JP6270085B1 - Information processing apparatus, information processing system, information processing method, and program - Google Patents

Abstract

A method for providing cooking information suitable for a user is provided. An information processing apparatus includes: an action history acquisition unit that acquires an action history representing an action of each user on a website that posts cooking information; an attribute of a first user whose attribute is known; A data generation unit 112 configured to generate relation information data representing a correspondence relationship between a character string included in the dish information and the user attribute based on the first action history indicating the action history of the user; and a second user Is estimated based on the second behavior history indicating the behavior history of the second user and the relation information data, and the second user based on the estimated second user attribute And an information providing unit 114 that provides information. [Selection] Figure 17

Description

  The present invention relates to an information processing apparatus, an information processing system, an information processing method, and a program.

  A technique for searching for a cooking recipe based on a search condition designated by a user and presenting the searched recipe is known. For example, Patent Literature 1 discloses a technique that can specify various search conditions. Specifically, the user can search for recipes by specifying a genre, calories, taste, ingredients, and the like as search conditions.

JP 2002-63178 A

  There are a wide variety of users who use services that provide cooking information as described above, and it is common that there is a difference in information to be obtained depending on their attributes (for example, age, sex, marriage history, etc.). Therefore, it is required to provide cooking information based on user attributes. However, when the user's attribute is unknown, there is a problem that cooking information based on the user attribute cannot be provided.

  SUMMARY An advantage of some aspects of the invention is that it provides an information processing apparatus, an information processing system, an information processing method, and a program capable of providing cooking information suitable for a user. I will.

  One aspect of the present invention is an action history acquisition unit that acquires an action history representing an action of each user on a website that posts cooking information, an attribute of a first user whose attribute is known, and the action of the first user. Based on a first action history indicating a history, a data generation unit that generates relationship information data representing a correspondence relationship between a character string included in the dish information and the attribute of the user, and an attribute of the second user, Based on the second behavior history indicating the behavior history of the second user and the related information data, and an estimation unit, and providing information to the second user based on the estimated attribute of the second user And an information providing unit.

  Further, according to one aspect of the present invention, an action history acquisition unit that acquires an action history representing an action of each user on a website that posts cooking information, an attribute of a first user whose attribute is known, and the first user's attribute Based on the first action history indicating the action history, a data generation unit that generates relation information data representing a correspondence relationship between the character string included in the dish information and the attribute of the user, and an attribute of the second user An estimation unit that estimates based on the second behavior history indicating the behavior history of the second user and the related information data, and provides information to the second user based on the estimated attribute of the second user And an information providing system.

  One embodiment of the present invention is an information processing method in an information processing apparatus, in which an action history acquisition step for acquiring an action history representing an action of each user on a website posting cooking information and an attribute are known. Based on the attribute of the first user and the first action history indicating the action history of the first user, relation information data representing the correspondence between the character string included in the dish information and the attribute of the user is generated. A data generation step, an estimation step of estimating an attribute of the second user based on a second behavior history indicating the behavior history of the second user and the relation information data, and an attribute of the estimated second user And an information providing step of providing information to the second user based on the information processing method.

  Further, according to one aspect of the present invention, an action history acquisition process for acquiring an action history representing an action of each user on a website posting cooking information on a computer, an attribute of a first user whose attribute is known, and the first A data generation process for generating relation information data representing a correspondence relationship between a character string included in the dish information and the user attribute based on a first action history indicating the action history of one user; a second user; Of the second user based on the estimated attribute of the second user and the estimated process of estimating the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the related information data. This is a program for executing an information providing process for providing information.

  According to one embodiment of the present invention, cooking information suitable for a user can be provided.

It is a 1st figure which shows an example of the display screen in the information processing system which concerns on embodiment of this invention. It is a 2nd figure which shows an example of the display screen in the information processing system which concerns on the embodiment. It is a block diagram showing an example of composition of an information processing system concerning the embodiment. It is a block diagram which shows the hardware structural example of the information processing apparatus and terminal device which concern on the embodiment. It is a figure which shows an example of the data structure of the menu data which concern on the embodiment. It is a figure showing an example of data composition of menu attribute data concerning the embodiment. It is a figure which shows an example of the data structure of the recipe data which concern on the same embodiment. It is a figure showing an example of data composition of recipe attribute data concerning the embodiment. It is a figure which shows an example of the data structure of the foodstuff data which concern on the embodiment. It is a figure which shows an example of the data structure of the dish data which concern on the embodiment. It is a figure showing an example of data composition of report data concerning the embodiment. It is a figure which shows an example of the data structure of the image data which concerns on the same embodiment. It is a figure showing an example of data composition of action history data concerning the embodiment. It is a figure showing an example of data composition of user data concerning the embodiment. It is a figure which shows an example of a data structure of the attribute information data which concerns on the embodiment. It is a figure which shows an example of the data structure of the relationship information data which concern on the embodiment. It is a block diagram which shows the function structural example of the information processing apparatus which concerns on the same embodiment. It is a figure showing an example of action history data concerning the embodiment. It is a figure which shows the specific example of the attribute historical data which concerns on the embodiment. It is a figure which shows the specific example of the relationship information data which concern on the same embodiment. It is a flowchart which shows the flow of a process by the information processing apparatus which concerns on the embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[Outline of Information Processing System 1]
An overview of the information processing system 1 according to the first embodiment of the present invention will be described. The information processing system 1 according to the present embodiment includes an information processing device 10 and a terminal device 20. The information processing apparatus 10 provides a web service that allows information posted by a user via the terminal device 20 to be disclosed to other users and enables information sharing between users. Below, the case of the web service which makes a recipe shareable is demonstrated as an example.

  1 and 2 are diagrams illustrating an example of a display screen of a web service provided by the information processing apparatus 10. The information processing apparatus 10 provides two posting (recording) functions including a recipe posting function and a report posting function. Information posted by these two posting functions is released on the website and can be referred to by other users.

  The recipe posting function is a function for posting a recipe newly created by the user. With this function, it is possible to post cooking titles, ingredients and their quantities, cooking methods, cooking results cooking images, and the like. The report posting function is a function for posting a report. Here, the report indicates an impression of the recipe posted by the recipe posting function. With this function, it is possible to post the contents described in the cooking method, the comment on the dish itself, the cooking image of the cooking result, and the like. In the present embodiment, posted information that is good for the recipe posting function and the report posting function is collectively referred to as cooking information. Further, the dish information may include advertisement information related to the dish.

P11 in FIG. 1 is a column for inputting the dish name or ingredient name of the recipe to be searched by the user. P12 is a column for inputting the purpose or application of the recipe to be searched by the user. P13 is a button for executing a recipe search. The user can search for a recipe by inputting a character string into P11 or P12 and pressing P13. When a character string is input to P11 and P12, a recipe search is executed by a combination of the input character strings.
P14 is a button for starting posting a recipe. When the user presses P14, the screen changes to a recipe posting screen, and the user can post a recipe.

P15 is a column for displaying a picked-up recipe. A combination of the photograph and title of the recipe that has been picked up is displayed, and when the user presses the photograph or title, the display transitions to the corresponding recipe display screen. The recipe to be picked up may be determined by the information processing system 1 according to a predetermined rule, or may be determined by an input from an administrator or the like.
P16 is a column for displaying the category of the recipe. A combination of a photo and a category name for each category is displayed, and when the user presses the photo or category name, the screen transitions to a screen for displaying a recipe of the corresponding category.

P17 is a column for displaying various contents that are regularly updated. The various contents are, for example, recipes by collaboration with various companies or tie-ups. The title of the content is displayed in P17, and when the user presses the title, the corresponding content display screen is displayed. The various contents may be determined by the information processing system 1 according to a predetermined rule, or may be determined by an input from an administrator or the like.
P18 is a column in which other information is displayed. The other information is, for example, a screen on which an advertisement banner is displayed.

P21 in FIG. 2 is a column for displaying the recipe posted by the user by the recipe posting function. A combination of a new recipe photo and title is displayed in P21, and when the user presses the photo or title, the screen transitions to a screen for displaying the corresponding recipe.
P22 is a column for displaying a report posted from the user by the report posting function. A combination of a new report photo and title is displayed in P22, and when the user presses the photo or title, the screen transits to a screen for displaying the corresponding report.
P23 is a column in which other information is displayed as in P18.

  1 and 2 are examples of the display screen according to the present embodiment, and the display form can be variously changed. For example, the screen configuration may be different for personal computers and smartphones. In addition, browsing food information via an application such as a smartphone is also referred to as browsing a website.

  The information processing apparatus 10 according to the present embodiment acquires an action history representing each user's action on a website that publishes cooking information shown in the examples of FIGS. 1 and 2. The action history is, for example, a browsing history of recipes and reports on a website of each user, or a posting history of recipes and reports. The information processing apparatus 10 acquires attribute information of a user whose attribute is known (hereinafter also referred to as a first user), and a character string included in the dish information based on the acquired attribute information and the user's action history Relation information data (probability model) representing a correspondence relation with a user attribute is generated.

  Thereafter, the information processing apparatus 10 estimates the attribute of a user whose attribute is unknown (hereinafter also referred to as a second user) based on the behavior history of the user and the generated relationship information data. Thereafter, the information processing apparatus 10 provides information suitable for the second user based on the estimated attribute of the second user. Specifically, the display order of each display column and recipe on the website is changed, pickup items are changed, and the like. Accordingly, it is possible to estimate the attribute of the user who accesses the website based on the behavior history of the user whose attribute is already known, and to provide information suitable for the user based on the estimated attribute.

[Configuration of Information Processing System 1]
Next, the configuration of the information processing system 1 will be described.
FIG. 3 is a block diagram illustrating a configuration example of the information processing system 1. The information processing system 1 includes an information processing device 10 and one or more terminal devices 20-1, 20-2,..., 20-N (N is a natural number). Hereinafter, the terminal devices 20-1, 20-2,..., 20 -N are collectively referred to as the terminal device 20. The information processing apparatus 10 and the terminal apparatus 20 are connected to a wired or wireless network NW and can communicate with each other.

  The information processing apparatus 10 is an electronic device including a computer, for example, a server apparatus. The information processing apparatus 10 has a web server function and provides cooking information in response to a request from the terminal apparatus 20. The information processing apparatus 10 manages various data necessary for presenting search results such as menu data, menu attribute data, recipe data, recipe attribute data, food data, dish data, report data, and the like. The information processing apparatus 10 manages action history data and user data. Note that the functions of the information processing apparatus 10 may be configured as a system by being distributed among a plurality of devices.

  The terminal device 20 is an electronic device including a computer, such as a personal computer, a tablet terminal, a smartphone, a mobile phone, or a game machine. The terminal device 20 provides a user interface, accepts input of a character string from the user, and presents various information provided by the information processing device 10 to the user.

[Hardware configuration]
Next, the hardware configuration of each device included in the information processing system 1 will be described.
FIG. 4 is a block diagram illustrating a hardware configuration example of the information processing device 10 and the terminal device 20. As shown in FIG. 4, each of the information processing apparatus 10 and the terminal apparatus 20 is physically exemplified by a CPU 101, a RAM 102 and a ROM 103 that are main storage devices, a communication module 104 that is a data transmission / reception device, a hard disk, a flash memory, and the like. The computer system includes an auxiliary storage device 105, an input device 106 exemplified by a touch panel and a keyboard as input devices, an output device 107 such as a display, and the like. In the information processing apparatus 10 and the terminal apparatus 20, the communication module 104, the input apparatus 106, and the output apparatus 107 are operated under the control of the CPU 101 by reading predetermined computer software on hardware such as the CPU 101 and the RAM 102. At the same time, by reading and writing data in the RAM 102 and the auxiliary storage device 105, a series of functions in each device is realized.

[Data structure]
Next, the configuration of various data processed by the information processing apparatus 10 will be described.
FIG. 5 is a diagram illustrating an example of a data configuration of the menu data. Menu data is data describing information about the contents of the menu, and is data in which one or more pieces of cooking information are associated with a menu ID (IDentifier).

  The menu ID is information for uniquely identifying a menu. Composition dish information is information which shows the dish which comprises a menu. In the component dish information, component dish recipe information and component dish category information are described. The component dish recipe information is information for specifying a dish recipe that constitutes a menu. For example, a recipe ID is described in the constituent dish recipe information. The recipe ID is information for uniquely identifying a recipe for cooking. The component dish category information is information indicating the position (type) of the dish in the menu. In the component dish category information, for example, types such as main dishes, side dishes, soups, and desserts may be described.

  By referring to such menu data, the information processing apparatus 10 can identify the dish constituting the menu and its type and present it to the user.

  FIG. 6 is a diagram illustrating an example of the data configuration of the menu attribute data. Menu attribute data is menu name information, menu poster information, menu registration date and time information, menu image information, poster comment information, setup comment information, menu cooking time information, This is data in which menu category information, member permission information, and menu report number information are associated with each other.

  Menu name information is information indicating the name of the menu. The name of the menu includes the names of dishes and ingredients constituting the menu. Menu poster information is information indicating a poster poster (creator). For example, the user ID is described in the menu poster information. The menu registration date and time information is information indicating the date and time when the menu was posted and registered. The menu image information is information indicating a captured image of the menu. The contributor comment information is information indicating a comment (for example, summary, background) attached to the menu by the contributor. The setup comment information is information indicating comments indicating notes and the like when cooking along the menu.

  Menu cooking time information is information indicating the approximate time required for cooking the menu. The menu cooking time information may indicate the total cooking time of each dish constituting the menu, or may indicate a time calculated and set separately. For example, when the cooking of a plurality of dishes can proceed simultaneously, the cooking time of the menu may be shorter than the total cooking time of each dish. The menu category information is information indicating the type of menu (for example, concept, calorie, expense, awarding the hall of fame, awards, etc., purpose, use). The member permission information is information indicating permission for information disclosure according to member settings. The menu report number information is information indicating the number of reports posted from the viewer for the menu.

  By referring to such menu attribute data, the information processing apparatus 10 can specify various menu attributes and present them to the user. Further, by referring to the member permission information, it is possible to control the disclosure of the menu information according to the member setting.

  FIG. 7 is a diagram illustrating an example of the data configuration of recipe data. Recipe data is data describing information about the contents of a recipe, and is data in which one or more recipe ingredients information and one or more cooking process information are associated with a recipe ID.

  Recipe ingredient information is information about ingredients used for a recipe. In the recipe ingredient information, used ingredient information, quantity information, and ingredient category information are described. The used food material information is information for specifying a food material used for a recipe. In the used food information, for example, a food ID is described. The food ID is information that uniquely identifies the food. The amount information is information indicating the amount of ingredients used for the recipe. The food category information is information indicating a group of ingredients in the recipe. For example, in the food category information, identification information of each group may be described so that a group of ingredients used in a certain cooking process can be distinguished from a group of ingredients used in another cooking process.

  Cooking process information is information which shows the operation | work in cooking in steps. In the cooking process information, cooking image information, process comment information, process time information, and cooking method information are described. The cooking image information is information indicating a captured image showing a cooking process. Process comment information is information which shows the explanatory text of a cooking process. Process time information is information which shows the time which a cooking process requires. The cooking method information is information indicating the type of cooking method in the cooking process. There are various types of cooking methods, such as cutting, boiling, baking, steaming, boiling, frying, and mixing.

  By referring to the recipe data in this way, the information processing apparatus 10 can specify various recipe information indicating a cooking method of cooking and present it to the user.

  FIG. 8 is a diagram illustrating a data configuration of recipe attribute data. The recipe attribute data is data describing the attribute information of the recipe. In the recipe attribute data, the recipe ID, recipe name information, target number information, recipe poster information, recipe registration date / time information, dish image information, poster comment information, and cooking time for the recipe ID Information, recipe category information, member permission information, and recipe report number information are associated with each other.

  The dish ID is information for uniquely identifying a dish. The recipe name information is information indicating the name of the recipe. The name of the recipe includes names of dishes that can be created based on the recipe and names of ingredients used in the recipe. The name of the recipe may include various symbols and onomatopoeia (described later) for explaining and modifying the recipe. The target number information is information indicating the amount of food indicated by the recipe. In the target number information, for example, information for one person, 2-3 persons, etc. is described. The recipe poster information is information indicating a recipe poster (creator). For example, a user ID is described in the recipe poster information. The recipe registration date / time information is information indicating the date / time when the recipe is posted and registered. The dish image information is information indicating a captured image of the dish. The contributor comment information is information indicating a comment (for example, outline, background) attached to the recipe by the contributor.

  The cooking time information is information indicating an approximate time required for cooking. The cooking time information may indicate the total time required for each cooking process, or may indicate a time that is separately calculated and set. For example, the cooking time may include time required for preparation, arrangement, etc. in addition to the time required for each cooking process. The recipe category information is information indicating the type of recipe (for example, concept, calorie, cost, awarding a hall of fame or award history, purpose, use). The recipe report number information is information indicating the number of reports posted from the viewer to the recipe.

  By referring to such recipe attribute data, the information processing apparatus 10 can specify various attributes of the recipe and present them to the user. In addition, by referring to the member permission information, it becomes possible to control the disclosure of recipe information according to the member setting.

  FIG. 9 is a diagram illustrating an example of a data configuration of the food material data. Ingredient data is data describing information about ingredients. Ingredient name information, nutrient information, calorie information, belonging ingredient information, and same kind ingredient information are associated with the ingredient ID.

  The ingredient name information is information indicating the name of the ingredient. The nutrient information is information indicating the nutrients contained in the food and the amount thereof. The calorie information is information indicating the calories per unit amount of food. Affiliated ingredient information is information indicating an affiliated ingredient. “Affiliated ingredient” is information indicating another ingredient conceptually included in a certain ingredient. For example, “fish” includes “sea bream” and “autumn fish”. In addition, “ginger” includes “ginger” and “canned salmon”. In other words, the belonging food is a food belonging to a subordinate concept of a certain food. In the belonging ingredient information, the ingredient ID of the belonging ingredient may be described. The same kind of ingredient information is information indicating the same kind of ingredient. The “same kind of ingredient” is information indicating another ingredient having the same kind of relationship with a certain ingredient.

  By referring to such food material data, the information processing apparatus 10 can identify the nutrients and calories included in the menu and dishes and present them to the user. Moreover, the information processing apparatus 10 can specify the relationship between two or more foodstuffs. For example, the information processing apparatus 10 can specify the affiliation ingredient or the same kind of ingredient of the input keyword ingredient. Therefore, the information processing apparatus 10 can extract menus and recipes not only for menus and recipes that can be directly extracted from the ingredients indicated by the input keyword, but also for belonging ingredients and similar ingredients and present them to the user.

  FIG. 10 is a diagram illustrating an example of a data configuration of dish data. The dish data is data describing information related to the dish, and the dish ID information, the associated dish information, and the same kind of dish information are associated with the dish ID.

  The dish name information is information indicating the name of the dish. The affiliation dish information is information indicating the affiliation dish. “Affiliated dish” is information indicating another dish that is conceptually included in a certain dish. For example, “boiled” includes “boiled” and “chikuzenni”. In other words, the affiliated dish is a dish belonging to a subordinate concept of a certain dish. In the affiliated dish information, a dish ID of the affiliated dish may be described. The same kind of dish information is information indicating the same kind of dish. The “same kind of dish” is information indicating another dish having the same kind of relationship with a certain dish.

  By referring to such dish data, the information processing apparatus 10 can specify the relationship between two or more dishes.

  FIG. 11 is a diagram illustrating an example of a data configuration of report data. Report data is data describing report information for a menu or recipe. In the report, a user who has cooked while browsing a menu or a recipe publishes opinions and impressions about the menu or the recipe. In the report data, report target information, report poster information, report image information, report comment information, and corresponding comment information are associated with the report ID.

  The report ID is information that uniquely identifies a report. The report target information is information indicating a report target. In the report information, for example, a menu ID and a recipe ID are described. The report poster information is information indicating a report poster (creator). For example, a user ID is described in the report poster information. The report image information is information indicating an image showing a cooking result (menu, cooking) and a cooking state by a report poster. The report comment information is information indicating an explanatory note of the report. Corresponding comment information is information indicating a reaction comment from a menu or recipe contributor (creator) to a report.

  By referring to such report data, the information processing apparatus 10 can evaluate menus and recipes. For example, menus and recipes with many reports are used for cooking by many users. Therefore, the information processing apparatus 10 can specify a popular menu or recipe.

  FIG. 12 is a diagram illustrating an example of a data configuration of image data. Image data is data describing information about an image, and imaging user information, imaging time information, and estimated usage information are associated with an image ID.

The image ID is data that uniquely identifies an image. The imaging user information is information indicating a user who has performed imaging. For example, a user ID is described in the imaging user information. The user who has taken an image includes a user who owns the image even if the image is not actually taken.
The imaging time information is information indicating the time when an image is captured. Image ID, imaging user information, and imaging time information may be generated, for example, when an image is captured. The estimated usage information is information indicating the usage estimated by the information processing apparatus 10 for an image. The use of the image estimated by the information processing apparatus 10 is for recipe posting or report posting.

  By referring to such image data, the information processing apparatus 10 can specify the use of the image for each image.

  FIG. 13 is a diagram illustrating an example of a data configuration of action history data. The action history data is data describing the action history on the user's website, and includes, for example, the user's browsing history, search history, recipe and report posting history, and the like. Here, as an example, a case where a browsing history is used as an action history will be described.

In the action history data, action user information, platform information, access time information, URL information, browsing recipe ID, browsing recipe title information, and the like are associated with the action history ID.
The action history ID is data that uniquely identifies the action history. The action user information is information indicating a user who has browsed the website. For example, a user ID is described in the action user information. If the user ID is unknown, an arbitrary ID that is temporarily paid out may be described.

  Platform information is information indicating information of the terminal device 20 when a user accesses a website via the terminal device 20. Specifically, it is information indicating the operating system, browser, terminal type, and the like of the terminal device 20. For example, the information processing apparatus 10 acquires platform information of the terminal device 20 from information (such as a user agent) included in an HTTP (Hypertext Transfer Protocol) request from the terminal device 20. By referring to the platform information, it is possible to grasp whether the terminal device 20 used by the user is a desktop personal computer or a mobile terminal, or what type of OS or browser is used.

  The access time information is information indicating the date and time when the user accesses (views) the website. The URL information is information representing a URL (Uniform Resource Locator) or a URI (Uniform Resource Identifier) of a website accessed (viewed) by the user. The browsing recipe ID is information indicating the recipe ID of the recipe browsed by the user.

  By referencing such behavior history data, the information processing apparatus 10 can track the behavior of the user on the website. For example, it is possible to know which user has accessed which URL from which platform and which recipe has been viewed. Also, by referring to the recipe attribute data using the recipe ID of the browsed recipe as a key, information such as the title, description, and image of the browsed recipe can be specified.

  FIG. 14 is a diagram illustrating an example of a data configuration of user data. The user data is data describing information about users who are registered as members in the recipe sharing service provided by the information processing system 1. User data includes user name, name information, password information, nickname information, date of birth information, gender information, contact information, link information, favorite menu information, favorite recipe information, , Data associated with member setting information.

  The name information is information indicating the name of the user. The password information is information indicating a password set for the user account. The password is an example of authentication information. As the authentication information, arbitrary information such as a fingerprint and a voiceprint may be used in addition to the password. The nickname information is information indicating a user's nickname (a name when being disclosed to others). The date of birth information is information indicating the date of birth of the user. Gender information is information indicating the gender of the user. The contact information is information indicating a user's contact information such as an email address, a telephone number, and an address. For example, by referring to the address, it is possible to perform processing according to the regionality of the user's whereabouts. The link information is information indicating a link to an account such as a user's SNS (Social Networking Service).

  Favorite menu information is information indicating a menu registered by the user as a favorite. Favorite recipe information is information indicating a recipe registered by the user as a favorite. The member setting information is information indicating the user's member setting. The member setting includes a plurality of types such as “normal member” and “special member”. Regular members cannot use some information retrieval services. On the other hand, special members can use all of the information retrieval services. As conditions for becoming a special member, for example, arbitrary conditions such as payment of a predetermined amount, use of an information search service for a predetermined period, use of a predetermined number of information search services, and the like may be employed.

  By referring to such user data, the information processing apparatus 10 can specify attributes such as the sex and age of the user. Thereby, the search result according to a user's attribute can be shown. Further, the information processing apparatus 10 can acquire the user's evaluation for the menu and the recipe based on the favorite menu information and the favorite recipe information. Further, the information processing apparatus 10 can provide an information search service according to the user's member setting based on the member setting information.

  FIG. 15 is a diagram illustrating an example of the configuration of attribute information data. The attribute information is information representing a user attribute, and sex information, age information, marriage status information, and the like are associated with the user ID.

  The user ID is an identifier for identifying the user. For a user whose user ID is unknown, a temporary ID may be issued and managed. The sex information is information representing the sex of the user. Age information is information indicating the age of the user. The age information may be information representing a rough age such as 20 or 30 in addition to the actual age of the user. Marriage status information is information indicating the marriage history of a user such as married or unmarried. The attribute information is not limited to the above, and various types of information representing user attributes may be used. Each attribute information may be acquired from user data or an external database. Further, it is not necessary to store all attribute information, and when attribute information cannot be acquired from the user database or the external database, that is, when the attribute is unknown, the attribute information may be blank.

  In this way, by referring to the attribute information data, the information processing apparatus 10 can centrally manage user attributes, and can provide information suitable for the user according to the user attributes. . Further, as will be described later, relation information data for estimating user attributes can be generated based on known user attribute information.

  FIG. 16 is a diagram illustrating an example of the configuration of the relationship information data. The relationship information is information indicating a correspondence relationship between a keyword included in cooking information on a website viewed by the user and a probability that the user is classified into each category of attribute (attribute probability) for each attribute. For example, when the cooking information browsed by the user includes the keyword “children”, the marriage status is 0.8 (80 percent) that the user is married and 0.2 (20 percent) that she is unmarried. ) Etc. The information processing apparatus 10 calculates the probability based on the user's behavior history data and attribute information data.

Thus, by generating and referring to the relationship information data, the information processing apparatus 10 can estimate the attribute of the user whose attribute is unknown. Furthermore, information suitable for the user can be provided based on the estimated user attribute.
Above, description about the structure of the various data which the information processing apparatus 10 processes is complete | finished.

[Configuration of Information Processing Apparatus 10]
Next, the functional configuration of the information processing apparatus 10 will be described.
FIG. 17 is a block diagram illustrating an example of a functional configuration of the information processing apparatus 10. The information processing apparatus 10 includes a control unit 11, a storage unit 12, and a communication unit 13.

The control unit 11 controls various functions of the information processing apparatus 10.
The storage unit 12 stores various data and programs used by the information processing apparatus 10. The storage unit 12 includes menu data, menu attribute data, recipe data, recipe attribute data, food data, dish data, report data, image data, action history data, user data, attribute information data, relationship information data, Stores estimation results and the like.
The communication unit 13 communicates with the terminal device 20 connected to the network, an external device (database server), and the like based on the control of the control unit 11.

The control unit 11 includes an action history acquisition unit 111, a data generation unit 112, an estimation unit 113, and an information provision unit 114.
The action history acquisition unit 111 acquires a user action history on a website provided by the information processing apparatus 10. As described above, the action history includes a user browsing history, a search history, a recipe and report posting history, and the like. The action history acquisition unit 111 acquires various action histories of the user and outputs them as action history data to the storage unit 12.

Here, a specific example of the action history data acquired by the action history acquisition unit 111 will be described.
FIG. 18 is a diagram illustrating a user's browsing history as a specific example of action history data. In the example of FIG. 18, the action history data includes fields of user ID, platform, access date / time, URL, and browsing recipe title in a record for each action ID. For example, with the action ID “001”, the user with the user ID “001” can access the URL “http://www.xxx.com/recipe/001” at 11:11:11 on January 1, 2017. It represents that the terminal device 20 whose platform is “Mobile OS-A” was accessed per second. In addition, at this time, the user browses a recipe titled “Children are stuffy! The behavior history data of a user whose attribute information is known (first user) and a user whose attribute information is unknown (second user) are managed as separate tables (for example, first behavior history data, second behavior history data, etc.). May be.

  Next, the data generation unit 112 will be described. The data generation unit 112 is relation information data representing a correspondence relationship between a character string included in the dish information on the website and the user's attribute based on the user's attribute whose attribute is known and the user's action history. Is generated. Specifically, the data generation unit 112 first acquires user attribute information from user data, an external database, or the like, and generates attribute information data.

Here, a specific example of attribute information data generated by the data generation unit 112 will be described.
FIG. 19 is a diagram illustrating a specific example of attribute information data. In the example of FIG. 19, the attribute information data includes fields for sex, age, and marriage status in a record for each user ID. For example, a user whose user ID is “001” indicates that the gender is “male”, the age is “40s”, and the marriage status is “married”. In the example of FIG. 19, for the users with user IDs “101” and “102”, no attribute information exists in the user data or external data, and the attribute information is unknown, so each field is blank. Note that the attribute information data of a user whose attribute information is known (first user) and a user whose attribute information is unknown (second user) may be managed as separate tables.

  The description of the data generation unit 112 will be continued. The data generation unit 112 refers to the action history data and extracts keywords included in the browsing recipe title. The keyword is a character string included in the browsing recipe title. In the example of FIG. 18, for example, the data generation unit 112 extracts words representing people such as “children” and “boyfriend”, and words representing dish names such as “fried rice” and “tomato soup” as keywords. . Further, the data generation unit 112 may extract various symbols such as symbols representing musical notes and heart marks, pictograms, and the like as keywords. In addition, the data generation unit 112 may extract words representing onomatopoeia such as “packed”, “molly” and the like as keywords. Onomatopoeia is a term that comprehensively represents an onomatopoeia that mimics the sound or voice of an object, an onomatopoeia (such as a gookugoku), or a mimetic word that mimics a state or the like (such as a parcel). Note that the data generation unit 112 may extract a part of a word or symbol as a keyword. In addition, the data generation unit 112 may extract fluctuations in keyword notation (for example, “children” and “children”) and process them as the same keyword. Note that the recipe title is a simple expression of the recipe name and features, so keywords can be extracted efficiently. However, the keywords can be extracted from information other than the recipe title, such as recipe descriptions and report sentences. It may be extracted. As a result, detailed data can be generated.

  Next, the data generation unit 112 refers to the attribute information data, and generates a probability model indicating the correspondence between the keyword and the user attribute for each keyword. Various methods may be used to calculate the probability. For example, the probabilistic model is calculated from the ratio of the number of married persons and the number of unmarried persons by referring to the marriage status of the attribute information data of the user who refers to a recipe including the keyword “children” in the title. In this case, all users included in the attribute information data may be referred to, or sampled users may be referred to. The data generation unit 112 outputs the generated probability model to the storage unit 12 as related information data.

Here, a specific example of the relationship information data generated by the data generation unit 112 will be described.
FIG. 20 is a diagram illustrating a specific example of the relationship information data. The example of FIG. 20 shows the relationship between each keyword and the classification (married, unmarried) in the attribute (marital status). Specifically, the relationship information data has a field for married and unmarried in a record for each keyword, and the probability calculated by the data generation unit 112 is input to each. For example, when the keyword is “child”, the probability of being married is 0.8 (80%), and the probability of being unmarried is 0.2 (20%). The fields included in the relationship information table are different for each attribute. For example, the age includes fields such as a teenager or less, a 20s, a 30s, a 40s, a 60s or more.

  Next, the estimation unit 113 will be described. The estimation unit 113 determines the attribute of the user whose attribute is unknown based on the behavior history data indicating the behavior history on the user's website generated by the behavior history acquisition unit and the relationship information data generated by the data generation unit. presume.

A specific example of processing of the estimation unit 113 will be described with reference to FIGS. 18 and 20. As an example, a case will be described in which the estimation unit 113 estimates the marriage status of the user with the user ID “101” in FIG.
First, the estimation unit 113 refers to the action history data, and acquires a recipe title (“children are packed ♪ Sanma no sesame fry *”, “genki Morimori ♪ Stamina 丼”) viewed by the user with the user ID “101”. Next, the estimation unit 113 refers to the relationship information data regarding the marriage status in FIG. 20 and acquires a probability model corresponding to “child”, “pack”, and “morimori” included in the acquired recipe title.

  Next, the estimation unit 113 calculates the probability that the user with the user ID “101” is married (or unmarried) based on the acquired probability model. Various schemes may be used to calculate the probability. For example, the probability of being married may be calculated as 1− (0.2 × 0.3 × 0.3) = 0.882 (98.2 percent). Further, a value obtained by inputting a value calculated based on the probability model into a predetermined function may be used.

  Then, when the calculated probability value is larger than the predetermined value, the estimation unit 113 determines the attribute classification of the user as an estimation result. In this example, if the predetermined value is 0.7, the probability value calculated by the above formula is 0.982 (> 0.7), so the user is estimated to be married. Thereafter, the estimation unit 113 outputs the estimation result to the storage unit 12.

Next, the information providing unit 114 will be described. The information providing unit 114 has a function for displaying objects such as HTML (HyperText Markup Language) and images, and provides cooking information in response to a request from the user (terminal device 20). In addition, the information providing unit 114 provides information corresponding to the user's attribute to the user whose attribute is known with reference to the attribute information data. Further, the information providing unit 114 provides information according to the estimated user attribute to the user whose attribute is unknown based on the estimation result calculated by the estimation unit 113. Providing information according to user attributes includes, for example, changing the display order of recipes and reports on a website, changing the size of display frames, changing the display order of search results, and the like. In addition, it may include the distribution of messages on a website, the provision of information by e-mail, and the like, the change of advertisement contents to be displayed, and the like.
This is the end of the description of the functional configuration of the information processing apparatus 10.

[Operation of Information Processing Apparatus 10]
Next, the operation of the information processing apparatus 10 will be described.
FIG. 21 is a flowchart showing the flow of processing by the information processing apparatus 10.

(Step S101) The action history acquisition unit 111 acquires action history data of a first user whose attribute is known. Thereafter, the process proceeds to step S102.
(Step S102) The data generation unit 112 acquires attribute information data of the first user. Thereafter, the process proceeds to step S103. Note that the order of the processing in step S101 and step S102 may be reversed.

(Step S103) If a predetermined number of user behavior history data and attribute information data whose attributes are known can be acquired (step S103 / Yes), the data generation unit 112 proceeds to step S104. If the predetermined number of data has not been acquired (step S103 / No), the process returns to step S101.
(Step S104) The data generation unit 112 generates relationship information data based on the acquired action history data and attribute information data. Thereafter, the process proceeds to step S105.
(Step S105) The action history acquisition unit 111 acquires action history data of a second user whose attribute is unknown. Note that the process of step S105 may be performed before or after the processes of steps S101 to S104. Thereafter, the process proceeds to step S106.

(Step S106) The estimation unit 113 estimates the attribute of the second user based on the second user's action history data and the relationship information data. Thereafter, the process proceeds to step S107.
(Step S107) The information providing unit 107 provides information to the second user based on the estimated attribute of the second user.
Above, description of the flow of the process by the information processing apparatus 10 is complete | finished.

[Modification 1]
Next, a modification of this embodiment will be described.
In this modification, the data generation unit 112 refers to the action history data of a user whose attribute is already known (first user), and includes symbols (symbols indicating musical notes, heart marks, symbols included in the recipe title viewed by the first user) Pictograph etc.) are extracted. Only a part of the symbols may be extracted instead of all. For example, when three heart marks are arranged, only one heart mark may be extracted. Then, the data generation unit 112 generates relation information data including the extracted symbols.

  The estimation unit 113 estimates the attribute of the second user based on the generated relationship information data and the action history information of the user (second user) whose attribute is unknown. At this time, the estimation unit 113 estimates the attribute of the second user in preference to the record of the related information data including the extracted symbol over the record of the related information data not including the symbol. Priority includes weighting a probability value related to a record including a symbol, or estimating a second user attribute by excluding a record not including the symbol. Referring to the example of FIG. 20, for example, the attribute probability shown in the record whose keyword is a heart mark is given priority over the attribute probability shown in other records.

Various symbols (including pictograms) often have a higher correlation with user attributes than other keywords. Therefore, it is possible to estimate with higher accuracy by preferentially estimating the attribute by giving priority to the record of the related information data including the symbol. In addition, since a symbol has a smaller amount of information than a keyword composed of a character string, data processing can be performed efficiently. In addition, about a symbol with a low correlation with a user's attribute (for example, exclamation mark etc.), you may exclude from a priority object and may estimate.
[Modification 2]
Next, another modification of the present embodiment will be described.
In this modification, the data generation unit 112 refers to the action history data of a user whose attribute is known (first user), and extracts a word representing onomatopoeia included in the recipe title viewed by the first user. Only a part of the words representing onomatopoeia may be extracted. For example, only “pack” may be extracted from “pack”. Then, the data generation unit 112 generates relation information data including the extracted onomatopoeia.

  The estimation unit 113 estimates the attribute of the second user based on the generated relationship information data and the action history information of the user (second user) whose attribute is unknown. At this time, the estimation unit 113 estimates the attribute of the second user in preference to the record of the related information data including the extracted onomatopoeia than the record of the related information data not including the onomatopoeia. As in the first modification, the priority includes weighting a probability value related to a record including onomatopoeia or estimating a second user attribute by excluding a record not including onomatopoeia. Referring to the example of FIG. 20, for example, the attribute probability shown in the record whose keywords are “packed” and “morimori” is given priority over the attribute probability shown in other records.

  Words that represent onomatopoeia often have a higher correlation with user attributes than other keywords. In particular, in relation to cooking information, for example, onomatopoeia is often used in order to directly represent the mode and image of cooking and cooking procedures such as “jujuju”, “pakupaku”, and “easily”. Therefore, it is possible to estimate with higher accuracy by preferentially estimating the attribute with priority on the record of relation information data including onomatopoeia. Note that onomatopoeia having a low correlation with the user attribute may be estimated by excluding it from the priority target.

[Summary of this embodiment]
As described above, the information processing apparatus 10 according to the present embodiment includes the behavior history acquisition unit 111 that acquires the behavior history representing the behavior of each user on the website on which the dish information is posted, and the first having a known attribute. Based on the user attribute and the first action history (action history data) indicating the action history of the first user, relation information data representing the correspondence between the character string included in the dish information and the user attribute is generated. The data generation unit 112, the estimation unit 113 that estimates the attribute of the second user based on the second behavior history (behavior history data) indicating the behavior history of the second user and the related information data, and the estimated second user And an information providing unit 114 that provides information to the second user based on the attribute of. Thereby, the attribute of the user who accessed the website can be estimated based on the action history of the user whose attribute is known, and information suitable for the user can be provided based on the estimated attribute.

  Moreover, the data generation part 112 may generate | occur | produce the relationship information data showing the correspondence of the character string regarding the recipe information which shows the procedure of cooking, and the attribute of a 1st user. Thereby, it is possible to perform processing on the character string related to the recipe information and estimate the user's attribute more efficiently.

  Further, the data generation unit 112 extracts at least a part of the words included in the title from the title of the recipe information corresponding to the first action history (action history data), and extracts based on the attribute of the first user Relationship information data representing a correspondence relationship between at least a part of the words and the attributes of the first user may be generated. Thereby, by estimating based on the word contained in the title which shows the content of a recipe simply, estimation of a user's attribute can be performed more efficiently, maintaining the precision of estimation.

  In addition, the data generation unit 112 extracts at least a part of the symbols included in the title from the title of the recipe information corresponding to the first action history (action history data), and at least a part of the extracted symbols and the first Relationship information data representing a correspondence relationship with one user's attribute may be generated. As a result, it is possible to process symbols having a high correlation with the user's attribute, and to generate the related information data more efficiently.

  The estimation unit 113 may estimate the attribute of the second user in preference to the relationship information data related to at least a part of the symbol over the relationship information data related to a character string that does not include at least a part of the symbol. . Thereby, it is possible to increase the accuracy of estimation by giving priority to symbols having high correlation with user attributes.

  Moreover, the data generation part 112 extracts at least one part of the word showing onomatopoeia contained in the said dish information from the dish information corresponding to the 1st action history (action history data), and based on the attribute of the 1st user. The relation information data representing the correspondence between at least a part of the extracted onomatopoeia words and the attributes of the first user may be generated. Thereby, it is possible to process onomatopoeia having a high correlation with the user's attribute, and to generate the related information data more efficiently.

  Further, the estimating unit 113 prioritizes the relationship information data related to at least a part of the word representing onomatopoeia over the relationship information data related to the character string not including at least a part of the word representing onomatopoeia. May be estimated. Thereby, it is possible to increase the accuracy of estimation by giving priority to onomatopoeia having a high correlation with user attributes.

  The information processing apparatus is recorded by recording a program for realizing the functions of the information processing apparatus 10 on a computer-readable recording medium, causing the computer system to read and execute the program recorded on the recording medium. 10 may be performed. Here, “loading and executing a program recorded on a recording medium into a computer system” includes installing the program in the computer system. The “computer system” here includes an OS and hardware such as peripheral devices. Further, the “computer system” may include a plurality of computer devices connected via a network including a communication line such as the Internet, WAN, LAN, and dedicated line.

  The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. As described above, the recording medium storing the program may be a non-transitory recording medium such as a CD-ROM. The recording medium also includes a recording medium provided inside or outside that is accessible from the distribution server in order to distribute the program. The code of the program stored in the recording medium of the distribution server may be different from the code of the program that can be executed by the terminal device. That is, the format stored in the distribution server is not limited as long as it can be downloaded from the distribution server and installed in a form that can be executed by the terminal device. Note that the program may be divided into a plurality of parts, downloaded at different timings, and combined in the terminal device, or the distribution server that distributes each of the divided programs may be different. Furthermore, the “computer-readable recording medium” holds a program for a certain period of time, such as a volatile memory (RAM) inside a computer system that becomes a server or a client when the program is transmitted via a network. Including things. The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

  Moreover, you may implement | achieve part or all of the information processing apparatus 10 in embodiment mentioned above as integrated circuits, such as LSI (Large Scale Integration). Each functional unit of the information processing apparatus 10 may be individually made into a processor, or a part or all of them may be integrated into a processor. Further, the method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. In addition, when an integrated circuit technology that replaces LSI appears due to the advancement of semiconductor technology, an integrated circuit based on the technology may be used.

  As described above, the embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to the above, and various design changes and the like can be made without departing from the scope of the present invention. It is possible to In addition, one aspect of the present invention can be modified in various ways within the scope of the claims, and the technical aspects of the present invention also relate to embodiments obtained by appropriately combining technical means disclosed in different embodiments. Included in the range. Moreover, it is the element described in said each embodiment and modification, and the structure which substituted the element which has the same effect is also contained.

DESCRIPTION OF SYMBOLS 1 ... Information processing system, 10 ... Information processing apparatus, 101 ... CPU, 102 ... RAM, 103 ... ROM, 104 ... Communication module, 105 ... Auxiliary storage device, 106 ... Input device, 107 ... Output device, 11 ... Control part, DESCRIPTION OF SYMBOLS 111 ... Action history acquisition part, 112 ... Data generation part, 113 ... Estimation part, 114 ... Information provision part, 12 ... Memory | storage part, 13 ... Communication part, 20 ... Terminal device

Claims (10)

An action history acquisition unit for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation unit for generating information data;
An estimation unit that estimates the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing unit for providing information to the second user based on the estimated attribute of the second user,
The data generation unit generates the relationship information data representing a correspondence relationship between the character string related to recipe information indicating a cooking procedure and the attributes of the first user, and the recipe information corresponding to the first action history Extracting at least a part of a symbol included in the title, and generating the relationship information data representing a correspondence relationship between the extracted at least a part of the symbol and the attribute of the first user,
The estimation unit estimates the attribute of the second user in preference to the relation information data related to at least part of the symbol over the relation information data related to a character string not including at least part of the symbol. ,
Information processing device. The data generation unit extracts at least a part of a word representing onomatopoeia included in the dish information from the dish information corresponding to the first action history, and extracts based on the attribute of the first user Generating the relationship information data representing a correspondence relationship between at least part of a word representing onomatopoeia and an attribute of the first user;
The information processing apparatus according to claim 1. The estimation unit prioritizes the relation information data relating to at least a part of the word representing the onomatopoeia over the relation information data relating to a character string not including at least a part of the word representing the onomatopoeia. Infer user attributes,
The information processing apparatus according to claim 2. An action history acquisition unit for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation unit for generating information data;
An estimation unit that estimates the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing unit for providing information to the second user based on the estimated attribute of the second user,
The data generation unit extracts at least a part of a word representing onomatopoeia included in the dish information from the dish information corresponding to the first action history, and extracts based on the attribute of the first user Generating the relationship information data representing a correspondence relationship between at least part of a word representing onomatopoeia and an attribute of the first user;
The estimation unit prioritizes the relation information data relating to at least a part of the word representing the onomatopoeia over the relation information data relating to a character string not including at least a part of the word representing the onomatopoeia. Infer user attributes,
Information processing device. An action history acquisition unit for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation unit for generating information data;
An estimation unit that estimates the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing unit for providing information to the second user based on the estimated attribute of the second user,
The data generation unit generates the relationship information data representing a correspondence relationship between the character string related to recipe information indicating a cooking procedure and the attributes of the first user, and the recipe information corresponding to the first action history Extracting at least a part of a symbol included in the title, and generating the relationship information data representing a correspondence relationship between the extracted at least a part of the symbol and the attribute of the first user,
The estimation unit estimates the attribute of the second user in preference to the relation information data related to at least part of the symbol over the relation information data related to a character string not including at least part of the symbol. ,
Information processing system. An information processing method in an information processing apparatus,
An action history acquisition step for acquiring an action history representing each user's action on the website for posting the cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation step for generating information data;
An estimation step of estimating the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relation information data;
An information providing step of providing information to the second user based on the estimated attribute of the second user,
In the data generating step, the recipe information corresponding to the first action history is generated by generating the relation information data representing a correspondence relation between the character string relating to recipe information indicating a cooking procedure and the attribute of the first user. Extracting at least a part of a symbol included in the title, and generating the relationship information data representing a correspondence relationship between the extracted at least a part of the symbol and the attribute of the first user,
In the estimation step, the attribute of the second user is estimated in preference to the relationship information data related to at least a part of the symbol over the relationship information data related to a character string not including at least a part of the symbol. ,
Information processing method. On the computer,
An action history acquisition process for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation process for generating information data;
An estimation process for estimating the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing process for providing information to the second user based on the estimated attribute of the second user, and a program for executing the information providing process,
In the data generation process, the recipe information corresponding to the first action history is generated by generating the relation information data representing a correspondence relation between the character string related to recipe information indicating a cooking procedure and the attribute of the first user. Extracting at least a part of a symbol included in the title, and generating the relationship information data representing a correspondence relationship between the extracted at least a part of the symbol and the attribute of the first user,
In the estimation process, the attribute of the second user is estimated in preference to the relationship information data related to at least a part of the symbol over the relationship information data related to a character string not including at least a part of the symbol. ,
program. An action history acquisition unit for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation unit for generating information data;
An estimation unit that estimates the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing unit for providing information to the second user based on the estimated attribute of the second user,
The data generation unit extracts at least a part of a word representing onomatopoeia included in the dish information from the dish information corresponding to the first action history, and extracts based on the attribute of the first user Generating the relationship information data representing a correspondence relationship between at least part of a word representing onomatopoeia and an attribute of the first user;
The estimation unit prioritizes the relation information data relating to at least a part of the word representing the onomatopoeia over the relation information data relating to a character string not including at least a part of the word representing the onomatopoeia. Infer user attributes,
Information processing system. An information processing method in an information processing apparatus,
An action history acquisition step for acquiring an action history representing each user's action on the website for posting the cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation step for generating information data;
An estimation step of estimating the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relation information data;
An information providing step of providing information to the second user based on the estimated attribute of the second user,
In the data generation step, from the cooking information corresponding to the first action history, at least a part of a word representing onomatopoeia included in the cooking information is extracted, and extracted based on the attribute of the first user Generating the relationship information data representing a correspondence relationship between at least part of a word representing onomatopoeia and an attribute of the first user;
In the estimation step, the relation information data relating to at least a part of the word representing the onomatopoeia is given priority over the relation information data relating to a character string not including at least a part of the word representing the onomatopoeia. Infer user attributes,
Information processing method. On the computer,
An action history acquisition process for acquiring an action history representing an action of each user on a website posting cooking information;
A relationship representing a correspondence relationship between a character string included in the dish information and the attribute of the user based on the attribute of the first user whose attribute is known and the first behavior history indicating the behavior history of the first user A data generation process for generating information data;
An estimation process for estimating the attribute of the second user based on the second behavior history indicating the behavior history of the second user and the relationship information data;
An information providing process for providing information to the second user based on the estimated attribute of the second user, and a program for executing the information providing process,
In the data generation process, from the cooking information corresponding to the first action history, at least a part of a word representing onomatopoeia included in the cooking information is extracted, and extracted based on the attribute of the first user Generating the relationship information data representing a correspondence relationship between at least part of a word representing onomatopoeia and an attribute of the first user;
In the estimation process, the relation information data relating to at least a part of the word representing the onomatopoeia is given priority over the relation information data relating to a character string not including at least a part of the word representing the onomatopoeia. Infer user attributes,
program.

Images