodiment. The information processing system includes an information processing device 1. In the example shown in FIG. 1, physicochemical analysis of livestock F, for example, cattle, is performed by analytical institution A or the like before the meat is distributed for consumption. Physicochemical analysis includes, for example, stable isotope ratio analysis, unsaturated fatty acid analysis, and trace element analysis. For example, stable isotope analysis, unsaturated fatty acid analysis, and trace element analysis are component analyses based on collected samples. The results of the physicochemical analysis are associated with the individual identification number of the cattle, etc. The results of the physicochemical analysis may also be associated with production area information.

[0014] For meat that has production area information attached, it is possible to check the physicochemical analysis using the individual cattle identification number. On the other hand, for meat from a slaughterhouse that does not have production area information attached to the meat, it is not possible to check the production area information of the meat. In such cases, the information processing device 1 identifies the physicochemical analysis results for the meat based on, for example, a photographed image BMP of the meat taken by consumer C. The information processing device 1 also associates sensory information R, such as the taste of the meat when eaten by consumer C, with the physicochemical analysis results for the meat.

[0015] It is preferable that the place of production information be information on the place of production of branded Japanese beef instead of or in addition to the place of production of the cattle.

[0016] Branded Wagyu beef includes beef and processed products registered under the Geographical Indication Protection System designated by the Ministry of Agriculture, Forestry and Fisheries, such as Matsusaka beef, Hida beef, Kobe beef, Tajima beef, Yamagata beef, and Tokachi beef. There are more than 200 types of branded Wagyu beef across the country, and each has its own definition established by each producer group.

[0017] <Functional configuration> The configuration of the information processing device 1 will be described with reference to FIG. FIG. 2 is a block diagram showing an example of the functional configuration of the information processing device 1 according to this embodiment. The information processing device 1 includes a control unit 110, a storage unit 130, an output unit 150, and a communication unit 190.

[0018] The information processing device 1 is, for example, a terminal device such as a PC (Personal Computer), a server device, a smartphone, or a tablet.

[0019] <Output unit 150> The output unit 150 has a function of outputting various types of information. The output unit 150 is realized by a display device such as a display included in the information processing device 1. The output unit 150 displays an output image output by the output processing unit 115, which will be described later. The output unit 150 may be a display device included in a device other than the information processing device 1.

[0020] <Communications Department 190> The communication unit 190 has the function of transmitting and receiving various types of information. The communication unit 190 may use either wired communication or wireless communication. For example, the communication unit 190 receives analytical information on meat from a research institute or the like (not shown). The analytical information is information in which the results of physicochemical analysis of the meat are associated with information on the place of production of the meat. The communication unit 190 also receives images of the meat taken by consumers. The communication unit 190 also receives sensory information sent from consumers. The communication unit 190 outputs the received information to the control unit 110.

[0021] <Control unit 110> The control unit 110 has a function of controlling the overall operation of the information processing device 1. This function is realized, for example, by causing a CPU (Central Processing Unit) provided as hardware in the information processing device 1 to execute a program.

[0022] As shown in FIG. 2, the control unit 110 includes an acquisition unit 111, a statistics unit 112, an image analysis unit 113, a specification unit 114, and an output processing unit 115.

[0023] <Acquisition part 111> The acquisition unit 111 has a function of acquiring various types of information via the communication unit 190. As shown in FIG. 2 , the acquisition unit 111 includes an analysis information acquisition unit 1111, a meat block image acquisition unit 1112, and a sensory information acquisition unit 1113.

[0024] <Analysis information acquisition unit 1111> The analytical information acquisition unit 1111 acquires analytical information for each specimen via the communication unit 190. Here, the specimen is, for example, a chunk of beef. The analytical information acquisition unit 1111 stores the acquired analytical information in the storage unit 130.

[0025] <Meat lump image acquisition unit 1112> The meat block image acquisition unit 1112 acquires an image of meat taken by a consumer via the communication unit 190. The meat block image acquisition unit 1112 stores the acquired image of meat in the storage unit 130. Here, the image of meat used in this embodiment is an image of a cross section of a meat block. In the following description, the image of meat will be referred to as a meat image.

[0026] <Sensory information acquisition unit 1113> The sensory information acquisition unit 1113 acquires the consumer's sensory information on meat via the communication unit 190. The sensory information acquisition unit 1113 stores the acquired sensory information in the storage unit .

[0027] <Statistics Department 112> The statistics unit 112 has a function of performing statistical processing on input information. The statistics unit 112 generates output information for the input information based on the information stored in the storage unit 130 and the input information. Specifically, the statistics unit 112 reads out the information stored in the storage unit 130 and generates a learning dataset based on the read information. The statistics unit 112 performs learning based on the generated learning dataset. For example, when a meat image is input, the statistics unit 112 performs learning using the meat image and the statistical information read out from the storage unit 130 as a learning dataset. The statistics unit 112 stores the learning result in the storage unit 130.

[0028] <Image Analysis Unit 113> Image analysis unit 113 performs image analysis on the input image. Image analysis unit 113 performs image analysis on the meat image stored in storage unit 130 to generate appearance data. Image analysis unit 113 stores the generated appearance data in storage unit 130. The appearance data is data that indicates the appearance of the meat.

[0029] The image analysis unit 113 will now be described in more detail. The image analysis unit 113 includes a cross-section detection unit 1131 , a lean meat detection unit 1132 , a feature region extraction unit 1133 , and a binarization unit 1134 .

[0030] <Cross-section detection unit 1131> The cross-section detection unit 1131 reads out a meat image from the image information storage unit 132. The cross-section detection unit 1131 performs image analysis on the meat image to detect a cross-sectional area of ​​a block of meat in the meat image. The cross-section detection unit 1131 stores, in the image information storage unit 132, information on a block of meat cross-section area that indicates the cross-sectional area of ​​the block of meat detected from the meat image in association with the meat image.

[0031] <Lean Meat Detector 1132> The lean meat detection unit 1132 reads out a meat image and meat green cross-sectional area information from the image information storage unit 132. The lean meat detection unit 1132 detects a lean meat area representing a lean meat part in the meat green cross-sectional area based on the meat image and the meat green cross-sectional area information. For example, the lean meat detection unit 1132 detects a fatty meat area representing a fatty meat part in the meat green cross-sectional area. Specifically, the lean meat detection unit 1132 detects, for example, a white part area in the meat image that continues from the end of the meat green cross-section toward the center of the meat green cross-sectional area as the fatty meat area. Then, the lean meat detection unit 1132 detects, as the lean meat area, an area in the meat green cross-sectional area excluding the fatty meat area. The lean meat detection unit 1132 stores lean meat area information representing the lean meat area in the image information storage unit 132 in association with the meat image.

[0032] <Feature region extraction unit 1133> The characteristic region extraction unit 1133 reads out the meat image and lean meat region information from the image information storage unit 132. The characteristic region extraction unit 1133 extracts a characteristic region from the lean meat region. For example, the characteristic region extraction unit 1133 extracts a characteristic region at a random position within the lean meat region by cutting out a region of a predetermined size. The characteristic region extraction unit 1133 stores the characteristic region information representing the characteristic region in the image information storage unit 132 in association with the meat image.

[0033] <Binarization unit 1134> The binarization unit 1134 reads out the meat image and characteristic region information from the image information storage unit 132. The binarization unit 1134 generates a histogram by inverting and binarizing the image of the characteristic region in the meat image. The binarization unit 1134 stores the distribution of pixel values ​​of the generated histogram as meat appearance data in the meat chunk information storage unit 133 in association with the meat image.

[0034] <Specific part 114> The identification unit 114 has a function of associating the analysis results with sensory information based on the image analysis results and statistical information. For example, the identification unit 114 identifies analytical information corresponding to a meat image. The identification unit 114 identifies sensory information corresponding to the meat image. The identification unit 114 associates the identified analytical information with the sensory information and stores them in the storage unit 130.

[0035] <Output processing unit 115> The output processing unit 115 has a function of controlling information output. For example, the output processing unit 115 causes the output unit 150 to output output information in which analytical information and sensory information corresponding to a meat image are associated with each other.

[0036] <Storage section 130> The storage unit 130 has a function of storing various types of information. The storage unit 130 includes an analysis information storage unit 131 , an image information storage unit 132 , a chunk of meat information storage unit 133 , a sensory information storage unit 134 , and a statistical information storage unit 135 .

[0037] <Analysis information storage unit 131> The analytical information storage unit 131 stores analytical information (see FIG. 4). The analytical information is information in which production area information and scientific data, which are the results of physicochemical analysis, are associated with each block of meat.

[0038] <Image information storage unit 132> The image information storage unit 132 stores image information (see FIG. 5) including image data of meat images.

[0039] <Meat loaf information storage section 133> The green meat information storage unit 133 stores green meat information (see FIG. 6) in which a meat image is associated with appearance data of the meat.

[0040] <Sensory information storage unit 134> The sensory information storage unit 134 stores sensory information (see FIG. 7).

[0041] <Statistical information storage section 135> The statistical information storage unit 135 stores the learning results and statistical information (see FIG. 8).

[0042] Next, a specific example of the processing of the image analysis unit 113 will be described with reference to FIG.

[0043] <Image analysis processing> The processing of the image analysis unit 113 will be described in more detail with reference to Fig. 3. Fig. 3 is a diagram showing an example of a meat image according to this embodiment. The illustrated example is an example of a meat image BMP. The meat image BMP is stored in the image information storage unit 132. First, the cross-section detection unit 1131 detects a chunk of meat cross-sectional region BM from the meat image BMP. The lean meat detection unit 1132 detects a fatty region SB in the chunk of meat cross-sectional region BM. Specifically, the lean meat detection unit 1132 detects a continuous white region from the end of the chunk of meat cross-sectional region BM as a fatty region SB. The lean meat detection unit 1132 detects a region excluding the fatty region SB from the chunk of meat cross-sectional region BM as a lean meat region AK. The feature region extraction unit 1133 cuts out a feature region SM of a predetermined size at a random position in the lean meat region AK. The binarization unit 1134 generates appearance data representing the appearance of the meat based on the meat image of the feature region SM.

[0044] Next, examples of the analytical information, image information, chunk of meat information, sensory information, and statistical information stored in the storage unit 130 will be described with reference to FIGS.

[0045] <Analysis information> FIG. 4 is a diagram illustrating an example of analysis information according to the present embodiment. The analysis information is stored in the analysis information storage unit 131. The analysis information is information in which an individual identification number, place of production, part, and scientific data are associated with a lump of meat ID. The lump of meat ID is identification information for identifying a lump of meat. The individual identification information is identification information for identifying a cow raised in the country. The place of production is information on the place of production of the meat associated with the individual identification number. The part is information indicating which part of the cow the lump of meat indicated by the lump of meat ID is from. The scientific data indicates the results of physicochemical analysis of the lump of meat.

[0046] For example, the first line indicates that when the "Meat Block ID" is "DEFG1", the "Individual Identification Number" is "Z987", the "Place of Origin" is "Matsusaka", the "Part" is "Sirloin", and the "Scientific Data" is "δ=X,···".

[0047] <Image information> FIG. 5 is a diagram showing an example of image information according to this embodiment. The image information is stored in the image information storage unit 132. The image information is information in which an image ID is associated with image data, meat chunk region information, lean meat region information, and characteristic region information. The image ID is identification information for identifying the meat image. The image data is data of the meat image. The meat chunk region information, lean meat region information, and characteristic region information are information indicating the meat chunk region, lean meat region, and characteristic region in the meat image.

[0048] For example, in the first line, when the "image ID" is "V123", the "image data" is associated with "V123.gif". Furthermore, the "image ID" is associated with "meat chunk region information", "lean meat region information", and "characteristic region information", such as coordinate information within the image.

[0049] <Meat loaf information> FIG. 6 is a diagram showing an example of green meat information according to this embodiment. The green meat information is stored in the green meat information storage unit 133. The green meat information is information in which a green meat ID is associated with an image ID and appearance data. The appearance data is data that represents the appearance of a cross section of the meat. For example, the first line indicates that when the "Meat Block ID" is "DEFG1", the "Image ID" is "V123" and the "Appearance Data" is "A12345.cvs".

[0050] <Sensory information> FIG. 7 is a diagram showing an example of sensory information according to this embodiment. The sensory information is stored in the sensory information storage unit 134. The sensory information is information in which a block of meat ID is associated with an image ID, appearance data, a store ID, and taste data. The store ID is identification information that identifies a store. For example, the store is a store that has registered a meat image of a block of meat. The taste data is sensory information for the block of meat. For example, it is information that represents the taste of a user who has eaten the block of meat corresponding to the meat image. The taste data is expressed on a five-point scale, for example, from "★" to "★★★★★". For example, "★★★★★" indicates a higher rating than "★".

[0051] For example, in the first line, when the "Meat Block ID" is "EFGH1", the "Image ID" is "V987", the "Appearance Data" is "A12346.cvs", the "Store ID" is "T876", and the "Taste Data" is "★★★★★".

[0052] <Statistics> FIG. 8 is a diagram showing an example of statistical information according to this embodiment. The statistical information is stored in the statistical information storage unit 135. The statistical information is information in which individual identification information, place of production, part, scientific data, taste ID, and taste data are associated with a block of meat ID. The taste ID is identification information for identifying the sensory information registered for each block of meat.

[0053] For example, in the first line, when the "Meat Block ID" is "DEFG1", the "Individual Identification Number" is "Z987", the "Place of Origin" is "Matsusaka", the "Part" is "Sirloin", the "Scientific Data" is "δ=X,···", the "Taste ID" is "U123", and the "Taste Data" is "★★★★★". In the illustrated example, multiple taste data are registered for the same green meat. In this case, the average value of the taste data having the same green meat ID may be associated with the analysis information.

[0054] Next, the processing flow will be described.

[0055] <Processing flow> FIG. 9 is a flowchart showing an example of processing in the information processing device 1 according to this embodiment. As shown in FIG. 9, first, the meat chunk image acquisition unit 1112 of the information processing device 1 acquires a meat image (step S101). Furthermore, the sensory information acquisition unit 1113 of the information processing device 1 acquires sensory information (step S102). Next, the image analysis unit 113 performs image analysis on the meat image (step S103). Specifically, the image analysis unit 113 extracts an image of a characteristic region based on the meat image. Then, the image analysis unit 113 generates appearance data based on the image of the characteristic region. Next, the identification unit 114 identifies analytical information corresponding to the meat image based on the image analysis result analyzed by the image analysis unit 113 and the statistical information stored in the statistical information storage unit 135, and associates the analytical information with the sensory information (step S104).

[0056] For example, the identification unit 114 identifies analytical information having a lump of meat ID that matches the lump of meat ID of the meat image. The identification unit 114 identifies sensory information having a lump of meat ID that matches the lump of meat ID of the meat image. The identification unit 114 associates the identified analytical information with the sensory information. That is, the identification unit 114 associates the analytical information with the sensory information using the lump of meat ID. Furthermore, when the identification unit 114 cannot identify sensory information using the lump of meat ID of the meat image, the identification unit 114 identifies sensory information having appearance data that is the same as or similar to the appearance data of the meat image. The identification unit 114 associates the identified sensory information with analytical information that corresponds to the lump of meat ID of the meat image.

[0057] As described above, the information processing device 1 according to this embodiment includes an acquisition unit (analysis information acquisition unit 1111) that acquires first appearance data representing the appearance of a first meat that is associated with physicochemical analysis information (analysis information) for the first meat, an image acquisition unit (meat chunk image acquisition unit 1112) that acquires an image of a second meat, an information acquisition unit (sensory information acquisition unit 1113) that acquires sensory information for the second meat, an image analysis unit 113 that generates second appearance data representing the appearance of the second meat based on the image, and an identification unit 114 that associates the physicochemical analysis information with the sensory information based on the first appearance data and the second appearance data.

[0058] This allows the information processing device 1 to associate analytical information with sensory information based on the appearance data of the meat. Furthermore, even for meat with insufficient traceability, the analytical information can be associated with sensory information, thereby improving traceability.

[0059] Second Embodiment In the second embodiment, an example of a case where meat is provided in a store and sensory information is efficiently collected from users who eat the meat will be described. Specifically, in the second embodiment, a case where, for example, an incentive is given to collect sensory information will be described. Note that in the second embodiment, differences from the first embodiment will be mainly described.

[0060] <Configuration of information processing device 1A> FIG. 10 is a block diagram showing an example of the functional configuration of an information processing device 1A according to this embodiment. The information processing device 1A includes a control unit 110A, a storage unit 130A, an output unit 150, and a communication unit 190. The control unit 110A includes an acquisition unit 111, a statistics unit 112, an image analysis unit 113, an identification unit 114, an output processing unit 115, and an assignment unit 116A. The storage unit 130A includes an analysis information storage unit 131, an image information storage unit 132, a meat chunk information storage unit 133, a sensory information storage unit 134, a statistical information storage unit 135, and an incentive information storage unit 136A.

[0061] <Giving unit 116A> The granting unit 116A reads out incentive information stored in the incentive information storage unit 136A. The incentive information is information configured from setting information (see FIG. 11), order information (see FIG. 12), and grant information (see FIG. 13). The setting information is information for setting a product and an incentive to be granted for that product. The order information is information for identifying a product ordered by a user at a store. The granting information is information in which a product is associated with the user's sensory information for that product. The granting unit 116A extracts order information including the product eligible for the incentive included in the setting information. The granting unit 116A extracts grant information including sensory information for the target product by the user identified by the order information. The granting unit 116A grants the incentive for the target product set in the setting information to the user identified by the grant information. The granting unit 116A associates the meat lump ID of the target product to which the incentive has been granted with the sensory information for the target product and stores them in the sensory information storage unit 134.

[0062] <Incentive Information Storage Unit 136A> The incentive information storage unit 136A stores incentive information. The configuration of the incentive information will be described with reference to Figs. 11, 12, and 13. Fig. 11 is a diagram showing an example of the configuration of setting information according to this embodiment. Fig. 12 is a diagram showing an example of the configuration of order information according to this embodiment. Fig. 13 is a diagram showing an example of the configuration of grant information according to this embodiment.

[0063] <Setting information> The setting information is information in which a chunk of meat ID, a product ID, and an incentive are associated with each other. For example, the setting information is information set by a store employee. The chunk of meat ID included in the setting information is, for example, identification information associated with a meat image photographed in advance by a store employee. The product ID is identification information that identifies a product that uses the chunk of meat identified by the chunk of meat ID. The incentive ID is identification information that identifies the content of the incentive to be granted.

[0064] In the example shown in FIG. 11, the first line indicates that when the "lump of meat ID" is "C765", the "product ID" is "P36790" and the "incentive ID" is "I9435".

[0065] Here, the content of the incentive is identified by referring to content information (not shown) in which the "incentive ID" and the "incentive content" are associated, but in this embodiment, the content information is described as being included in the setting information.

[0066] <Order Information> The order information is information in which an order ID, a product ID, and a user ID are associated with each other. As shown in Fig. 12, for example, an order identified by an order ID indicates that a user identified by a user ID has ordered a product identified by the product ID. The order information is generated each time a product is ordered by a user. For example, for an order to be assigned by the assigning unit 116A, the product ID included in the setting information is included in the order information.

[0067] <Additional information> The assigned information is information in which a product ID, a taste ID, taste data, and a user ID are associated with each other. The example shown in Fig. 13 indicates that a user with a "user ID" of "U6798" has registered "taste data" of a product with a "product ID" of "P36790" as "★★★★★." The assigned information is generated, for example, by a user registering sensory information for a product to which a product ID has been assigned.

[0068] Next, an example of a display screen relating to incentive settings will be described.

[0069] <Example of incentive setting screen> 14A, 14B, 14C, and 14D are diagrams showing examples of display screens for setting incentive information according to this embodiment. The example display screens shown in the figures transition in the order of 14A, 14B, 14C, and 14D.

[0070] The example illustrated in FIG. 14A is an example screen displayed on a setting terminal, such as a tablet terminal, when a store employee sets the terminal to incentive setting mode. When the incentive setting mode is set, a "Menu Setting" screen is displayed on the terminal. The "Menu Setting" screen includes a menu selection box (not shown). The menu selection box is an operator for setting some or all of the menu items offered at the store. The menu selection box displays, for example, a list of selectable menu items. For example, a store employee selects the menu "Matsuzaka Beef Steak" in the menu selection box. The "Menu Setting" screen displays the selected menu item "Matsuzaka Beef Steak," an image of the menu item, for example, an image of "Matsuzaka Beef Steak," and the price of the "Matsuzaka Beef Steak" (3,000 yen). The "Menu Setting" screen also displays an operator "Coupon Setting" for setting incentives for the selected menu item, such as coupons. For example, when a store employee taps the operator "Coupon Setting" on the "Menu Setting" screen shown in FIG. 14A, the terminal displays the example screen shown in FIG. 14B.

[0071] The example shown in FIG. 14B is an example of a "Coupon Settings" screen that is displayed on the terminal device when an operation on the "Coupon Settings" operator is detected on the example screen shown in FIG. 14A. The "Coupon Settings" screen displays a condition selection box (not shown), a content selection box (not shown), and a meat block selection box (not shown). The condition selection box is an operator for setting conditions for granting a coupon. For example, the condition selection box displays a plurality of selectable conditions for granting a coupon that have been set in advance. The content selection box is an operator for setting coupon contents. For example, the content selection box displays selectable coupon contents that have been set in advance. The meat block selection box is an operator for setting a meat block to be used in the menu set in FIG. 14A. For example, the meat block selection box displays a selectable image of meat that has been photographed in advance at the store.

[0072] The "Coupon Settings" screen displays the "Conditions," "Contents," and "Selected Cut of Meat" selected by each operator. The "Coupon Settings" screen shown in FIG. 14B is displayed on the terminal device based on the selection of "Conditions" and "Taste Response" in the condition selection box, "Contents" and "200 yen discount" in the content selection box, and "Selected Cut of Meat" and "V543.gif" in the cut of meat selection box. The "Coupon Settings" screen also displays a "Confirm" operator (not shown) for confirming each selected item. When a store employee taps the "Confirm" operator on the "Coupon Settings" screen, the terminal device displays the example screen shown in FIG. 14C.

[0073] The example shown in FIG. 14C is an example of a "Settings" screen that is displayed on the terminal device when an operation on the "Confirm" operator (not shown) is detected on the example screen shown in FIG. 14B. In the illustrated example, the "Settings" screen displays the menu set in FIG. 14A, the coupon details set in FIG. 14B, and a meat image corresponding to the cut of meat set in FIG. 14B. The "Settings" screen also displays a "Settings" operator (not shown) for confirming each selected item. When a store employee taps the "Settings" operator on the "Settings" screen, the terminal device displays the example screen shown in FIG. 14D.

[0074] The example shown in Figure 14D is a "Settings Complete" screen indicating that the incentive has been set according to Figures 14A, 14B, and 14C. The terminal device displays the text "Menu set" as the "Settings Complete" screen.

[0075] For example, the "product ID" "P36790" in the setting information shown in FIG. 11 corresponds to the product ID of the menu item "Matsusaka Beef Steak" set in FIGS. 14A, 14B, 14C, and 14D. Furthermore, for example, the "incentive ID" "I9435" in FIG. 11 corresponds to the "incentive content" in the corresponding content information, which corresponds to the condition "taste response" and the content "200 yen discount" set in FIGS. 14A, 14B, 14C, and 14D. Furthermore, for example, the "chunk of meat ID" "C765" in the setting information shown in FIG. 11 corresponds to the chunk of meat ID of the chunk of meat "V543.gif" set in FIGS. 14A, 14B, 14C, and 14D.

[0076] Next, an example of a display screen relating to incentive awarding will be described.

[0077] <Example of incentive awarding screen> 15A, 15B, 15C, and 15D are diagrams showing examples of display screens when incentives are awarded according to this embodiment. The example display screens shown in the figures transition in the order of 15A, 15B, 15C, and 15D.

[0078] The example shown in FIG. 15A is an example of a screen displayed on an order terminal, such as a tablet terminal, used by a customer at a restaurant. The example shown in FIG. 15A is an "Order History" screen that is displayed when a customer checks their order history on the order terminal after their meal. In the example shown, an order history is displayed indicating that the customer ordered "Matsusaka Beef Steak." The "Order History" screen also displays a "Checkout" operator for transitioning between screens. Here, it is assumed that a coupon is set for the menu item "Matsusaka Beef Steak" as shown in FIGS. 14A, 14B, 14C, and 14D. When the customer has finished checking the order history and operates the "checkout" button in FIG. 15A, the order terminal displays the example screen in FIG. 15B.

[0079] The example shown in Figure 15B is an example of a screen that is displayed when a product ID for which a coupon is set exists among the product IDs included in the customer's order history. The example screen shown is displayed based on the conditions and content of the coupon. For example, if the settings are as shown in Figures 14A, 14B, 14C, and 14D, the screen will display the conditions and content, such as "There is a coupon. Would you like to answer the survey?" and "Complete the survey to get 200 yen off your bill." The screen also displays controls "Yes" and "No" (neither shown) that indicate the customer's intention regarding answering the survey. When the "No" control is operated, the order terminal displays a standby screen (not shown). On the other hand, when the "Yes" control is operated, the order terminal displays the example screen shown in Figure 15C.

[0080] The example illustrated in FIG. 15C is an example of a "Survey Response" screen for accepting "Survey Responses." The "Survey Response" screen displays response input boxes for the items "Gender," "Age," and "Overall Taste Rating." The response input box for the "Gender" item is an operator for setting the customer's gender, etc. For example, the response input box for the "Gender" item displays "Male," "Female," and "No Answer" as selectable options for input. The input response box for the "Age" item is an operator for setting the customer's age or generation. For example, the input response box for the "Age" item prompts the customer to enter a character string representing the customer's age or generation. The response input box for the "Overall Taste Rating" item is an operator for setting sensory information for the coupon-eligible product. For example, the response input box for the "Overall Taste Rating" prompts the user to enter the result of evaluating the taste on a five-point scale. Specifically, the response input box for the "Overall Taste Rating" prompts the user to enter the taste using the number of stars. After receiving input for each item and operating the "Answer" button to finalize the questionnaire response, the order terminal displays the example screen shown in FIG. 15D.

[0081] The example shown in Figure 15D is an example of a "Complete" screen that is displayed when the questionnaire responses, i.e., the registration of sensory information, are completed and the coupon is issued normally. In the example shown, the "Complete" screen displays "Thank you for your responses" on the order terminal.

[0082] For example, the order history shown in FIG. 15A corresponds to the order identified by the order ID in the order information shown in FIG. 12. The "Matsusaka Beef Steak" included in the order history shown in FIG. 15A corresponds to the product ID in the order information shown in FIG. 12 and the assigned information shown in FIG. 13. The customer attribute information of gender and age shown in FIG. 15C corresponds to the attribute information (not shown) associated with the user ID in the assigned information shown in FIG. 13. The sensory information shown in FIG. 15C corresponds to the taste data in the assigned information shown in FIG. 13.

[0083] Next, the processing flow will be described.

[0084] <Processing flow> FIG. 16 is a flowchart showing an example of processing in the information processing device 1A according to this embodiment. As shown in the figure, first, the meat block image acquisition unit 1112 of the information processing device 1A acquires meat images (step S201). Here, the meat images acquired in step S201 include meat images of meat blocks used in menus provided in the restaurant. Next, the image analysis unit 113 of the information processing device 1A performs image analysis on the meat images (step S202). Specifically, the image analysis unit 113 extracts images of characteristic regions based on the meat images. Then, the image analysis unit 113 generates appearance data based on the images of the characteristic regions. Next, the identification unit 114 identifies analysis information corresponding to the meat images based on the image analysis results analyzed by the image analysis unit 113 and the statistical information stored in the statistical information storage unit 135, and associates the analysis information with the meat block information (step S203).

[0085] The granting unit 116A of the information processing device 1A sets an incentive based on the setting information stored in the incentive information storage unit 136A (step S204). The sensory information acquisition unit 1113 of the information processing device 1A acquires the sensory information (step S205). The granting unit 116A grants an incentive to the user who registered the sensory information based on the incentive information stored in the incentive information storage unit 136A (step S206). For example, the identification unit 114 identifies analysis information having a lump of meat ID that matches the lump of meat ID of the meat image. The identification unit 114 identifies sensory information having a lump of meat ID that matches the lump of meat ID of the meat image. The identification unit 114 associates the identified analysis information with the sensory information (step S207).

[0086] As described above, the information processing device 1A according to this embodiment includes an acquisition unit (analysis information acquisition unit 1111) that acquires first appearance data representing the appearance of a first meat that is associated with physicochemical analysis information (analysis information) for the first meat, an image acquisition unit (meat chunk image acquisition unit 1112) that acquires an image of a second meat, an information acquisition unit (sensory information acquisition unit 1113) that acquires sensory information for the second meat, an image analysis unit 113 that generates second appearance data representing the appearance of the second meat based on the image, and an identification unit 114 that associates the physicochemical analysis information with the sensory information based on the first appearance data and the second appearance data.

[0087] This allows the information processing device 1A to associate analytical information with sensory information based on the appearance data of the meat. Furthermore, even for meat with insufficient traceability, the analytical information can be associated with sensory information, thereby improving traceability.

[0088] The restaurant further includes a granting unit 116A that grants an incentive, and grants an incentive to a customer based on the acquired sensory information of the customer.

[0089] This allows for efficient collection of sensory information about the block of meat, thereby reducing bias in sensory information due to customer preferences.

[0090] Third Embodiment In the third embodiment, an example of estimating the production location of a cut of meat based on the analytical information and the sensory information associated with each other in the first embodiment will be described. In the third embodiment, differences from the first embodiment will be mainly described.

[0091] <Configuration of information processing device 1B> FIG. 17 is a block diagram showing an example of the functional configuration of an information processing device 1B according to this embodiment. Information processing device 1B includes a control unit 110B, a storage unit 130, an output unit 150, and a communication unit 190. Control unit 110B includes an acquisition unit 111, a statistics unit 112, an image analysis unit 113B, an identification unit 114, an output processing unit 115, and a determination unit 117B. Image analysis unit 113B includes a cross-section detection unit 1131, a red meat detection unit 1132, a feature region extraction unit 1133, a binarization unit 1134, and an edge detection unit 1135B.

[0092] <Edge detection unit 1135B> The edge detection unit 1135B reads out the meat image and the characteristic region information from the image information storage unit 132. The edge detection unit 1135B performs edge detection for each image of the characteristic region in the meat image, and detects marbling feature amounts such as the shape of the marbling within the characteristic region, the distribution of the marbling within the characteristic region, and the distribution rate of the marbling within the characteristic region. The edge detection unit 1135B stores the marbling feature amounts as marbling feature data in the meat chunk information storage unit 133 in association with the meat image.

[0093] <Judgment section 117B> The determination unit 117B reads out the chunk of meat information stored in the chunk of meat information storage unit 133 and estimates analytical information of the chunk of meat based on the marbling characteristics of the chunk of meat. The determination unit 117B identifies a meat image associated with marbling characteristic data that represents the marbling characteristics of the chunk of meat and the same or similar marbling characteristic data. The determination unit 117B estimates the analytical information associated with the identified meat image as sensory information of the chunk of meat.

[0094] Furthermore, the determination unit 117B reads out the chunk of meat information stored in the chunk of meat information storage unit 133, and estimates the place of production of the chunk of meat based on the marbling characteristics of the chunk of meat. Specifically, the determination unit 117B identifies a meat image in which marbling characteristic data that represents the marbling characteristics of the chunk of meat is associated with the same or similar marbling characteristic data. The determination unit 117B refers to the analysis information associated with the identified meat image, and estimates that the production place information included in the analysis information is the place of production of the chunk of meat.

[0095] Furthermore, the determination unit 117B reads out the chunk of meat information stored in the chunk of meat information storage unit 133, and estimates the sensory information of the chunk of meat based on the marbling characteristics of the chunk of meat. The determination unit 117B identifies a meat image in which marbling characteristic data representing the marbling characteristics of the chunk of meat and the same or similar marbling characteristic data are associated. The determination unit 117B refers to the analysis information associated with the identified meat image, and estimates the sensory information associated with the analysis information as the sensory information of the chunk of meat.

[0096] Furthermore, the determination unit 117B identifies the marbling characteristic data, which indicates the characteristics of the marbling of the block of meat, and the appearance data of the meat associated with the same or similar marbling characteristic data. The determination unit 117B references the analytical information associated with the identified appearance data, and estimates the place of production information included in the analytical information as the place of production information of the block of meat. The determination unit 117B also references the analytical information associated with the identified appearance data, and estimates the sensory information included in the analytical information as the sensory information of the block of meat.

[0097] The determination unit 117B stores the estimated information in the storage unit .

[0098] <Meat loaf information storage section 133> The green meat information storage unit 133 stores green meat information (see FIG. 18) in which the image of the meat is associated with the appearance data and marbling characteristic data of the meat.

[0099] <Meat loaf information> FIG. 18 is a diagram showing an example of green meat information according to this embodiment. As shown in the figure, the green meat information is stored in the green meat information storage unit 133. The green meat information is information in which a green meat ID is associated with an image ID, appearance data, and marbling characteristic data. The appearance data is data that represents the appearance of a cross section of the meat.

[0100] Next, the processing flow will be described.

[0101] <Processing flow> FIG. 19 is a flowchart showing an example of processing in the information processing device 1B according to this embodiment. First, the information processing device 1B executes the processes of steps S101 to S104. Then, as shown in Fig. 19, the process of step S301 is executed. The edge detection unit 1135B reads out the meat image and feature region information from the image information storage unit 132 and detects the feature amount of marbling. The edge detection unit 1135B stores marbling feature data indicating the feature amount of marbling in the chunk of meat information storage unit 133 in association with the meat image (step S301).

[0102] The determination unit 117B identifies a meat image in which the marbling characteristic data representing the characteristics of the marbling of the block of meat and the same or similar marbling characteristic data are associated, or the determination unit 117B identifies meat appearance data in which the marbling characteristic data representing the characteristics of the marbling of the block of meat and the same or similar marbling characteristic data are associated (step S302).

[0103] The determination unit 117B estimates the analytical information associated with the specified meat image as the sensory information of the green meat. The determination unit 117B references the analytical information associated with the specified meat image and estimates the production area information included in the analytical information as the production area of ​​the green meat. The determination unit 117B references the analytical information associated with the specified meat image and estimates the sensory information associated with the analytical information as the sensory information of the green meat. Alternatively, the determination unit 117B references the analytical information associated with the specified appearance data and estimates the production area information included in the analytical information as the production area information of the green meat. Furthermore, the determination unit 117B references the analytical information associated with the specified appearance data and estimates the sensory information included in the analytical information as the sensory information of the green meat (step S303).

[0104] As described above, the information processing device 1B according to this embodiment includes an image acquisition unit (chunk of meat image acquisition unit 1112) that acquires an image of meat, an image analysis unit 113B that analyzes the image of meat, and an estimation unit (determination unit 117B) that estimates meat information based on the image analysis results.

[0105] This allows meat information about the meat to be obtained by acquiring an image of the meat, thereby improving traceability.

[0106] The meat information is information about the place of production of the meat. This allows us to estimate the origin of meat by acquiring an image of the meat, improving traceability and providing safety and security for meat.

[0107] The meat information is sensory information about meat. This allows the consumer to estimate the taste of the meat by acquiring an image of the meat, thereby improving convenience for the consumer.

[0108] The meat information is physicochemical analysis information of the meat. This allows us to estimate physicochemical analysis information of meat by acquiring images of the meat, which improves traceability and provides safety and security for meat.

[0109] The image analysis unit 113B calculates the feature amount of marbling of the block of meat in the meat image, and the estimation unit (determination unit 117B) estimates meat information based on the feature amount of marbling. This will improve traceability and provide safety and security for meat.

[0110] The image analysis unit 113B calculates appearance data of the block of meat in the meat image, and the estimation unit (determination unit 117B) estimates meat information based on the appearance data. This will improve traceability and provide safety and security for meat.

[0111] <Fourth embodiment> In the fourth embodiment, an example of presenting foods suitable for the quality of a block of meat or foods suitable for the meat from the producing area of ​​the block of meat will be described based on the sensory information and analytical information associated in the first embodiment. In the fourth embodiment, differences from the first embodiment will be mainly described, and other descriptions will be omitted.

[0112] <Configuration of information processing device 1C> FIG. 20 is a block diagram showing an example of the functional configuration of an information processing device 1C according to this embodiment. The information processing device 1C includes a control unit 110C, a storage unit 130, an output unit 150, and a communication unit 190. The control unit 110C includes an acquisition unit 111, a statistics unit 112, an image analysis unit 113, an identification unit 114, an output processing unit 115, a determination unit 117B, and a recommendation unit 118C.

[0113] <Recommendation Department 118C> The recommendation unit 118C estimates the meat quality of the meat image. Based on the appearance data and statistical information, the recommendation unit 118C estimates a part of meat having appearance data identical or similar to the appearance data of the block of meat as the meat quality of the block of meat. The recommendation unit 118C estimates a best-match food corresponding to meat identified by a block of meat ID of the same part as the part of meat as a food suitable for the meat quality of the block of meat in the meat image. The recommendation unit 118C also extracts a meat block ID of a production area corresponding to the production area of ​​the meat image from the statistical information. The recommendation unit 118C estimates recommended foods suitable for meat for each production area based on statistics of best-matched foods corresponding to the extracted meat block IDs of the production areas.

[0114] <Statistics> FIG. 21 is a diagram showing an example of statistical information according to this embodiment. The statistical information is information in which analytical information, recommended foods, and best-match foods are associated with each other. In this embodiment, best-match foods are associated with meat chunk IDs instead of the sensory information used in the first embodiment. For example, information on products ordered along with the target product is collected from the customer's order history, and the statistical information is generated by associating the best-match foods with the analytical information via the meat chunk ID. In addition, recommended foods corresponding to the production region are determined by performing statistical processing based on the best-match foods for meat chunk IDs from the same production region. In the illustrated example, the recommended food "wine" is a food suitable for the production region "Matsusaka," and the foods suitable for each part (meat quality) are the best-match foods.

[0115] <Processing flow> FIG. 22 is a flowchart showing an example of processing in the information processing device 1C according to this embodiment. First, the information processing device 1C executes the processes from step S101 to step S104, and then executes the process of step S401 as shown in FIG.

[0116] The determination unit 117B identifies a meat image associated with the appearance data of the green meat and the same or similar appearance data. The determination unit 117B references the analysis information associated with the identified appearance data and estimates the meat quality of the green meat based on the analysis information. The determination unit 117B also references the analysis information associated with the identified appearance data and estimates production location information of the green meat based on the analysis information (step S401). The recommendation unit 118C estimates the best-matched food corresponding to the part as a food suitable for the meat quality based on the estimation result and statistical information. Also, the recommendation unit 118C estimates the recommended food corresponding to the production area as a food suitable for the meat of the production area based on the estimation result and statistical information (step S402).

[0117] As described above, the information processing device 1C according to this embodiment includes an image acquisition unit (chunk of meat image acquisition unit 1112) that acquires an image of meat, an analysis unit (image analysis unit 113) that analyzes the image, and a presentation unit (recommendation unit 118C) that presents foods suitable for meat based on the analysis results.

[0118] This allows the user to know what foods are suitable to be eaten with chunks of meat, providing a more enjoyable dining experience.

[0119] Fifth Embodiment In the fifth embodiment, an example of estimating a consumer's preferred meat quality based on the analytical information and sensory information associated in the first embodiment will be described. In the fifth embodiment, differences from the first embodiment will be mainly described. Here, in the fifth embodiment, analytical information for each sample by the analytical information acquisition unit 1111 and sensory information on the consumer's meat by the sensory information acquisition unit 1113 may be acquired without acquiring a photographed image of the meat by the meat chunk image acquisition unit 1112.

[0120] <Configuration of information processing device 1> <Statistics Department 112> The statistical unit 112 generates a training dataset based on the analytical information stored in the storage unit 130 or the analytical information acquired by the analytical information acquisition unit 1111, and the sensory information stored in the storage unit 130 or the sensory information acquired by the sensory information acquisition unit 1113. The statistical unit 112 performs training based on the training dataset.

[0121] Specifically, the statistical unit 112 inputs sensory information preferred by consumers into a learning model that has learned the correspondence between analytical information and sensory information as training data, and obtains analytical information on the meat (meat quality) preferred by consumers as output.

[0122] The statistical unit 112 may generate a training data set that learns the correspondence between analytical information and sensory information, in addition to or instead of analytical information and sensory information, and / or production area information and / or rearing information. In this case, the statistical unit 112 may generate a training model by learning based on the training data set. In this case, when the statistical unit 112 inputs at least one of sensory information, analytical information, production area information and / or rearing information into the training model, analytical information and rearing information of meat (meat quality) preferred by consumers are output.

[0123] This allows producers to understand how to raise their animals to produce meat that consumers prefer.

[0124] Here, rearing information includes information such as information on feeding, information on feed, information on the rearing environment, information on climate, information on diseases, and birth information. Information on feeding includes information such as feeding date and time, feed amount, and water intake. Information on feed includes information on the type of feed and the feed blend ratio. Information on the rearing environment includes information on feeding methods such as feed and grazing, barn temperature, barn humidity, and type of grass in the pasture. Information on climate includes information on the temperature, humidity, and weather inside and outside the barn.

[0125] Next, the flow of processing by the information processing device 1 according to the fourth embodiment will be described.

[0126] <Processing flow> First, the sensory information acquisition unit 1113 of the information processing device 1 acquires sensory information. Next, the statistics unit 112 of the information processing device 1 inputs the acquired sensory information into a learning model that uses the sensory information and analytical information as training data, and thereby obtains analytical information as an output.

[0127] As described above, the information processing device 1 according to this embodiment includes a sensory information acquisition unit 1113 that acquires sensory information about meat, and a statistics unit 112 that obtains physicochemical analysis information about meat as an output by inputting the acquired sensory information about meat into a learning model that has learned the correspondence between the sensory information about meat and physicochemical analysis information about meat.

[0128] This allows producers to understand how to raise their animals to produce meat that consumers prefer.

[0129] Sixth Embodiment In the sixth embodiment, an example will be described in which foods suitable for the quality of a block of meat, foods suitable for meat from the producing area of ​​the block of meat, or cooking methods suitable for the quality of the block of meat are presented based on the sensory information and analytical information associated in the first embodiment. In the sixth embodiment, differences from the fourth embodiment will be mainly described, and other descriptions will be omitted.

[0130] <Configuration of information processing device 1C> The information processing device 1C includes a control unit 110C, a storage unit 130, an output unit 150, and a communication unit 190. The control unit 110C includes an acquisition unit 111, a statistics unit 112, an image analysis unit 113, an identification unit 114, an output processing unit 115, a determination unit 117B, and a recommendation unit 118C.

[0131] <Recommendation Department 118C> The recommendation unit 118C estimates the meat quality of the meat image. Based on the appearance data and statistical information, the recommendation unit 118C estimates a part of meat having appearance data identical or similar to the appearance data of the block of meat as the meat quality of the block of meat. The recommendation unit 118C estimates a best-match food corresponding to meat identified by a block of meat ID of the same part as the part of meat as a food suitable for the meat quality of the block of meat in the meat image.

[0132] The recommendation unit 118C also extracts a meat block ID of a production area corresponding to the production area of ​​the meat image from the statistical information. The recommendation unit 118C estimates recommended foods suitable for meat for each production area based on statistics of best-matched foods corresponding to the extracted meat block IDs of the production areas.

[0133] The recommendation unit 118C also estimates the meat quality of the meat image. Based on the appearance data and statistical information, the recommendation unit 118C estimates the part of meat having appearance data identical or similar to the appearance data of the block of meat as the meat quality of the block of meat. The recommendation unit 118C estimates the cooking method corresponding to the meat identified by the block of meat ID of the same part as the part of meat as the cooking method suitable for the meat quality of the block of meat in the meat image.

[0134] <Statistics> The statistical information is information in which the analytical information, recommended foods, and best-match foods shown in FIG. 21 are associated with each other, as well as the optimal cooking method and sensory information. In this embodiment, in addition to the sensory information in the first embodiment, best-match foods are associated with meat chunk IDs. For example, information on products ordered along with the target product is collected from the customer's order history, and the statistical information is generated by associating the best-match foods with the analytical information and sensory information via the meat chunk ID. In addition, recommended foods corresponding to the production region are determined by performing statistical processing based on the best-match foods for meat chunk IDs from the same production region. In the illustrated example, the recommended food "wine" is a food suitable for the production region "Matsusaka," and foods suitable for each part (meat quality) are the best-match foods.

[0135] Furthermore, for example, the statistical information is generated by collecting information on products ordered along with the target product from the customer's order history, and associating the cooking method, analytical information, and sensory information via the meat block ID. Furthermore, the optimal cooking method is determined by performing statistical processing based on the cooking method and sensory information of meat block IDs with similar meat quality.

[0136] <Processing flow> First, the information processing device 1C executes the processes from step S101 to step S104, and then executes the process of step S401 as shown in FIG.

[0137] The determination unit 117B identifies a meat image associated with the appearance data of the green meat and the same or similar appearance data. The determination unit 117B references the analysis information associated with the identified appearance data and estimates the meat quality of the green meat based on the analysis information. The determination unit 117B also references the analysis information associated with the identified appearance data and estimates production location information of the green meat based on the analysis information (step S401).

[0138] Based on the estimation result and statistical information, recommendation unit 118C estimates that the best-matched food corresponding to the part is a food suitable for the meat quality. Furthermore, the recommendation unit 118C estimates that the recommended food items corresponding to the production area are foods suitable for meat from the production area, based on the estimation result and statistical information. Furthermore, the recommendation unit 118C estimates the optimum cooking method suited to the meat quality as the cooking method suited to the meat quality based on the estimation result and statistical information.

[0139] As described above, the information processing device 1C according to this embodiment includes an image acquisition unit (meat chunk image acquisition unit 1112) that acquires an image of meat, an analysis unit (image analysis unit 113) that analyzes the image, and a presentation unit that presents foods suitable for the meat and / or cooking methods suitable for the meat quality based on the analysis results.

[0140] This allows people to learn what foods go well with chunks of meat and how to cook them to suit the meat's texture, providing them with a more enjoyable experience of eating.

[0141] <Hardware configuration> The configuration of the information processing devices 1, 1A, 1B, and 1C will be described with reference to Fig. 23. Fig. 23 is a block diagram showing an example of the hardware configuration of the information processing devices 1, 1A, 1B, and 1C according to this embodiment. The information processing devices 1, 1A, 1B, and 1C each include a CPU 11, a drive unit 12, a storage medium 13, an input unit 14, an output unit 15, a ROM 16 (Read Only Memory), a RAM 17 (Random Access Memory), an auxiliary storage unit 18, and an interface unit 19. The CPU 11, the drive unit 12, the input unit 14, the output unit 15, the ROM 16, the RAM 17, the auxiliary storage unit 18, and the interface unit 19 are connected to one another via a bus.

[0142] The CPU 11 referred to here refers to a processor in general, and includes not only a device called a CPU in the narrow sense, but also, for example, a GPU, a DSP, etc. Furthermore, the CPU 11 referred to here is not limited to being realized by a single processor, but may be realized by combining multiple processors of the same or different types.

[0143] The CPU 11 controls the information processing devices 1, 1A, 1B, and 1C by reading and executing programs stored in the auxiliary storage unit 18, ROM 16, and RAM 17, and by reading various data stored in the auxiliary storage unit 18, ROM 16, and RAM 17 and writing the various data to the auxiliary storage unit 18 and RAM 17. The CPU 11 also reads various data stored in the storage medium 13 via the drive unit 12 and writes the various data to the storage medium 13. The storage medium 13 is a portable storage medium such as a magneto-optical disk, a flexible disk, or a flash memory, and stores various data.

[0144] The drive unit 12 is a device for reading out a storage medium 13 such as an optical disk drive or a flexible disk drive.

[0145] The input unit 14 is an input device such as a mouse, a keyboard, a touch panel, a power button, and a setting button.

[0146] The output unit 15 is an output device such as a display unit and a speaker.

[0147] The ROM 16 and RAM 17 store programs and various data for operating the various functional units of the display device 10.

[0148] The auxiliary storage unit 18 is a hard disk drive, a flash memory, or the like, and stores programs and various data for operating the functional units of the information processing devices 1, 1A, 1B, and 1C.

[0149] The interface unit 19 has a communication interface and is connected to the network NW by wire or wirelessly.

[0150] <Modification> Each embodiment of the present invention has been described above. Next, modified examples of the embodiments of the present invention will be described. Note that each modified example described below may be applied alone to each embodiment of the present invention, or may be applied in combination with each other to each embodiment of the present invention. Furthermore, each modified example may be applied in place of the configuration described in the embodiment of the present invention, or may be applied in addition to the configuration described in the embodiment of the present invention.

[0151] In each of the above embodiments, the image analysis unit may perform hyperspectral imaging on the meat image and calculate the distribution of fatty acids and unsaturated fatty acids in the meat block. Furthermore, the image analysis unit may calculate the distribution ratio of fatty acids and the distribution ratio of unsaturated fatty acids in the meat block based on the distribution of fatty acids and unsaturated fatty acids. In this case, the meat image is preferably an image captured by a hyperspectral camera.

[0152] The image analysis unit may also use near-infrared spectroscopy on the meat block image to identify amino acids and types of amino acids.

[0153] In each of the above embodiments, the image analysis section may extract a plurality of characteristic regions and perform image analysis using the average value of the characteristics of each of the extracted characteristic regions.

[0154] The above describes a modified example of the present invention. Note that some or all of the configurations of the information processing system and information processing device in the above-described embodiment may be implemented by a computer. In this case, a program for implementing the functions may be recorded on a computer-readable recording medium, and the program may be loaded into the computer system and executed. Note that the term "computer system" as used herein includes hardware such as an OS and peripheral devices. Furthermore, the term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into the computer system. Furthermore, the term "computer-readable recording medium" may also include media that dynamically store programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or telephone lines, or media that store programs for a fixed period of time, such as volatile memory within a computer system that serves as a server or client. The program may be designed to implement some of the functions described above, or may be capable of implementing the functions in combination with a program already stored in the computer system, or may be implemented using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0155] The embodiments of the present invention have been described in detail above with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes can be made within the scope of the gist of the present invention. [Explanation of symbols]

[0156] F Meat A Analysis Institute R Sensory Information BMP image C Consumer 1, 1A, 1B, 1C Information processing equipment 11 CPU 12 Drive section 13 Storage medium 14 Input section 15, 150 output section 16 ROM 17 RAM 18 Auxiliary storage 19 Interface section 110, 110A, 110B, 110C control unit 111 Acquisition Department 1111 Analysis information acquisition department 1112 Meat lump image acquisition unit 1113 Sensory Information Acquisition Unit 112 Statistics Department 113, 113B Image analysis department 1131 Cross-section detection unit 1132 Lean meat detection unit 1133 Feature Region Extraction Unit 1134 Binarization section 1135B Edge detection unit 114 Specific section 115 Output Processing Unit 116A Granting Department 117B Judgment section 118C Recommendation Department 130, 130A storage section 131 Analysis information storage unit 132 Image information storage unit 133 Meat lump information storage unit 134 Sensory Information Storage Unit 135 Statistical information storage unit 136A incentive information storage unit 190 Communications Department NW Network

Claims

1. a sensory information acquisition unit that acquires sensory information about meat; a statistical unit that outputs physicochemical analysis information for meat by inputting the acquired sensory information for meat into a learning model that has learned the correspondence between at least sensory information for meat and physicochemical analysis information for meat; An information processing system comprising:

2. the learning model is a learning model that has learned a correspondence relationship between sensory information on the meat, physicochemical analysis information on the meat, and breeding information on livestock animals, inputting the acquired sensory information about the meat into the learning model to obtain physicochemical analysis information about the meat and breeding information about livestock animals as outputs; The information processing system according to claim 1 .

3. The livestock animal breeding information is at least one of feed information regarding feed, breeding environment information regarding the breeding environment, disease information of livestock animals, birth information of livestock animals, and age information of livestock animals. The information processing system according to claim 2 .

4. a sensory information acquisition unit that acquires sensory information about meat; a statistical unit that outputs physicochemical analysis information for meat by inputting the acquired sensory information for meat into a learning model that has learned the correspondence between at least sensory information for meat and physicochemical analysis information for meat; An information processing device comprising:

5. An information processing method executed by a computer of an information processing device, a sensory information acquisition step of acquiring sensory information about meat; a statistical step of inputting the acquired sensory information about meat into a learning model that has learned the correspondence between at least the sensory information about meat and the physicochemical analysis information about meat, thereby obtaining the physicochemical analysis information about meat as an output; An information processing method comprising:

6. The computer of the information processing device a sensory information acquisition step of acquiring sensory information about meat; a statistical step of inputting the acquired sensory information about meat into a learning model that has learned the correspondence between at least the sensory information about meat and the physicochemical analysis information about meat, thereby obtaining the physicochemical analysis information about meat as an output; A program to execute.

Images