JP6280847B2 - Taste estimation device and taste estimation method, ranking device and ranking method, taste estimation program and ranking program - Google Patents

Description

  The present invention relates to a technique for quantitatively estimating a subjective sensation (taste) such as hotness or sourness, or ranking based on the estimated taste.

  There are various information providing services on the Internet, and the user can obtain information that serves as a reference for actions such as eating out and playing. For example, when eating out, it is possible to search for restaurants based on location, budget, store evaluation, and the like.

  If you can use subjective sense (taste) information, such as acidity and pungent taste, as a material for searching for restaurants like this, you can search for a menu of your favorite spiciness and search for restaurants that suit you more It becomes. About this point, the nonpatent literature 1 which investigated the relationship between taste stimulation and a heart rate is known.

Shimamura Muneo, Hoshino Kaori, “Responsiveness of Autonomic Nervous Function by Taste Stimulation”, Tokyo Kasei University Bulletin 37 (2), p. 51-58, 1997 “Development and practical application of functional material“ hitoe ”that enables continuous measurement of biological information just by wearing it” January 30, 2014 NTT Holding Company News Release, Internet <URL: http://www.ntt.co .jp / news2014 / 1401 / 140130a.html>

  If the knowledge of Non-Patent Document 1 is used, it is considered that subjective senses such as acidity and pungent taste can be quantitatively grasped from heartbeat variability.

  However, since the heart rate changes due to various factors such as behavior and environment, it is necessary to observe the heart rate variability after specifying a situation such as eating spicy food. Therefore, in real life, it is necessary to annotate the situation each time and estimate the pain, etc., which may be a heavy burden on the user.

  The present invention is made to solve such a conventional problem, and solves the problem of quantitatively estimating subjective sensations such as acidity and pungent taste in an easy method that does not burden the user (user). It is said.

  One aspect of the taste estimation apparatus of the present invention includes a history storage database that stores a user ID, store information, menu information, and taste information in association with each other, an input reception unit that receives a user ID of user input and store information, A user ID of a similar user whose taste information is similar to the user of the user ID received by the input reception unit is selected from the history storage database, and the taste information of the similar user with respect to the menu information of the store information received by the input reception unit is stored in the history storage database. And a display unit that associates the menu information and the taste information extracted by the estimation unit and presents them to the user.

  According to another aspect of the taste estimation apparatus of the present invention, a voice acquisition unit that acquires the user's utterance content, a biological information acquisition unit that acquires the user's biological information, and a meal start based on the utterance content acquired by the voice acquisition unit. An estimation unit that determines a timing and a timing at which a specific taste is felt and estimates a user's taste information from the determined biological information.

  One aspect of the ranking device of the present invention includes a history storage database that associates and stores user IDs, store information, menu information, and taste information, and stores taste information for each store information or menu information stored in the history storage database. A ranking unit that calculates an evaluation value and ranks store information or menu information based on the calculated evaluation value, and a display unit that presents the store information or menu information and the ranking of the information in association with each other.

  Another aspect of the ranking device according to the present invention includes a history storage database that stores a user ID, store information, menu information, and taste information in association with each other, and a taste corresponding to the menu information or store information received by the input receiving unit. A ranking unit that ranks user IDs based on taste information in an information database; and a display unit that presents user IDs and rankings in association with each other.

  According to one aspect of the taste estimation method of the present invention, an input reception step of receiving a user ID of user input and store information, and a history of user IDs of similar users whose taste information is similar to the user of the user ID received by the input reception unit An estimation step for extracting taste information of similar users for the menu information of the store information received from the storage database selected from the storage database from the history storage database, and the menu information and taste information extracted in the estimation step are associated with each other And a display step presented to the user.

  According to another aspect of the taste estimation method of the present invention, a voice acquisition step of acquiring the user's utterance content, a biological information acquisition step of acquiring the user's biological information, and a meal start based on the utterance content acquired in the voice acquisition step. An estimation step of determining a timing and a timing at which a specific taste is felt, and estimating the taste information of the user from the biological information at both determined timings.

  One aspect of the ranking method of the present invention is a ranking step of calculating an evaluation value of taste information for each store information or menu information held in the history accumulation database, and ranking the store information or menu information based on the calculated evaluation value. And a display step of presenting the store information or menu information and the ranking of the information in association with each other.

  In another aspect of the ranking method of the present invention, a ranking step of ranking user IDs based on taste information in taste information database corresponding to store information or menu information held in the history accumulation database, and correspondence between the user ID and the ranking And a display step to be presented.

  In addition, this invention is good also as an aspect of the program which makes a computer function as said apparatus. This program can be provided through a network or a recording medium.

  ADVANTAGE OF THE INVENTION According to this invention, subjective senses, such as a sour taste and a pungent taste, can be estimated quantitatively by the easy method which does not become a user's (user) burden.

The block diagram of the taste estimation apparatus which concerns on 1st Embodiment of this invention. The flowchart which shows the process of the same taste estimation apparatus. The block diagram of the taste estimation apparatus which concerns on 2nd Embodiment of this invention. (A) is an example of data held in the history storage database, (b) is an example of processing for complementing pain information based on user similarity, and (c) is an example of data held in the history storage database after complementation. The flowchart which shows the process of the same log | history storage part. The flowchart which shows the process of the estimation function part. Example of information presented to the user The block diagram of the ranking apparatus of the application example 1. FIG. The flowchart which shows the process of the ranking process part. (A) is an example of data held in the history storage database, (b) is an example of processing for calculating the average of the hotness for each menu, (c) a ranking result pattern 1, and (d) a ranking result pattern 2. The block diagram of the ranking apparatus of the application example 2. FIG. The flowchart which shows the process of the ranking process part. (A) is an example of data held in the history storage database, (b) is an example of processing for ranking users according to the hardness tolerance of the store menu, (c) is a ranking result pattern 1, and (d) is a ranking result pattern. 2

  Hereinafter, a taste estimation device according to an embodiment of the present invention will be described. Here, as an example, a case in which hotness is estimated among tastes (subjective sensations) will be described, but other tastes that can be estimated from heartbeats such as acidity and sweetness can be similarly processed. The instantaneous heart rate calculated from the time of one beat is simply called the heart rate. A value obtained by averaging several instantaneous heart rates may be used as the heart rate.

<< First Embodiment >>
Based on FIG. 1, the structural example of the taste estimation apparatus which concerns on 1st Embodiment of this invention is demonstrated. Here, it is assumed that the taste estimation apparatus 101 is connected to a microphone and a heart rate monitor (not shown) by wire / wireless.

  Specifically, the taste estimation device 101 is configured by a computer, and includes a CPU, a main storage device (RAM, ROM, etc.), an auxiliary storage device (hard disk drive device, solid state drive device, etc.), and the like.

  As a result of the cooperation between the hardware resource and the software resource (OS, application, etc.), the taste estimation apparatus 101 recognizes and acquires the user's individual speech from the microphone attached to the user, and A biometric information acquisition unit 120 that acquires a user's heart rate information (biological information) from a mounted heart rate meter, and an appropriate measurement timing is grasped from the acquired data of both the units 110 and 120, and the hardness is estimated from the heart rate variability value. A possible estimation unit 130 and a visualization unit 140 that presents information on the hotness estimated by the estimation unit 130 to the user are implemented. Hereinafter, specific processing contents of the taste estimation apparatus 101 will be described with reference to FIG. Here, the processing content of the estimation unit 130 will be mainly described.

  S210: When the process is started, the voice acquisition unit 110 and the biological information acquisition unit 120 continue to measure the voice and heart rate spoken by the user. The measurement data is sequentially sent to the estimation unit 130. Note that the measurement by the biological information acquisition unit 120 is based on the assumption that the user is wearing a biological sensor. As this biosensor, biometric information measurement wear using the functional material of Non-Patent Document 2 is mainly used.

  S220: The estimation unit 130 extracts both utterances related to the start of meal and hotness from the measurement data from the voice acquisition unit 110, that is, the utterances recognized by the voice acquisition unit 110. Here, as an utterance of the start of a meal, for example, “you will receive” is considered. Moreover, “spicy” can be considered as an utterance related to hotness.

  S230: The estimation unit 130 determines whether or not both utterances regarding the start and the hotness of the meal in S220 can be acquired, and the utterance interval between the two utterances is within 30 minutes. As a result of the determination, if this determination condition (both utterances can be acquired and the interval between both utterances is within 30 minutes) is not satisfied, the process ends. If the determination condition is satisfied, the process proceeds to S240.

S240: The estimation unit 130 acquires (1) the heart rate immediately after the user's meal start from the heart rate data acquired by the biometric information acquisition unit 120, and (2) the heart rate for one minute after the utterance related to spiciness. Calculate the difference between both heart rates. For example, if the heart rate immediately after the start of the meal is “x” and the heart rate calculated every second per minute after speaking is [y ₁ , y ₂ ,, y ₆₀ ], then “max (y _i −x)” The difference in heart rate can be calculated.

  S250: The estimation unit 130 converts the heart rate difference (maximum value) calculated in S240 into hotness, and uses the converted hotness as an estimated value. At this time, “spicy = difference in heart rate (maximum value)” may be used. Also, the difference between the degree of subjective pain and the heart rate obtained in advance by a questionnaire is learned, and the relational expression of the learning result is expressed as It may be used to convert the heart rate difference into hotness.

  S260: The visualization unit 140 presents the hotness estimated in S250 to the user, and ends the process. This presentation method may be displayed on the monitor of the taste estimation apparatus 101, or may be transmitted to a user terminal (PC, smartphone, etc.) (not shown) and displayed on the screen. As a result, the following effects can be obtained.

  That is, conventionally, when a subjective sense such as hotness or sourness, ie, taste, is quantitatively estimated using the heart rate, it is necessary to annotate the situation of “spicy food”. On the other hand, according to the taste estimation apparatus 101, the user does not need the annotations and uses the subjective sensation estimation because the user can grasp the heart rate measurement timing using the utterance contents naturally uttered by the user. Can be reduced.

  In addition, since a subjective feeling such as hotness can be easily estimated quantitatively, large-scale data can be collected and used by applying to various services such as hotness ranking of stores.

<< Second Embodiment >>
Based on FIG. 3, the structural example of the taste estimation apparatus which concerns on 2nd Embodiment is demonstrated. This taste estimation apparatus 301 is configured by a server (computer) on the Web, and creates a database of the intensity of taste (here, pungency) that a user feels when eating a menu at a store, and uses it for services on the Internet.

  That is, the intensity of hotness that is different for each user is stored in a database in association with a store or a menu, and by using this, the intensity of hotness of the store menu that is expected when the user eats is estimated.

  Here, the taste estimation apparatus 301 includes a history storage unit A that stores data in the history storage database 360 in advance, and an estimation function unit B that estimates the user's painfulness based on the history storage database. It may be configured on the same server or on separate servers.

(1) History storage unit A
As shown in FIG. 3, the history storage unit A includes a meal information input unit 310, a voice acquisition unit 320, a biological information acquisition unit 330, a position information acquisition unit 340, a determination unit 350, and a history storage database 360. It is assumed that the history accumulation database 360 is constructed in the storage device. Note that the voice acquisition unit 320 and the biometric information acquisition unit 330 perform the same processing as the voice acquisition unit 110 and the biometric information acquisition unit 120, and thus description thereof is omitted.

  The meal information input unit 310 receives a menu of a meal that the user eats and receives the input menu. The meal information input unit 310 is not an essential configuration but an arbitrary configuration.

  The position information acquisition unit 340 acquires the name of the store visited by the user. At that time, an input from the user may be accepted, or the store name can be automatically acquired using a GPS or a store information database prepared separately.

  Similar to the estimation unit 130, the determination unit 350 grasps an appropriate measurement timing based on the acquired data of the voice acquisition unit 320 and the biological information acquisition unit 330, and estimates painfulness from the heartbeat fluctuation value.

  The estimated value of hotness is stored in the history accumulation database 360 together with the acquired data of the meal information input unit 310 and the position information acquisition unit 340. As shown in FIG. 4A, the history accumulation database 360 has a store name as store information, a menu as meal information, and hotness data (a degree of hotness) as taste information for each user information. Number) and are saved. Hereinafter, specific processing contents of the history storage unit A will be described with reference to FIG.

  S510: When the process is started, the meal information input unit 310 and the position information acquisition unit 340 acquire a menu of meals to be eaten by the user, the name of the shop visited, and a user ID, and store them in the history accumulation database 360. At this time, the menu of the meal and the user ID may be directly input by the user, or may be automatically acquired based on the voice at the time of order input to the microphone.

  S520 to S570: In S520, the voice acquisition unit 320 and the biological information acquisition unit 330 execute the same processing as in S210. In S530 to S560, the determination unit 350 executes the same processing as in S220 to S250.

  S570: The determination unit 350 records and stores the pain estimated in S560 in the record of the corresponding user ID in the history accumulation database 360, and ends the process.

(2) Estimation function part B
The estimation function unit B presents a menu hotness estimation value to the user based on the data stored in the history accumulation database 360. That is, the hotness of the menu of the store unknown to the user of the input user ID is estimated using hotness data for the menu stored in the history storage database.

  As shown in FIG. 3, the estimation function unit B includes an input receiving unit 370 that receives a user ID input by a user through a user terminal (not shown) and a store name that the user wants to know the pain of the menu, and a history storage database 360. An estimation unit 380 that estimates the hotness of the menu of the store received by the input reception unit 370 based on the saved data, and a visualization unit 390 that transmits the hotness estimated by the estimation unit 380 to the user terminal and presents it to the user. Implement. Hereinafter, specific processing contents of the estimation function unit B will be described with reference to FIG.

  S610: The input receiving unit 370 is a user ID (hereinafter referred to as an input ID) input by operating a user terminal input means, for example, a keyboard (including a software keyboard), and the name of a store where the user wants to know the pain of the menu. (Hereinafter referred to as the input store name).

  S620: The estimation unit 380 tries to acquire another user ID (other user ID other than the input ID) for the menu of the input store from the history storage database 360.

  S630: The estimation unit 380 checks whether or not the other user ID has been acquired as a result of the attempt of S620. As a result of the confirmation, if the other user ID cannot be acquired, the process ends. If the other user ID can be acquired, the process proceeds to S640.

  S640: The estimation unit 380 calculates the similarity in pain between the user of the input user ID and the other user related to the user ID acquired in S620. For example, for each user, a vector may be created for the hotness data for each menu, and the cosine similarity of the created vector may be calculated.

  S650: The estimation unit 380 selects another user having the highest similarity calculated in S640 as a similar user. After this selection, the hotness data for the menu of the similar store input store name is acquired from the history accumulation database 360. At this time, if there are a plurality of menus, the hotness data of the plurality of menus is acquired.

  The similar user's hotness data acquired here is estimated as the user's hotness data of the input ID. The details will be described with reference to FIGS. 4B and 4C. First, the estimation unit 380 creates the intermediate file F1 of FIG. 4B based on the pain data of the other user acquired in S620.

  In the intermediate file F1, the hotness data of the menu is described for each user ID. A similar user is selected from the users with the user ID described here, and the hot data of the user with the input ID is complemented based on the hot data of the similar user. For example, in FIG. 4B, the hotness data “5” of the similar user with the user ID “0001” is described and supplemented with the hotness data of “xx curry” with the input ID “0003”.

  After this complementation, the data stored in the history accumulation database 360 is updated based on the description content of the intermediate file F1. For example, in FIG. 4C, the hotness data of the user menu “xx curry” relating to the input ID “0003” has the same numerical value “5” as the hotness data of the similar user relating to the user ID “0001”. The data has been added and updated.

  S660: The visualization unit 390 transmits the pain data estimated in S650 to the user terminal in association with the store and the menu. The information transmitted here is displayed on the screen of the user terminal and presented to the user, and the process ends. For example, as shown in FIG. 7, a menu and hotness data (numbers) can be displayed on the screen as “XX restaurant hotness information”.

  Therefore, according to the taste estimation apparatus 301, it is possible to construct a service on the Internet that can present the menu of an unknown store that the user wants to know. At this time, since a similar user is selected for each user, the hotness data based on the strength of the hotness of the user can be provided, which is beneficial for the user.

≪Application 1≫
An application example 1 of the taste estimation apparatus 301 will be described with reference to FIG. Here, the taste estimation device 301 is applied as a ranking device 801 that ranks the hotness intensity of a store menu based on data stored in the history accumulation database 360.

  The ranking device 801 includes a history accumulating unit A and a ranking processing unit C, and the history accumulating unit A is the same as the taste estimation device 301, and thus description thereof is omitted. The history storage unit A and the ranking processing unit C may be configured on the same server or may be configured on separate servers.

  The ranking processing unit C includes a ranking unit 870 that calculates the hotness ranking (ranking) of the store menu based on the data stored in the history accumulation database 360, and a display unit 880 that displays the ranking calculated by the ranking unit 870. To do.

  Specific processing contents of the ranking processing unit C will be described with reference to FIG. First, when the process is started, the ranking unit 870 calculates the average of the hotness data for each menu existing in the history accumulation database 360 (S910). At this time, the ranking unit 870 creates the intermediate file F2 of FIG. 10B based on the hotness data acquired from the history storage database 360.

  In the intermediate file F2, hotness data of each user ID is described for each menu, and an average value of hotness data for each described menu is calculated. The menu is ranked based on the average value calculated here, and the ranking list L1 of FIG. 10C is created. In the ranking list L1, rankings, store names, menus, and hotness data are associated.

  Next, the display unit 880 displays the ranking result and ends the process (S930). As this display format, the ranking list L1 can be transmitted to a user terminal (not shown) and displayed on the screen of the user terminal.

  Further, as shown in FIG. 10 (d), the ranking result may be mapped on a map displayed on the user terminal, or the hotness ranking within the region designated by the user or the designated category may be displayed. Good.

  According to such a ranking device 801, since the hotness ranking of the menu that the user wants to eat is presented based on the quantitatively estimated hotness data, an objective ranking can be presented to the user, which is useful on the Internet. Can be provided as a simple service.

  Note that the ranking device 801 can rank not only the menu hotness ranking but also the hotness of stores. In this case, the ranking unit 870 calculates an average value (may be a total value) or a maximum value of menu hotness data for each store existing in the history storage database 360. The hotness of the store may be ranked based on the average value or the maximum value, and the ranking, the store name, and the menu (the hardest menu in the store) may be presented to the user.

≪Application 2≫
Application example 2 of the taste estimation apparatus 301 will be described with reference to FIG. Here, the taste estimation device 301 is applied as a ranking device 1110 that ranks a user's hardness tolerance based on data stored in the history accumulation database 360.

  The ranking device 1110 includes a history accumulation unit A and a ranking processing unit D. Since the history accumulation unit A is the same as the taste estimation device 301, a description thereof is omitted. The history storage unit A and the ranking processing unit D may be configured on the same server or may be configured on separate servers.

  The ranking processing unit D includes a ranking unit 1170 that calculates a ranking related to the user's pain resistance based on the data stored in the history storage database 360, and a display unit 1180 that displays the ranking of the pain resistance calculated by the ranking unit 1170. Implement.

  The specific processing content of the ranking processing unit D will be described based on FIG. First, when the process is started, the ranking unit 1170 obtains a user's hardness tolerance value for each store name existing in the history accumulation database 360 (S1210).

  For this hotness tolerance value, hotness data stored in the history accumulation database 360 is used. That is, the ranking unit 1170 acquires user pain data for each menu from the history accumulation database 360 for each store, and creates the intermediate file F3 of FIG. 13B based on the acquired data.

  Next, the ranking unit 1170 ranks the users for each menu of each store based on the hotness data described in the intermediate file F3 (S1220). At this time, since the numbers of the hotness data described in the intermediate file F3 are ranked in ascending order, the higher the hotness data number, the lower the hotness resistance is evaluated, while the smaller the number, the higher the hotness resistance is evaluated. Is done.

  Then, the display unit 1180 displays the ranking for each menu in S1220 in a list format as shown in FIG. 13C, and the process ends. For example, the list of FIG. 13C can be transmitted to the user terminal and displayed on the screen of the user terminal.

  At this time, since the user ranking for “XX curry” of “XX restaurant” is displayed, the ranking device 1110 can be used as a reference for selecting a shop by the user. In this respect, it can be provided as a useful service on the Internet.

  Further, the ranking is not limited to the ranking for a specific menu for each store, and it is possible to standardize the value based on the hotness of the store and to obtain a ranking for total hotness resistance for all menus.

  Note that the ranking devices 801 and 1110 can be configured in combination with the taste estimation device 301. In this case, what is necessary is just to comprise by the log | history storage part A, the estimation function part B, and the ranking process parts C and D (any may be sufficient). As a result, the user is presented with the ranking of the menu hotness in addition to the hotness of the menu of the unknown store, and further useful information can be obtained.

≪Programs≫
The present invention relates to a taste estimation program / ranking program that causes a computer to function as a part or all of each of the units 110 to 140, 310 to 390, 870, 880, 1170, and 1180 of the taste estimation devices 101 and 301 or the ranking devices 801 and 1110. It can also be configured as. According to this program, it is possible to cause the computer to execute part or all of S210 to S260, S510 to S570, S610 to S660, S910 to S930, and S1210 to S1230.

  The program can be provided through a network such as a website or e-mail. The program is stored in a recording medium such as a CD-ROM, DVD-ROM, CD-R, CD-RW, DVD-R, DVD-RW, MO, HDD, BD-ROM, BD-R, or BD-RE. It is also possible to record, save and distribute. This recording medium is read using a recording medium driving device, and the program code itself realizes the processing of the above embodiment, so that the recording medium also constitutes the present invention.

101, 301 ... Taste estimation device 801, 1110 ... Ranking device 110, 320 ... Audio acquisition unit 120, 330 ... Biological information acquisition unit 130, 380 ... Estimation unit 140, 390 ... Visualization unit 310 ... Meal information input unit 340 ... Position information Acquiring unit 350 ... Discriminating unit 360 ... History storage database 370 ... Input receiving unit 870, 1170 ... Ranking unit 880, 1180 ... Display unit

Claims (8)

A history storage database that stores user ID, store information, menu information, and taste information in association with each other;
An input receiving unit that receives a user ID and store information of user input;
A user ID of a similar user whose taste information is similar to the user of the user ID received by the input reception unit is selected from the history storage database, and the taste information of the similar user with respect to the menu information of the store information received by the input reception unit is stored in the history storage database. An estimation unit extracted from
A display unit that associates the menu information extracted by the estimation unit with the taste information and presents it to the user;
A taste estimation apparatus comprising: User ID, store information, menu information, information acquired from a biometric sensor immediately after an utterance related to a taste of the user during the meal and a start of the user's meal, and information acquired from the biometric sensor after an utterance related to the taste during the user's meal A history accumulation database that holds and associates taste information quantitatively estimated based on
A ranking unit that calculates an evaluation value of quantitative taste information for each store information or menu information held in the history accumulation database, and ranks the store information or menu information based on the calculated evaluation value;
A display unit that associates and presents store information or menu information with the ranking of the information;
A ranking device characterized by comprising: User ID, store information, menu information, information acquired from a biometric sensor immediately after an utterance related to a taste of the user during the meal and a start of the user's meal, and information acquired from the biometric sensor after an utterance related to the taste during the user's meal A history accumulation database that holds and associates taste information quantitatively estimated based on
A ranking unit that ranks user IDs based on taste information in a taste information database corresponding to menu information or store information received by the input receiving unit;
A display unit that associates and presents a user ID and a ranking;
A ranking device comprising: A computer estimates a user's taste information based on a history storage database that stores a user ID, store information, menu information, and taste information in association with each other,
An input reception step for receiving a user ID and store information of user input;
A user ID of a similar user whose taste information is similar to the user whose user ID is received by the input reception unit is selected from the history storage database, and the taste information of the similar user with respect to the menu information of the store information received in the input reception step is stored in the history storage database. An estimation step to extract from
A display step for associating the menu information extracted in the estimation step with the taste information and presenting it to the user;
A taste estimation method comprising: Information acquired from the biosensor immediately after the utterance about the user ID, the store information, the menu information, the utterance about the taste of the user during the meal and the start of the meal of the user, and the utterance about the taste during the meal of the user A ranking method based on a history storage database that associates and holds taste information quantitatively estimated based on the information ,
A ranking step of calculating an evaluation value of quantitative taste information for each store information or menu information held in the history accumulation database, and ranking the store information or menu information based on the calculated evaluation value;
A display step of presenting store information or menu information in association with the ranking of the information;
A ranking method characterized by comprising: Information acquired from the biosensor immediately after the utterance about the user ID, the store information, the menu information, the utterance about the taste of the user during the meal and the start of the meal of the user, and the utterance about the taste during the meal of the user A ranking method based on a history storage database that associates and holds taste information quantitatively estimated based on the information ,
A ranking step for ranking user IDs based on taste information in taste information database corresponding to store information or menu information held in the history accumulation database;
A display step of associating and presenting a user ID and a ranking;
A ranking method characterized by comprising: A taste estimation program for causing a computer to function as the apparatus according to claim 1 . A ranking program for causing a computer to function as the device according to claim 2 .

Images