WO2021000521A1 - 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质 - Google Patents

菜谱推荐方法、菜谱推荐装置以及机器可读存储介质 Download PDF

Info

Publication number
WO2021000521A1
WO2021000521A1 PCT/CN2019/124175 CN2019124175W WO2021000521A1 WO 2021000521 A1 WO2021000521 A1 WO 2021000521A1 CN 2019124175 W CN2019124175 W CN 2019124175W WO 2021000521 A1 WO2021000521 A1 WO 2021000521A1
Authority
WO
WIPO (PCT)
Prior art keywords
recipe
user
recipes
information
coefficient
Prior art date
Application number
PCT/CN2019/124175
Other languages
English (en)
French (fr)
Inventor
吕秀凤
王超
卞景富
陈泽伟
Original Assignee
合肥美的电冰箱有限公司
合肥华凌股份有限公司
美的集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 合肥美的电冰箱有限公司, 合肥华凌股份有限公司, 美的集团股份有限公司 filed Critical 合肥美的电冰箱有限公司
Publication of WO2021000521A1 publication Critical patent/WO2021000521A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0621—Item configuration or customization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations

Definitions

  • the present invention relates to the field of smart homes, in particular to a recipe recommendation method, a recipe recommendation device and a machine-readable storage medium.
  • the purpose of the embodiments of the present invention is to provide a recipe recommendation method, a recipe recommendation device, and a machine-readable storage medium.
  • a recipe recommendation method includes: acquiring a recipe and user information; and determining a recipe label of the recipe in a preset dimension according to the recipe. A set; determine the user tag set of the user information in the predetermined dimension according to the user information; determine the fit between the recipe and the user information according to the recipe tag set and the user tag set; and In a case where the fit is greater than a preset threshold, the recipe is recommended to the user.
  • the recipe includes multiple recipes
  • the recipe recommendation method further includes: determining the number of recipes of the multiple recipes whose fit is greater than a preset threshold; and when the number of recipes exceeds a preset number range In the case of adjusting the preset threshold value, the number of recipes is within the preset number range.
  • the determining the degree of fit between the recipe and the user information according to the recipe tag set and the user tag set includes: determining whether the recipe tag set corresponds to the user tag set in the recipe tag set. The number of associated tags associated with the tag; and the fit degree is determined according to the number of associated tags.
  • the predetermined dimension is an ingredient type dimension, a recipe type dimension, a user demand dimension, or an environment dimension.
  • the user information includes the food material category that the user pays attention to
  • the user tag set is a set of the food material category that the user pays attention to
  • the recipe The tag set is a collection of the types of ingredients included in the recipe
  • the determining the number of associated tags in the recipe tag set that is associated with the tags in the user tag set includes: determining the types of ingredients included in the recipe
  • the set is the number of the same types of foods in the set of food types that the user pays attention to.
  • the user information includes recipes that the user pays attention to
  • the user tag set is a set of attribute characteristics of all recipes that the user pays attention to.
  • the recipe tag set is a collection of attribute characteristics of the recipe itself
  • the determining the number of associated tags in the recipe tag set that is associated with the tags in the user tag set includes: determining the attribute of the recipe itself
  • the set of features has the same number of attribute features in the set of attribute features of all recipes that the user pays attention to.
  • the recipe that the user pays attention to is determined according to at least one of the following: the number of times the user searches for recipes, the number of times the user views the recipes, and the recipes favorited by the user.
  • the user information includes user demand information
  • the user tag set is a set of user demand characteristics determined according to the demand information
  • the recipe tag set is a set of recipe function features determined according to the recipe
  • the determining the number of associated tags in the recipe tag set that is associated with the tags in the user tag set includes: determining the recipe function The number of recipe function features associated with the user demand feature in the feature set.
  • the demand information includes physical demand information and/or taste demand information.
  • the user information includes environmental information where the user is currently located, and the user tag set is a set of environmental features determined according to the environmental information
  • the recipe tag set is a set of environmental features determined according to the recipe
  • the determining the number of associated tags in the recipe tag set that is associated with the tags in the user tag set includes: determining according to the environment The set of environmental features determined by the information has the same number of environmental features in the set of environmental features determined according to the recipe.
  • the environmental information includes at least one of the following: geographic information, time information, and weather information.
  • the preset dimensions include a plurality of preset dimensions, and each of the preset dimensions has its own dimensional coefficient
  • the recipe recommendation method further includes: respectively determining the need for recommendation according to each of the preset dimensions.
  • a set of recommended recipes for the user determine the inclusion relationship between each of the recipes and each of the recommended recipe sets; determine the first of each recipe according to the dimensional coefficient of each of the preset dimensions and the inclusion relationship A recipe coefficient; sort the recipes according to the first recipe coefficient; and recommend a predetermined number of recipes to the user according to the ranking.
  • the recipe recommendation method further includes: determining the ingredient coefficient of each ingredient according to the user information; determining the second recipe coefficient of each recipe according to the ingredient coefficient and the types of ingredients included in the recipe; wherein Sorting the recipes according to the first recipe coefficient includes: determining a final recipe coefficient of the recipe according to the first recipe coefficient and the second recipe coefficient; and ranking the recipe according to the final recipe coefficient .
  • the user information includes the stored time of each food material
  • the determining the food material coefficient of each food material according to the user information includes: according to the stored time of the food material and a predetermined availability of the food material
  • the storage time determines the storage time ratio; and the food material coefficient of the food material is determined according to the storage time ratio.
  • the user information further includes at least one of the types of ingredients that the user pays attention to, the recipes that the user pays attention to, the user's demand information, and the user's environment information, and the ingredients of each ingredient are determined according to the user information.
  • the coefficient includes: determining the food material coefficient of the food material according to at least one of the type of food material that the user pays attention to, the recipe that the user pays attention to, the user's demand information, and the environmental information where the user is located, and the storage time ratio.
  • a recipe recommendation device configured to execute the above-mentioned recipe recommendation method; a human-computer interaction module configured to recommend needs to users Of the recipe is communicated to the user.
  • the recipe recommendation device is a refrigeration device or a mobile device.
  • a machine-readable storage medium stores instructions on which are used to enable the processor to execute the above-mentioned recipe when executed by a processor Recommended method.
  • the recipes can be recommended to the users according to the degree of fit, which can be recommended to the users.
  • the recipes are more in line with the user’s eating habits, save the time for users to find recipes, and improve user experience.
  • Fig. 1 exemplarily shows a flowchart of a recipe recommendation method provided by an embodiment of the present invention
  • FIG. 2 exemplarily shows a flowchart of a method for determining the type of food that a user pays attention to according to an optional embodiment of the present invention
  • FIG. 3 exemplarily shows a flow chart of a method for recommending recipes according to the dimension of food types according to an alternative embodiment of the present invention
  • FIG. 4 exemplarily shows a flow chart of a method for recommending recipes based on multiple dimensions provided by an alternative embodiment of the present invention
  • Fig. 5 exemplarily shows a block diagram of factors for determining recommended recipes provided by an alternative embodiment of the present invention.
  • Fig. 6 exemplarily shows a block diagram of a recipe recommendation device provided by an embodiment of the present invention.
  • Control module 20 Human-computer interaction module
  • the directional indication is only used to explain that it is in a certain posture (as shown in the drawings). If the specific posture changes, the relative positional relationship, movement, etc. of the components below will also change the directional indication accordingly.
  • Fig. 1 exemplarily shows a flowchart of a recipe recommendation method provided by an embodiment of the present invention.
  • an embodiment of the present invention provides a recipe recommendation method, and the recipe recommendation method may include:
  • Step S11 obtaining recipes and user information.
  • Step S12 Determine the recipe label set of the recipe in the preset dimension according to the obtained recipe.
  • Step S13 Determine a user tag set of the user information in a predetermined dimension according to the obtained user information.
  • Step S14 Determine the degree of fit between the recipe and the user information according to the recipe tag set and the user tag set.
  • Step S15 in the case where the fit is greater than the preset threshold, recommend the recipe to the user.
  • the recipes recommended to the user can be more consistent
  • the recipe recommendation method may be implemented based on a recipe recommendation device such as a mobile device or a refrigerating device.
  • the mobile device may include a mobile phone, a tablet computer, or a laptop, and the refrigerating device may include a refrigerator or a freezer.
  • the recipe recommendation device can acquire user information and multiple recipes. Among them, the user information may be entered by the user himself, or detected by other devices.
  • the recipe can be pre-stored in the recipe recommendation device, or it can be obtained from the Internet or a cloud server.
  • a predetermined dimension may be determined first, and the predetermined dimension may include a dimension of food types, a dimension of recipe types, a dimension of user needs, or an environmental dimension. In other words, you can start from different dimensions to recommend suitable recipes for users.
  • multiple tags can be included.
  • a label that matches the user information in the preset dimension can be determined, and a user label set can be formed.
  • the fit between the recipe and the user information can be determined according to the recipe tag set and the user tag set, and recipes with a fit greater than a preset threshold are recommended to the user. It should be noted that the order between the above step S12 and step S13 can be interchanged.
  • the preset threshold may be an integer greater than or equal to 1, and may be predetermined according to conditions such as actual needs of the user and the total number of recipes that can be obtained.
  • the preset threshold may be fixed or variable.
  • the preset threshold can be dynamically adjusted according to the number of recommended recipes. Specifically, the number of recipes of a plurality of recipes whose fit is greater than a preset threshold can be determined first, and if the number of recipes exceeds the preset number range, the preset threshold can be adjusted so that the number of recipes is within the preset number range .
  • the preset threshold can be lowered to make the fit greater than The preset threshold value is between 5 and 8 recipes; if 10 recipes with a fit greater than the preset threshold can be obtained based on the current preset threshold, the preset threshold can be increased to make the recipe with a fit greater than the preset threshold Between 5 and 8.
  • the recipes can be sorted according to the fit of each recommended recipe, and the recipes with a large fit can be recommended to the user first.
  • step S14 may include:
  • Step S141 Determine the number of associated tags in the recipe tag set that are associated with the tags in the user tag set.
  • Step S142 Determine the fit degree according to the number of associated tags.
  • the recipe tag set of each recipe can be compared with the user tag set to determine which tags in the recipe tag set are the same as the user tag.
  • the corresponding tags in the set are associated, and the number of associated tags associated with the tags in the user tag set is counted.
  • the degree of fit between the recipe and the user information is determined.
  • the number of associated tags can be directly used to indicate the degree of fit, or the ratio between the number of associated tags and the total number of tags in the user tag set may be used to indicate the degree of fit.
  • the user information may include the food material category that the user pays attention to.
  • the user tag set may be a collection of food types that the user pays attention to, and the recipe tag set may be a set of food types included in the recipe.
  • the types of ingredients that the user pays attention to can be determined by obtaining information such as the types of ingredients stored in the user's refrigerator, the frequency of each ingredient purchased by the user, and the lack of reminders for common ingredients set by the user. For example, it is possible to obtain the frequency of each ingredient purchased by the user and the types of ingredients that the user sets frequently used ingredients lacking reminders, and detect the types of ingredients stored in the refrigerator.
  • the types of ingredients stored in the user's refrigerator can be used as the types of ingredients that the user pays attention to, and the types of ingredients that are ranked by the user's purchase frequency and the types of ingredients that the user sets for lack of reminders can be used as the types of ingredients that the user pays attention to.
  • the existing ingredients in the user's refrigerator do not have tomatoes or pork, but tomatoes and pork are ranked first and second in the list of frequently purchased products by the user, tomatoes and pork can also be used as the types of ingredients that the user pays attention to.
  • the user does not have eggs in the refrigerator, but the user manually sets the egg lack of a reminder function, that is, as long as the number of eggs in the refrigerator is below a certain threshold, the user will be reminded to buy eggs.
  • a reminder function that is, as long as the number of eggs in the refrigerator is below a certain threshold
  • eggs can be regarded as the type of food that users pay attention to.
  • the types of ingredients stored in the refrigerator can be detected by installing a camera on the refrigerator and identifying the types of ingredients in the refrigerator through the camera, or by installing a scanner on the refrigerator and scanning the identification code on the ingredients through the scanner.
  • the set of types of ingredients included in the recipe can be compared with the set of types of ingredients that the user pays attention to.
  • the number of the same food types in the two sets is the number of associated tags in the above-mentioned recipe tag set. That is, the base of the intersection of the set of food types included in the recipe and the set of food types that the user pays attention to is the number of associated tags in the recipe tag set.
  • the set of food types that the user pays attention to is T1. Since the main ingredients and auxiliary materials included in each recipe are known, the information about the types of food contained in each recipe can be obtained.
  • the sets T21, T22,...T2n and T1 can be intersected respectively to obtain T31, T32,...T3n.
  • the cardinality of the sets T31, T32,...T3n is determined, and the recipes corresponding to the set whose cardinality is greater than the preset threshold are recommended to the user.
  • the base of the set T31 is 4>3, so the set T31 can correspond to ( That is, the recipe corresponding to the set T21 is recommended to the user, and the base of the set T32 is 2 ⁇ 3, so the recipe corresponding to the set T32 (that is, the recipe corresponding to the set T22) will not be recommended to the user.
  • the recipes can also be sorted according to the fit of each recipe recommended to the user. That is, the recommendation order is determined according to the cardinal size of the intersection corresponding to each recipe recommended to the user. Since the recipes with a large cardinality of the intersection are more in line with user needs, the recipes can be sorted according to the cardinality of the intersection from large to small, and the recipes with a large cardinality are first recommended to users.
  • the user information may include the recipe that the user pays attention to, and the user tag set may be a collection of attribute characteristics of all recipes that the user pays attention to.
  • the label set may be a set of attribute characteristics of the recipe itself.
  • the recipe that the user pays attention to can be determined according to at least one of the following: the number of times the user searches for the recipe, the number of times the user views the recipe, and the recipes that the user favorites. That is to say, it is possible to obtain the user’s search habits for recipe search through terminals such as the refrigerator or mobile phone APP through search box input or voice search, and the user’s viewing habit of viewing recipes through various portals through terminals such as refrigerator or mobile phone APP.
  • the recipes that the user favorites, and determine the recipes that the user pays attention to based on the acquired search habits, viewing habits, and favorite recipes of the user can be regarded as the recipes that the user pays attention to, and the recipes with the number of searches and/or viewing times greater than the preset value are also regarded as the recipes that the user pays attention to.
  • the attribute feature of the recipe that the user pays attention to can be determined.
  • the attribute feature may include, for example, the recipe cuisine (Hunan, Sichuan, Cantonese, etc.), the season corresponding to the recipe (spring, summer, autumn, winter), and the recipe Main ingredients, recipe types (meat and vegetarian), etc.
  • the attribute feature set of all the recipes that the user pays attention to can be used as the user tag set
  • the attribute feature set of each recipe itself can be used as the recipe tag set of each recipe
  • the attribute feature set of the recipe itself can be combined with the user's attention
  • the number of the same attribute feature in the attribute feature set of all the recipes is used as the number of associated tags in the recipe tag set. That is, the base of the intersection of the set of attribute characteristics of the recipe itself and the set of attribute characteristics of all recipes that the user pays attention to can be taken as the number of associated tags of the recipe tag set.
  • the user tag set may include the following tags: Hunan cuisine, Sichuan cuisine, fish, duck.
  • the recipe tag set of the recipe may include the following tags: Hunan cuisine, chicken, and the number of associated tags in the recipe tag set is 1, that is, Hunan cuisine.
  • the types of recipes viewed, searched, and collected by the user can be fully considered, so that the recipes recommended to the user are more consistent with the recipes expected by the user, and therefore more in line with the needs of the user.
  • the user information when the preset dimension is the user demand dimension, the user information may include user demand information, and the user tag set may be a set of user demand characteristics determined according to the demand information.
  • the label set may be a set of functional features of the recipe determined according to the recipe.
  • the demand information may include physical demand information and/or taste demand information. In other words, the demand information can be determined according to the user's physical condition and taste preferences. It should be noted that the user can refer to one user or all members of a family.
  • the user's physical demand information and taste demand information can be directly or indirectly obtained through terminals such as refrigerators, mobile phone APPs, and household-related networked small appliances.
  • terminals such as refrigerators, mobile phone APPs, and household-related networked small appliances.
  • users can directly enter physical needs information and taste information through recipe recommendation devices such as refrigerators or mobile phones, and smart scales that are associated with recipe recommendation devices via WiFi or Bluetooth can obtain user weight information or body fat information, and then The user's body requirement information is determined according to the user's weight information or body fat information (for example, when the body weight is overweight, the body requirement information is determined to be "less fat” and "less sugar”).
  • the user's exercise information can also be obtained through a bracelet that is associated with the recipe recommendation device via wifi or Bluetooth, or the user's blood pressure information can be obtained through a blood pressure meter.
  • the set of user demand characteristics can be determined according to the demand information. For example, if the demand information indicates that the user does not like spicy food and prefers vegetarian dishes, the set of user demand characteristics may include the following two tags: no spicy and vegetarian dishes.
  • the set of recipe function characteristics of each recipe can be obtained, and the number of recipe function characteristics associated with the user demand feature in the set of recipe function characteristics is used as the number of associated tags of the recipe label set.
  • the set of functional features of the recipe may include the following tags: Cantonese cuisine, meat dishes. Since Cantonese cuisine does not contain hot peppers, Cantonese cuisine is associated with "No Spicy", so that the number of associated tags in the recipe tag set is 1, namely Cantonese cuisine.
  • the user information when the preset dimension is the environmental dimension, may include the environmental information where the user is currently located, and the user tag set may be a set of environmental characteristics determined according to the environmental information, and the recipe The label set may be a set of environmental characteristics determined according to the recipe.
  • the environmental information may include at least one of geographic information, time information, and weather information.
  • the user's location, weather of the day, seasonal solar terms, seasons, holidays and other information can be used as environmental information; after obtaining environmental information, the set of environmental characteristics can be determined based on geographic information, time information, and weather information.
  • geographic information can be obtained by locating users, and information such as weather, seasonal solar terms, seasons, and holidays can be obtained through the Internet.
  • information such as weather, seasonal solar terms, seasons, and holidays
  • the set of environmental characteristics determined according to the environmental information may include the following tags: Northeast, Winter.
  • the number of the same environmental feature in the set of environmental features determined according to the environmental information and the set of environmental features determined based on the recipe may be used as the associated label of the recipe label set quantity. That is, the base of the intersection of the set of environmental features determined according to the environmental information and the set of environmental features determined according to the recipe may be used as the number of associated tags of the recipe tag set. For example, if a recipe is Northeastern cuisine and its ingredients are ingredients that can be obtained in winter in Northeast China, the set of environmental characteristics of the recipe may include the following tags: Northeast, Winter. Therefore, relative to the above-mentioned set of environmental characteristics determined according to environmental information, the number of associated tags in the set of recipe tags is two, namely, northeast and winter.
  • different types of environmental features can be set with different priorities.
  • the priority of the holiday environment feature may be set to the highest, and when the holiday environment feature determined according to the recipe is associated with the holiday environment feature determined according to the user's environment information, the recipe is preferentially recommended.
  • the recipes with the environmental characteristics of the Lantern Festival are preferred; when the day is determined to be the Dragon Boat Festival based on the user's environmental information, the environment with the Dragon Boat Festival is preferred Characteristic recipes. In this way, recipe recommendations can be made more flexible and intelligent.
  • the environment information of the user can be fully considered, so that the recipes recommended to the user are more consistent with the environment where the user is located. For example, hot soup for nourishing stomach can be recommended for users in winter, and cold dishes and soup for refreshing summer heat can be recommended for users in summer.
  • the embodiment of the present invention also provides a method for recommending recipes for users based on multiple dimensions.
  • the preset dimensions may include multiple preset dimensions, and each preset dimension may have its own dimensional coefficient.
  • the recipe recommendation method may include:
  • step S21 a set of recommended recipes to be recommended to the user is determined according to each preset dimension.
  • Step S22 Determine the containment relationship between each recipe and each recommended recipe set.
  • Step S23 Determine the first recipe coefficient of each recipe according to the dimension coefficient of each preset dimension and the determined inclusion relationship.
  • Step S24 Sort the recipes according to the first recipe coefficients.
  • Step S25 Recommend a predetermined number of recipes to the user according to the ranking.
  • the predetermined dimension may include the dimension of food types, the dimension of recipe types, the dimension of user requirements, or the dimension of environment.
  • the dimension coefficients of the food type dimension, the recipe type dimension, the user demand dimension, or the environment dimension can be represented by Q 1 to Q 4 respectively.
  • the dimensional coefficient can be directly proportional to the recipe coefficient, and recipes with a large recipe coefficient can be recommended to users first.
  • the dimensional system of each dimension can be defined and self-adjusted according to the importance of different situations. For example, dimensions with more comprehensive information acquisition and/or higher frequency of use may have larger dimensional coefficients, and dimensions with incomplete information acquisition and/or lower frequency of use may have lower dimensional coefficients.
  • a fixed dimension coefficient can be set for each dimension according to the actual situation.
  • the dimensional coefficients of the food type dimension and the recipe type dimension are relatively larger, and the dimensional coefficients of the user demand dimension and the environmental dimension are relatively smaller.
  • the dimensional coefficient of the user demand dimension can be set to be relatively low.
  • the dimensional coefficient of the recipe category dimension is set to be relatively high.
  • the user has entered complete user demand information, and is associated with small home appliances such as sports bracelets and weight scales, but rarely actively searches and view recipes. Generally, only the recommended recipes are viewed, indicating that the user is more concerned about individuals Healthy, because the dimensional coefficient of the user demand dimension can be set relatively high, and the dimensional coefficient of the recipe category dimension can be set relatively low.
  • the recommended recipe set that needs to be recommended to the user can be determined based on each dimension. Then, for any recipe, the inclusion relationship between the recipe and each recommended recipe set can be determined. The dimensional coefficient and the determined inclusion relationship determine the first recipe coefficient of each recipe. For example, if recipe A is included in the recommended recipe set determined according to the dimensions of the ingredients and also included in the recommended recipe set determined according to the dimensions of the recipe, then the first recipe coefficient of the recipe A can be (Q 1 ⁇ Q 4 ) Or (Q 1 +Q 4 ).
  • all recipes can be sorted by the first recipe coefficient according to the first recipe coefficient of each recipe (for example, sorted by the first recipe coefficient from large to small), and the A predetermined number of recipes are recommended to the user.
  • the top 5 recipes may be recommended to the user, or the top 3 recipes and the 2 middle ranked recipes may be recommended to the user.
  • the recipe that needs to be recommended to the user can also be determined according to the dimensional coefficients of different dimensions and the types of ingredients included in the recipe.
  • the ingredient coefficient of each ingredient can be determined according to the obtained user information
  • the second recipe coefficient of each recipe can be determined according to the ingredient coefficient of each ingredient and the types of ingredients included in the recipe, and then the second recipe coefficient of each recipe is determined according to the first recipe coefficient and the first recipe coefficient.
  • the recipe coefficient determines the final recipe coefficient of the recipe, and ranks the recipes according to the final recipe coefficient, so as to recommend the top-ranked recipes to the user.
  • food ingredients each coefficient can be expressed by P i, where i represents the type of food.
  • the ingredient coefficient can be determined mainly based on the storage time ratio K.
  • the storage time ratio K the relative storage time of each ingredient can be determined.
  • the recipe coefficient of a recipe can be directly proportional to the ingredient coefficient of the ingredients it includes.
  • the ingredient coefficient is larger, the recipe coefficient of the recipe including the ingredient is relatively larger, and the ingredients with longer storage time can be given priority. Recommend to users.
  • the ingredient coefficient may be modified according to at least one of the type of ingredient that the user pays attention to, the recipe that the user pays attention to, the user's demand information, and the environmental information where the user is located. That is to say, the user's search habits and viewing habits included in the user information, the user's physical needs information and taste demand information, and seasonal weather and geographic information can be used as the correction factor for the ingredient coefficient determined according to the storage time ratio K.
  • a set of recommended recipes according to the food type dimension, the recipe type dimension, the user demand dimension, and the environment dimension may be determined based on the types of ingredients the user pays attention to, the recipes the user pays attention to, the user's demand information, and the user's environment information.
  • the food material coefficient of the food material may be increased by a preset value according to the dimensional coefficient of the recommended recipe set.
  • the final recipe coefficient of the recipe can be determined according to the ingredient coefficient of each ingredient included in the recipe and the dimensional coefficient corresponding to the recommended recipe set where the recipe is located. Specifically, the dimensional coefficient of each dimension and the ingredient coefficient of each ingredient can be obtained first, and then the final recipe coefficient of the recipe is determined according to the dimension corresponding to the recommended recipe set where the recipe is located and the types of ingredients included in the recipe.
  • the first recipe coefficient of the recipe may be Q 1 ⁇ Q 4
  • the second recipe coefficient of the recipe may be P cabbage ⁇ P pork
  • the final recipe coefficient of the recipe may be (Q 1 ⁇ Q 4 ) ⁇ (P cabbage ⁇ P pork ).
  • the final recipe coefficient of each recipe can be determined, so that the recipes can be sorted according to the value of the final recipe coefficient of each recipe.
  • the recipes can be sorted according to the value of the final recipe coefficient from large to small, and A predetermined number (for example, 5) of the top-ranked recipes are recommended to the user.
  • the above-mentioned solution of the present invention can recommend recipes for users by combining ingredients factors and dimensional factors.
  • the recipe recommended to the user may be determined based on the dimensional coefficient of each dimension, the ingredient coefficient of the ingredients included in each recipe, and the correlation between the recipe and each dimension.
  • the ingredient coefficient and dimensionality coefficient can be determined according to various user information such as the ratio of ingredient storage time, ingredient storage habits, user search and viewing habits, user's physical needs information and taste demand information, and seasonal weather and geographic information. And determine the final recipe coefficient according to the ingredient coefficient and the dimension coefficient, and then recommend the recipe to the user according to the final recipe coefficient. In this way, it is possible to more accurately recommend recipes that conform to the user's living habits, thereby improving user experience.
  • the embodiment of the present invention also provides a recipe recommendation device, which may include a control module 10 and a human-computer interaction module 20.
  • the control module 10 is configured to execute the above-mentioned recipe recommendation method.
  • the human-computer interaction module 20 is configured to convey the recipes that need to be recommended to the user to the user.
  • the recipe recommending device may be a refrigerating device or a mobile device, the refrigerating device may be a refrigerator or a freezer, etc., and the mobile device may be a mobile phone, a tablet computer, or a notebook computer.
  • the control module 10 may include a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with the DSP core, a controller, and a microcontroller , Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) circuit, any other type of integrated circuit (IC) and state machine, etc.
  • the human-computer interaction module 20 may include a display screen or a speaker, etc., that is, it may convey the recommended recipe to the user through a screen display or voice broadcast.
  • the embodiment of the present invention also provides a machine-readable storage medium having instructions stored on the machine-readable storage medium for enabling the processor to execute the aforementioned recipe recommendation method when executed by the processor.
  • the program is stored in a storage medium and includes several instructions to enable the single-chip microcomputer, chip or processor (processor) Execute all or part of the steps of the method described in each embodiment of the present invention.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种菜谱推荐方法、菜谱推荐装置以及机器可读存储介质，属于智能家居领域。该菜谱推荐方法包括：获取菜谱和用户信息（S11）；根据获取的菜谱确定该菜谱在预设维度中的菜谱标签集合（S12）；根据获取的用户信息确定该用户信息在预定维度中的用户标签集合（S13）；根据菜谱标签集合和用户标签集合确定菜谱与用户信息之间的契合度（S14）；在契合度大于预设阈值的情况下，将菜谱推荐给用户（S15）。该菜谱推荐方法可以使得推荐给用户的菜谱更加符合用户的饮食习惯，并节约用户查找菜谱的时间，提高用户体验。

Description

菜谱推荐方法、菜谱推荐装置以及机器可读存储介质
相关申请的交叉引用
本申请要求2019年7月4日提交的中国专利申请201910600511.X的权益，该申请的内容通过引用被合并于本文。
技术领域
本发明涉及智能家居领域，具体地涉及菜谱推荐方法、菜谱推荐装置以及机器可读存储介质。
背景技术
随着科技的进步，智能家居产品正逐步普及。智能家居产品的出现为人们提供了诸多便利，改变了人们的生活方式。在饮食方面，现有的智能家居产品一般只能为用户提供用户所搜索的菜谱，智能化程度低且费时费力，从而导致用户体验差。
发明内容
为至少部分地解决现有技术中存在的上述问题，本发明实施方式的目的是提供一种菜谱推荐方法、菜谱推荐装置以及机器可读存储介质。
为了实现上述目的，在本发明实施方式的第一方面，提供一种菜谱推荐方法，所述菜谱推荐方法包括：获取菜谱和用户信息；根据所述菜谱确定该菜谱在预设维度中的菜谱标签集合；根据所述用户信息确定该用户信息在所述预定维度中的用户标签集合；根据所述菜谱标签集合和所述用户标签集合确定所述菜谱与所述用户信息之间的契合度；以及在所述契合度大于预设阈值的情况下，将所述菜谱推荐给用户。
可选地，所述菜谱包括多个菜谱，所述菜谱推荐方法还包括：确定多个所述菜谱中契合度大于预设阈值的菜谱的菜谱数量；以及在所述菜谱数量超出预设数量范围的情况下，调整所述预设阈值，以使得所述菜谱数量在预设数量范围内。
可选地，所述根据所述菜谱标签集合和所述用户标签集合确定所述菜谱与所述用户信息之间的契合度包括：确定在所述菜谱标签集合中与所述用户标签集 合中的标签相关联的关联标签的数量；以及根据所述关联标签的数量确定所述契合度。
可选地，所述预定维度为食材种类维度、菜谱种类维度、用户需求维度或环境维度。
可选地，在所述预设维度为所述食材种类维度的情况下，所述用户信息包括用户关注的食材种类，所述用户标签集合为所述用户关注的食材种类的集合，所述菜谱标签集合为所述菜谱包括的食材种类的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：确定所述菜谱包括的食材种类的集合与所述用户关注的食材种类的集合中相同的食材种类的数量。
可选地，在所述预设维度为所述菜谱种类维度的情况下，所述用户信息包括用户关注的菜谱，所述用户标签集合为所述用户关注的全部菜谱的属性特征的集合，所述菜谱标签集合为所述菜谱自身的属性特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：确定所述菜谱自身的属性特征的集合与所述用户关注的全部菜谱的属性特征的集合中相同的属性特征的数量。
可选地，根据以下至少一者确定所述用户关注的菜谱：用户搜索菜谱的次数、用户查看菜谱的次数和用户收藏的菜谱。
可选地，在所述预设维度为所述用户需求维度的情况下，所述用户信息包括用户的需求信息，所述用户标签集合为根据所述需求信息确定的用户需求特征的集合，所述菜谱标签集合为根据所述菜谱确定的菜谱功能特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：确定所述菜谱功能特征的集合中与所述用户需求特征相关联的菜谱功能特征的数量。
可选地，所述需求信息包括身体需求信息和/或口味需求信息。
可选地，在所述预设维度为所述环境维度的情况下，所述用户信息包括用户当前所处的环境信息，所述用户标签集合为根据所述环境信息确定的环境特征的集合，所述菜谱标签集合为根据所述菜谱确定的环境特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包 括：确定根据所述环境信息确定的环境特征的集合与根据所述菜谱确定的环境特征的集合中相同的环境特征的数量。
可选地，所述环境信息包括以下至少一者：地域信息、时间信息和天气信息。
可选地，所述预设维度包括多个预设维度，且每个所述预设维度具有各自的维度系数，所述菜谱推荐方法还包括：根据每个所述预设维度分别确定需要推荐给用户的推荐菜谱集合；确定每个所述菜谱与每个所述推荐菜谱集合之间的包含关系；根据每个所述预设维度的维度系数和所述包含关系确定每个菜谱的第一菜谱系数；根据所述第一菜谱系数对所述菜谱进行排序；以及根据所述排序将预定数量的菜谱推荐给所述用户。
可选地，所述菜谱推荐方法还包括：根据所述用户信息确定每种食材的食材系数；根据所述食材系数和所述菜谱所包括的食材种类确定每个菜谱的第二菜谱系数；其中根据所述第一菜谱系数对所述菜谱进行排序包括：根据所述第一菜谱系数和所述第二菜谱系数确定所述菜谱的最终菜谱系数；根据所述最终菜谱系数对所述菜谱进行排序。
可选地，所述用户信息包括每种食材的已储存时间，所述根据所述用户信息确定每种食材的食材系数包括：根据所述食材的已储存时间和预先确定的所述食材的可储存时间确定存放时间比；以及根据所述存放时间比确定所述食材的食材系数。
可选地，所述用户信息还包括用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息中至少一者，所述根据所述用户信息确定每种食材的食材系数包括：根据用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息中至少一者和所述存放时间比确定所述食材的食材系数。
在本发明实施方式的第二方面，提供一种菜谱推荐装置，所述菜谱推荐装置包括：控制模块，被配置为执行上述的菜谱推荐方法；人机交互模块，被配置为将需要推荐给用户的所述菜谱传达给所述用户。
可选地，所述菜谱推荐装置为制冷设备或移动设备。
在本发明实施方式的第三方面，提供一种机器可读存储介质，该机器可读 存储介质上存储有指令，该指令用于在被处理器执行时使得所述处理器能够执行上述的菜谱推荐方法。
在上述技术方案中，通过为菜谱和用户信息设置标签，并根据菜谱的标签和用户信息的标签确定菜谱与用户信息之间的契合度，从而根据契合度为用户推荐菜谱，可以使得推荐给用户的菜谱更加符合用户的饮食习惯，并节约用户查找菜谱的时间，提高用户体验。
本发明实施方式的其它特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
附图是用来提供对本发明实施方式的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本发明实施方式，但并不构成对本发明实施方式的限制。在附图中：
图1示例性示出了本发明一种实施方式提供的菜谱推荐方法的流程图；
图2示例性示出了本发明一种可选实施方式提供的确定用户关注的食材种类的方法的流程图；
图3示例性示出了本发明一种可选实施方式提供的根据食材种类维度的菜谱推荐方法的流程图；
图4示例性示出了本发明一种可选实施方式提供的基于多维度的菜谱推荐方法的流程图；
图5示例性示出了本发明一种可选实施方式提供的用于确定推荐菜谱的因素的框图；以及
图6示例性示出了本发明一种实施方式提供的菜谱推荐装置的框图。
附图标记说明
10 控制模块 20 人机交互模块
具体实施方式
以下结合附图对本发明的具体实施方式进行详细说明。应当理解的是，此 处所描述的具体实施方式仅用于说明和解释本发明，并不用于限制本发明。
需要说明，若本发明实施方式中有涉及方向性指示(诸如上、下、左、右、前、后……)，则该方向性指示仅用于解释在某一特定姿态(如附图所示)下各部件之间的相对位置关系、运动情况等，如果该特定姿态发生改变时，则该方向性指示也相应地随之改变。
另外，若本发明实施方式中有涉及“第一”、“第二”等的描述，则该“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施方式之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本发明要求的保护范围之内。
图1示例性示出了本发明一种实施方式提供的菜谱推荐方法的流程图。如图1所示，本发明实施方式提供一种菜谱推荐方法，该菜谱推荐方法可以包括：
步骤S11，获取菜谱和用户信息。
步骤S12，根据获取的菜谱确定该菜谱在预设维度中的菜谱标签集合。
步骤S13，根据获取的用户信息确定该用户信息在预定维度中的用户标签集合。
步骤S14，根据菜谱标签集合和用户标签集合确定该菜谱与用户信息之间的契合度。
步骤S15，在契合度大于预设阈值的情况下，将该菜谱推荐给用户。
如此，通过为菜谱和用户信息设置标签，并根据菜谱的标签和用户信息的标签确定菜谱与用户信息之间的契合度，从而根据契合度为用户推荐菜谱，可以使得推荐给用户的菜谱更加符合用户的饮食习惯，并节约用户查找菜谱的时间，提高用户体验。
具体地，该菜谱推荐方法可以基于移动设备或制冷设备等菜谱推荐装置实现，该移动设备可以包括手机、平板电脑或笔记本电脑等，制冷设备可以包括冰箱或冰柜等。该菜谱推荐装置能够获取用户信息和多个菜谱。其中，该用户信息可以是用户自己录入的，也可以是通过其他设备检测到的。相应地，菜谱可以是 预先存储在菜谱推荐装置中的，也可以是从互联网或云端服务器获取的。在需要为用户推荐菜谱时，可以首先确定一个预定维度，该预定维度可以包括食材种类维度、菜谱种类维度、用户需求维度或环境维度等。也就是说，可以从不同的维度出发来为用户推荐合适的菜谱。在每个预定维度中，可以包括多个标签。在获取用户信息后，可以确定在该预设维度中与该用户信息相符合的标签，并形成用户标签集合。另外，还可以预先确定在该预设维度中与每个菜谱相符合的标签，并形成每个菜谱的菜谱标签集合。在确定用户标签集合与菜谱标签集合后，可以根据菜谱标签集合和用户标签集合确定该菜谱与用户信息之间的契合度，并将契合度大于预设阈值的菜谱推荐给用户。需要说明的是，上述步骤S12和步骤S13之间的顺序可以互换。
需要说明的是，预设阈值可以为大于或等于1的整数，并可以根据用户实际需要和能够获取的菜谱总数等条件进行预先确定。另外，该预设阈值可以是固定的，也可以是可变的。例如，该预设阈值可以根据推荐菜谱数量进行动态调整。具体地，可以首先确定多个菜谱中契合度大于预设阈值的菜谱的菜谱数量，如果该菜谱数量超出预设数量范围，则可以调整预设阈值，以使得该菜谱数量在预设数量范围内。举例来说，在需要给用户推荐5～8个菜谱的情况下，如果基于当前的预设阈值可以得到3个契合度大于预设阈值的菜谱，则可以降低预设阈值，以使得契合度大于预设阈值的菜谱处于5～8个之间；如果基于当前的预设阈值可以得到10个契合度大于预设阈值的菜谱，则可以增加预设阈值，以使得契合度大于预设阈值的菜谱处于5～8个之间。
此外，在根据契合度确定需要给用户推荐的菜谱后，可以根据每个被推荐菜谱的契合度大小对菜谱进行排序，并优先推荐契合度大的菜谱给用户。
进一步地，上述步骤S14可以包括：
步骤S141，确定在菜谱标签集合中与用户标签集合中的标签相关联的关联标签的数量。
步骤S142，根据关联标签的数量确定契合度。
具体地，在确定每个菜谱的菜谱标签集合和用户信息的用户标签集合后，可以将每个菜谱的菜谱标签集合分别与用户标签集合进行比对，以确定菜谱标签集合中哪些标签与用户标签集合中相应的标签相关联，并计算与用户标签集合中 的标签相关联的关联标签的数量。随后，根据菜谱的关联标签的数量，确定该菜谱与用户信息之间的契合度。其中，可以直接采用关联标签的数量来表示契合度，也可以采用关联标签的数量与用户标签集合的标签总数之间的比值表示契合度。
在本发明一种可选实施方式中，在预设维度为食材种类维度的情况下，用户信息可以包括用户关注的食材种类。用户标签集合可以为用户关注的食材种类的集合，菜谱标签集合可以为菜谱包括的食材种类的集合。如图2所示，用户关注的食材种类可以通过获取用户冰箱中存储的食材种类、用户购买的每种食材的频次以及用户设置的常用食材缺少提醒等信息确定。举例来说，可以获取用户购买的每种食材的频次和用户设置常用食材缺少提醒的食材种类，并检测冰箱中存储的食材种类。随后，可以将用户冰箱中存储的食材种类作为用户关注的食材种类，并且也可以将用户购买频次排序靠前的食材种类和用户设置食材缺少提醒的食材种类作为用户关注的食材种类。例如，用户冰箱中现有食材没有西红柿和猪肉，但是用户经常购买的清单排序中西红柿和猪肉位列第一和第二，则可以将西红柿和猪肉也作为用户关注的食材种类。再例如，用户冰箱中没有鸡蛋，但是用户通过手动设置鸡蛋缺少提醒功能，即只要冰箱内鸡蛋的数量低于一定的阈值就会提醒用户购买鸡蛋，可见用户对于鸡蛋的关注度和需求较高，因此可以将鸡蛋作为用户关注的食材种类。其中冰箱中存储的食材种类可以通过在冰箱上安装摄像头并通过摄像头识别冰箱内的食材种类来进行检测，或者可以在冰箱上安装扫描器并通过扫描器扫描食材上的识别码来进行检测。
在确定用户关注的食材种类后，可以将菜谱包括的食材种类的集合与用户关注的食材种类的集合进行比较。两个集合中相同的食材种类的数量即为上述菜谱标签集合的关联标签的数量。也就是说，菜谱包括的食材种类的集合与用户关注的食材种类的集合的交集的基数即为菜谱标签集合的关联标签的数量。
举例来说，如图3所示，用户关注的食材种类的集合为T1，由于每个菜谱中所包括的食材主料和辅料是已知的，因此可以获取每个菜谱所包含的食材种类的集合T21、T22、……T2n。随后，可以分别将集合T21、T22、……T2n与T1取交集，得到T31、T32、……T3n。之后，确定集合T31、T32、……T3n的基数，并将基数大于预设阈值的集合所对应的菜谱推荐给用户。例如，若预设阈值m＝3，集合T31＝(a、b、c、d)，集合T32＝(a、b)，则集合T31的基数为4＞3， 因此可以将集合T31对应的(也即集合T21对应的)菜谱推荐给用户，集合T32的基数为2≤3，因此集合T32对应的(也即集合T22对应的)菜谱不会推荐给用户。在确定推荐给用户的菜谱后，还可以根据每个推荐给用户的菜谱的契合度对这些菜谱进行排序。即根据每个推荐给用户的菜谱所对应的交集的基数大小确定推荐顺序。由于交集的基数大的菜谱更符合用户需求，因此菜谱可以根据交集的基数由大到小进行排序，并将基数大的菜谱优先推荐给用户。
在根据食材种类维度为用户推荐菜谱时，可以充分考虑用户当前存储的食材种类和经常购买的食材种类，从而使得推荐给用户的菜谱更符合用户的生活和消费习惯。
在本发明另一种可选实施方式中，在预设维度为菜谱种类维度的情况下，用户信息可以包括用户关注的菜谱，用户标签集合可以为用户关注的全部菜谱的属性特征的集合，菜谱标签集合可以为菜谱自身的属性特征的集合。其中，可以根据以下至少一者确定用户关注的菜谱：用户搜索菜谱的次数、用户查看菜谱的次数和用户收藏的菜谱。也就是说，可以获取用户通过冰箱或手机APP等终端以搜索框输入或者语音搜索等途径进行菜谱搜索的搜索习惯、用户通过冰箱或手机APP等终端以通过各种入口进行的菜谱查看的查看习惯以及用户收藏的菜谱，并根据获取的用户的搜索习惯、查看习惯和收藏的菜谱确定用户关注的菜谱。例如，可以将用户收藏的菜谱作为用户关注的菜谱，并将用户搜索次数和/或查看次数大于预设值的菜谱也作为用户关注的菜谱。
在获取用户关注的菜谱后，可以确定用户关注的菜谱的属性特征，该属性特征可以例如包括菜谱菜系(湘菜、川菜、粤菜等)、菜谱对应的时令(春季、夏季、秋季、冬季)、菜谱主要食材、菜谱种类(荤、素)等。随后，可以将用户关注的全部菜谱的属性特征的集合作为用户标签集合，将每个菜谱自身的属性特征的集合作为每个菜谱的菜谱标签集合，并将菜谱自身的属性特征的集合与用户关注的全部菜谱的属性特征的集合中相同的属性特征的数量作为菜谱标签集合的关联标签的数量。也就是说，可以将菜谱自身的属性特征的集合与用户关注的全部菜谱的属性特征的集合的交集的基数作为菜谱标签集合的关联标签的数量。
举例来说，如果用户关注的菜谱为湘菜、川菜，且主要食材为鱼、鸭等， 则用户标签集合可以包括以下标签：湘菜、川菜、鱼、鸭。如果一菜谱为湘菜且主要食材为鸡，则该菜谱的菜谱标签集合可以包括以下标签：湘菜、鸡，进而该菜谱标签集合的关联标签数量为1个，即湘菜。
在根据菜谱种类维度为用户推荐菜谱时，可以充分考虑用户查看、搜索和收藏的菜谱种类，从而使得推荐给用户的菜谱与用户期望的菜谱更加一致，因此更符合用户的需求。
在本发明一种可选实施方式中，在预设维度为用户需求维度的情况下，用户信息可以包括用户的需求信息，用户标签集合可以为根据该需求信息确定的用户需求特征的集合，菜谱标签集合可以为根据菜谱确定的菜谱功能特征的集合。其中，该需求信息可以包括身体需求信息和/或口味需求信息。也就是说，可以根据用户的身体情况和口味喜好确定该需求信息。需要说明的是，用户可以指一个用户，也可以指一个家庭的全部成员。
具体地，可以通过冰箱、手机APP以及家庭相关联的联网小家电等终端直接或间接获取的用户的身体需求信息和口味需求信息。例如，可以让用户直接通过冰箱或手机等菜谱推荐装置录入身体需求信息和口味需求信息，也可以由与菜谱推荐装置通过wifi或蓝牙进行关联的智能秤获取用户的体重信息或体脂信息，进而根据用户的体重信息或体脂信息确定用户的身体需求信息(例如，当体重过重时，确定身体需求信息为“少油脂”、“少糖”)。此外，还可以通过与菜谱推荐装置通过wifi或蓝牙进行关联的手环获取用户的运动信息，或者通过血压仪获取用户的血压信息等。另外，还可以通过对用户定位来获取用户所在的地域信息，并根据地域信息获取用户喜爱的菜系，进而根据用户喜爱的菜系确定用户的口味需求信息，并且还可以通过用户查看、搜索或收藏的菜谱确定用户的口味需求信息。
在获取用户的需求信息后，可以根据该需求信息确定用户需求特征的集合。例如，如果该需求信息表明用户不喜欢吃辣且偏爱素菜，则用户需求特征的集合可以包括以下两个标签：无辣、素菜。在确定用户需求特征的集合后，可以获取各个菜谱的菜谱功能特征的集合，并将菜谱功能特征的集合中与用户需求特征相关联的菜谱功能特征的数量作为菜谱标签集合的关联标签的数量。例如，当用户需求特征的集合包括：无辣、素菜，而一菜谱为粤菜且为荤菜，则该菜谱的功能 特征的集合可以包括以下标签：粤菜、荤菜。由于粤菜不含辣椒，因此粤菜与“无辣”相关联，从而该菜谱标签集合的关联标签数量为1个，即粤菜。
在本发明一种可选实施方式中，在预设维度为环境维度的情况下，用户信息可以包括用户当前所处的环境信息，用户标签集合可以为根据环境信息确定的环境特征的集合，菜谱标签集合可以为根据菜谱确定的环境特征的集合。具体地，环境信息可以包括地域信息、时间信息和天气信息中至少一者。也就是说，可以将用户所在的地域、当日天气、时令节气、季节、节假日等信息作为环境信息；在获取环境信息后，可以根据地域信息、时间信息和天气信息等确定环境特征的集合，以作为用户标签集合。其中，地域信息可以通过对用户进行定位来获取，天气、时令节气、季节、节假日等信息可以通过联网获取。举例来说，当根据环境信息确定用户所处的环境为东北地区的冬季时，则根据该环境信息确定的环境特征的集合可以包括以下标签：东北、冬季。
进一步地，在确定与用户的环境信息对应的环境特征后，可以将根据环境信息确定的环境特征的集合与根据菜谱确定的环境特征的集合中相同的环境特征的数量作为菜谱标签集合的关联标签的数量。也就是说，可以将根据环境信息确定的环境特征的集合与根据菜谱确定的环境特征的集合的交集的基数作为菜谱标签集合的关联标签的数量。例如，如果一菜谱为东北菜且其食材为东北地区冬季可获取的食材，则该菜谱的环境特征的集合可以包括以下标签：东北、冬季。因此，相对于上述根据环境信息确定的环境特征的集合，该菜谱标签集合的关联标签的数量为2个，即东北和冬季。
此外，可以为不同类型的环境特征(即标签)设置不同的优先级。例如，节日类环境特征的优先级可以设置为最高，当根据菜谱确定的节日类环境特征与根据用户的环境信息确定的节日类环境特征相关联时，优先推荐该菜谱。例如，当根据用户的环境信息确定当日为元宵节时，则优先推荐具有元宵节这一环境特征的菜谱；当根据用户的环境信息确定当日为端午节时，则优先推荐具有端午节这一环境特征的菜谱。如此，可以使菜谱推荐更加灵活、智能。
在根据环境维度为用户推荐菜谱时，可以充分考虑用户所处的环境信息，从而使得推荐给用户的菜谱与用户所处的环境更加一致。例如，可以在冬季为用户推荐养胃热汤，在夏季为用户推荐凉菜、清凉解暑汤。
以上描述了基于各个单一维度为用户推荐菜谱的方法。除此之外，本发明实施方式还提供一种基于多维度为用户推荐菜谱的方法。也就是说，预设维度可以包括多个预设维度，且每个预设维度可以具有各自的维度系数，该菜谱推荐方法可以包括：
步骤S21，根据每个预设维度分别确定需要推荐给用户的推荐菜谱集合。
步骤S22，确定每个菜谱与每个推荐菜谱集合之间的包含关系。
步骤S23，根据每个预设维度的维度系数和确定的包含关系确定每个菜谱的第一菜谱系数。
步骤S24，根据所述第一菜谱系数对所述菜谱进行排序。
步骤S25，根据所述排序将预定数量的菜谱推荐给所述用户。
具体地，该预定维度可以包括食材种类维度、菜谱种类维度、用户需求维度或环境维度等。其中，食材种类维度、菜谱种类维度、用户需求维度或环境维度的维度系数可以分别用Q 1～Q 4进行表示。维度系数可以与菜谱系数成正比，菜谱系数大的菜谱可以优先推荐给用户。其中，每个维度的维度系统可以根据不同情况下的重要程度进行定义和自调整。例如，信息获取较全面和/或使用频次较高的维度，其维度系数可以较大，信息获取不全和/或使用频次较低的维度，其维度系数较小。如果各个维度的信息完整程度差距不大和/或使用频次接近的情况下，可以根据实际情况为各个维度设定固定的维度系数。一般情况下，食材种类维度和菜谱种类维度的维度系数相对更大，用户需求维度和环境维度的维度系数相对更小。
举例来说，在上述四个维度中，若用户未进行任何家电关联，也未录入完整的用户需求信息，但是经常搜索和查看菜谱，则可以将用户需求维度的维度系数设置为相对较低，菜谱种类维度的维度系数设置为相对较高。在另一个例子中，用户录入了完整的用户需求信息，且关联了运动手环、体重秤等小家电，但很少主动搜索和查看菜谱，一般只看推荐的菜谱，则说明用户比较关注个人健康，因可以将用户需求维度的维度系数设置为相对较高，菜谱种类维度的维度系数设置为相对较低。
在一具体实施方式中，可以基于每个维度分别确定需要推荐给用户的推荐菜谱集合，随后对于任意菜谱而言，可以确定该菜谱与各个推荐菜谱集合的包含 关系，之后可以根据每个维度的维度系数和确定的包含关系确定每个菜谱的第一菜谱系数。举例来说，如果菜谱A既包含于根据食材维度确定的推荐菜谱集合中，又包含于根据菜谱维度确定的推荐菜谱集合中，则该菜谱A的第一菜谱系数可以为(Q 1×Q 4)或(Q 1+Q 4)。在确定第一菜谱系数后，可以根据每个菜谱的第一菜谱系数对全部菜谱按第一菜谱系数的大小进行排序(例如按第一菜谱系数由大到小进行排序)，并根据该排序将预定数量的菜谱推荐给用户，例如可以将排序最靠前的5个菜谱推荐给用户，或将排序最靠前的3个菜谱和2个排位靠中间的菜谱推荐给用户。
在本发明一种可选实施方式中，还可以根据不同维度的维度系数和菜谱所包括的食材种类确定需要推荐给用户的菜谱。具体地，可以根据获取的用户信息确定每种食材的食材系数，并根据每种食材的食材系数和菜谱所包括的食材种类确定每个菜谱的第二菜谱系数，随后根据第一菜谱系数和第二菜谱系数确定菜谱的最终菜谱系数，并根据该最终菜谱系数对菜谱进行排序，以将排序靠前的菜谱推荐给用户。其中，每种食材的食材系数可以用P i表示，其中i表示食材种类。该食材系数P i可以基于以下至少一个因素确定：食材已存放时间K1、食材可存放时间K2、存放时间比K(K＝K1/K2)、用户搜索习惯和查看习惯、用户的身体需求信息和口味需求信息、季节天气地域等环境信息等。
具体地，该食材系数可以主要根据存放时间比K确定。通过该存放时间比K可以确定每种食材的相对存放时间。即食材的存放时间比K越大，则说明该食材的相对存放时间越长，可存放时间越短，因此可以将该食材的食材系数设置的越大，以优先推荐包括该食材的菜谱。更具体地，菜谱的菜谱系数可以与其所包括的食材的食材系数成正比，在食材系数越大时，包括该食材的菜谱的菜谱系数也相对越大，进而可以优先将存放时间较长的食材推荐给用户。例如，白菜可以在冰箱内存放的时间为120天，即白菜的K2为120，用户家的白菜在冰箱已经存放了40天，即白菜的K1为40，则白菜的时间存放比K＝K1/K2＝40/120＝1/3，相应地，该白菜的食材系数也可以设置为1/3。
在根据存放时间比K确定食材系数后，还可以根据用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息中至少一者对食材系数进行修正。也就是说，可以根据用户信息中包括的用户搜索习惯和查看习惯、 用户的身体需要信息和口味需求信息、季节天气地域信息等信息作为根据存放时间比K确定的食材系数的修正因子。举例来说，可以分别基于用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息确定根据食材种类维度、菜谱种类维度、用户需求维度和环境维度的推荐菜谱集合。随后，可以确定四个推荐菜谱集合所包括的菜谱中包含哪些种类的食材，并根据每种食材所在的推荐菜谱集合修正该种类食材的食材系数。例如，如果某种食材处于一个推荐菜谱集合中，则可以根据该推荐菜谱集合的维度系数将该食材的食材系数相应增加预设值。
如图4所示，在确定每种食材的食材系数后，可以根据菜谱所包括的各个食材的食材系数和该菜谱所在的推荐菜谱集合对应的维度系数确定该菜谱的最终菜谱系数。具体来说，可以先获取每个维度的维度系数和每种食材的食材系数，随后根据该菜谱所在的推荐菜谱集合对应的维度和该菜谱所包括的食材种类确定该菜谱的最终菜谱系数。例如，如果一菜谱包含于根据食材种类维度和菜谱种类维度确定的推荐菜谱集合中，并且该菜谱包括白菜和猪肉两种食材时，则该菜谱的第一菜谱系数可以为Q 1×Q 4，该菜谱的第二菜谱系数可以为P 白菜×P 猪肉，该菜谱的最终菜谱系数可以为(Q 1×Q 4)×(P 白菜×P 猪肉)。基于上述方法，可以确定每个菜谱的最终菜谱系数，从而可以根据每个菜谱的最终菜谱系数的数值对菜谱进行排序，例如可以根据最终菜谱系数的数值由大到小对菜谱进行排序，并将排序在前的预定数量(例如5个)的菜谱推荐给用户。
如图5所示，本发明上述方案，可以综合食材因素和维度因素来为用户推荐菜谱。在为用户推荐菜谱时，可以基于每个维度的维度系数、每个菜谱所包括食材的食材系数以及菜谱与各个维度之间的相关性来确定推荐给用户的菜谱。具体来说，可以根据食材存放时间比、食材存放习惯、用户搜索习惯和查看习惯、用户的身体需求信息和口味需求信息、季节天气地域等环境信息等多种用户信息确定食材系数和维度系数，并根据食材系数和维度系数确定最终菜谱系数，进而根据该最终菜谱系数向用户推荐菜谱。如此可以更加精准地推荐符合用户的生活习惯的菜谱，从而提高用户体验。
相应地，如图6所示，本发明实施方式还提供一种菜谱推荐装置，该菜谱推荐装置可以包括控制模块10和人机交互模块20。其中，控制模块10被配置 为执行上述的菜谱推荐方法。人机交互模块20被配置为将需要推荐给用户的菜谱传达给所述用户。其中，该菜谱推荐装置可以为制冷设备或移动设备，该制冷设备可以为冰箱或冰柜等，该移动设备可以为手机、平板电脑或笔记本电脑等。控制模块10可以包括通用处理器、专用处理器、常规处理器、数字信号处理器(DSP)、多个微处理器、与DSP核心关联的一个或多个微处理器、控制器、微控制器、专用集成电路(ASIC)、现场可编程门阵列(FPGA)电路、其他任何类型的集成电路(IC)以及状态机等等。人机交互模块20可以包括显示屏或扬声器等，也就是说，可以通过画面显示或语音播报等方式来向用户传达推荐的菜谱。
此外，本发明实施方式还提供一种机器可读存储介质，该机器可读存储介质上存储有指令，该指令用于在被处理器执行时使得处理器能够执行上述的菜谱推荐方法。
以上结合附图详细描述了本发明的可选实施方式，但是，本发明并不限于上述实施方式中的具体细节，在本发明实施方式的技术构思范围内，可以对本发明实施方式的技术方案进行多种简单变型，这些简单变型均属于本发明实施方式的保护范围。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本发明实施方式对各种可能的组合方式不再另行说明。
本领域技术人员可以理解实现上述实施方式方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得单片机、芯片或处理器(processor)执行本发明各个实施方式所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
此外，本发明的各种不同的实施方式之间也可以进行任意组合，只要其不违背本发明实施方式的思想，其同样应当视为本发明所公开的内容。

Claims (18)

  1. 一种菜谱推荐方法，其特征在于，所述菜谱推荐方法包括：
    获取菜谱和用户信息；
    根据所述菜谱确定该菜谱在预设维度中的菜谱标签集合；
    根据所述用户信息确定该用户信息在所述预定维度中的用户标签集合；
    根据所述菜谱标签集合和所述用户标签集合确定所述菜谱与所述用户信息之间的契合度；以及
    在所述契合度大于预设阈值的情况下，将所述菜谱推荐给用户。
  2. 根据权利要求1所述的菜谱推荐方法，其特征在于，所述菜谱包括多个菜谱，所述菜谱推荐方法还包括：
    确定多个所述菜谱中契合度大于预设阈值的菜谱的菜谱数量；以及
    在所述菜谱数量超出预设数量范围的情况下，调整所述预设阈值，以使得所述菜谱数量在预设数量范围内。
  3. 根据权利要求1所述的菜谱推荐方法，其特征在于，所述根据所述菜谱标签集合和所述用户标签集合确定所述菜谱与所述用户信息之间的契合度包括：
    确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量；以及
    根据所述关联标签的数量确定所述契合度。
  4. 根据权利要求3所述的菜谱推荐方法，其特征在于，所述预定维度为食材种类维度、菜谱种类维度、用户需求维度或环境维度。
  5. 根据权利要求4所述的菜谱推荐方法，其特征在于，在所述预设维度为所述食材种类维度的情况下，所述用户信息包括用户关注的食材种类，所述用户标签集合为所述用户关注的食材种类的集合，所述菜谱标签集合为所述菜谱包括的食材种类的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：
    确定所述菜谱包括的食材种类的集合与所述用户关注的食材种类的集合中相同的食材种类的数量。
  6. 根据权利要求4所述的菜谱推荐方法，其特征在于，在所述预设维度为所述菜谱种类维度的情况下，所述用户信息包括用户关注的菜谱，所述用户标签集合为所述用户关注的全部菜谱的属性特征的集合，所述菜谱标签集合为所述菜谱自身的属性特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：
    确定所述菜谱自身的属性特征的集合与所述用户关注的全部菜谱的属性特征的集合中相同的属性特征的数量。
  7. 根据权利要求6所述的菜谱推荐方法，其特征在于，根据以下至少一者确定所述用户关注的菜谱：用户搜索菜谱的次数、用户查看菜谱的次数和用户收藏的菜谱。
  8. 根据权利要求4所述的菜谱推荐方法，其特征在于，在所述预设维度为所述用户需求维度的情况下，所述用户信息包括用户的需求信息，所述用户标签集合为根据所述需求信息确定的用户需求特征的集合，所述菜谱标签集合为根据所述菜谱确定的菜谱功能特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：
    确定所述菜谱功能特征的集合中与所述用户需求特征相关联的菜谱功能特征的数量。
  9. 根据权利要求8所述的菜谱推荐方法，其特征在于，所述需求信息包括身体需求信息和/或口味需求信息。
  10. 根据权利要求4所述的菜谱推荐方法，其特征在于，在所述预设维度为所述环境维度的情况下，所述用户信息包括用户当前所处的环境信息，所述用户标签集合为根据所述环境信息确定的环境特征的集合，所述菜谱标签集合为根 据所述菜谱确定的环境特征的集合，所述确定在所述菜谱标签集合中与所述用户标签集合中的标签相关联的关联标签的数量包括：
    确定根据所述环境信息确定的环境特征的集合与根据所述菜谱确定的环境特征的集合中相同的环境特征的数量。
  11. 根据权利要求10所述的菜谱推荐方法，其特征在于，所述环境信息包括以下至少一者：地域信息、时间信息和天气信息。
  12. 根据权利要求1至11中任意一项权利要求所述的菜谱推荐方法，其特征在于，所述预设维度包括多个预设维度，且每个所述预设维度具有各自的维度系数，所述菜谱推荐方法还包括：
    根据每个所述预设维度分别确定需要推荐给用户的推荐菜谱集合；
    确定每个所述菜谱与每个所述推荐菜谱集合之间的包含关系；
    根据每个所述预设维度的维度系数和所述包含关系确定每个菜谱的第一菜谱系数；
    根据所述第一菜谱系数对所述菜谱进行排序；以及
    根据所述排序将预定数量的菜谱推荐给所述用户。
  13. 根据权利要求12所述的菜谱推荐方法，其特征在于，所述菜谱推荐方法还包括：
    根据所述用户信息确定每种食材的食材系数；
    根据所述食材系数和所述菜谱所包括的食材种类确定每个菜谱的第二菜谱系数；
    其中，根据所述第一菜谱系数对所述菜谱进行排序包括：
    根据所述第一菜谱系数和所述第二菜谱系数确定所述菜谱的最终菜谱系数；
    根据所述最终菜谱系数对所述菜谱进行排序。
  14. 根据权利要求13所述的菜谱推荐方法，其特征在于，所述用户信息包 括每种食材的已储存时间，所述根据所述用户信息确定每种食材的食材系数包括：
    根据所述食材的已储存时间和预先确定的所述食材的可储存时间确定存放时间比；以及
    根据所述存放时间比确定所述食材的食材系数。
  15. 根据权利要求14所述的菜谱推荐方法，其特征在于，所述用户信息还包括用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息中至少一者，所述根据所述用户信息确定每种食材的食材系数包括：
    根据用户关注的食材种类、用户关注的菜谱、用户的需求信息以及用户所处的环境信息中至少一者和所述存放时间比确定所述食材的食材系数。
  16. 一种菜谱推荐装置，其特征在于，所述菜谱推荐装置包括：
    控制模块，被配置为执行根据权利要求1至15中任意一项权利要求所述的菜谱推荐方法；
    人机交互模块，被配置为将需要推荐给用户的所述菜谱传达给所述用户。
  17. 根据权利要求16所述的菜谱推荐装置，其特征在于，所述菜谱推荐装置为制冷设备或移动设备。
  18. 一种机器可读存储介质，其特征在于，该机器可读存储介质上存储有指令，该指令用于在被处理器执行时使得所述处理器能够执行根据权利要求1至15中任意一项权利要求所述的菜谱推荐方法。
PCT/CN2019/124175 2019-07-04 2019-12-10 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质 WO2021000521A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910600511.X 2019-07-04
CN201910600511.XA CN110335118A (zh) 2019-07-04 2019-07-04 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质

Publications (1)

Publication Number Publication Date
WO2021000521A1 true WO2021000521A1 (zh) 2021-01-07

Family

ID=68143126

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/124175 WO2021000521A1 (zh) 2019-07-04 2019-12-10 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质

Country Status (2)

Country Link
CN (1) CN110335118A (zh)
WO (1) WO2021000521A1 (zh)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110335118A (zh) * 2019-07-04 2019-10-15 合肥美的电冰箱有限公司 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质
CN110955692B (zh) * 2019-11-29 2021-11-16 广东美的厨房电器制造有限公司 菜谱信息处理方法、处理装置、厨房电器及可读存储介质
CN111241292A (zh) * 2019-12-27 2020-06-05 珠海格力电器股份有限公司 一种菜谱推荐方法、装置、电子设备及存储介质
CN113158017A (zh) * 2020-01-22 2021-07-23 青岛海尔电冰箱有限公司 菜谱推荐方法、冰箱、计算机可读存储介质
CN111581491A (zh) * 2020-03-31 2020-08-25 海信集团有限公司 一种基于时间轴的菜谱推荐方法及系统
CN111552873A (zh) * 2020-04-21 2020-08-18 佛山市顺德区美的洗涤电器制造有限公司 菜谱推荐方法及装置、存储介质
CN111652312B (zh) * 2020-06-03 2023-02-07 上海维外科技有限公司 一种有选择特性的集合间契合程度的度量方法、系统以及存储介质
CN111881341B (zh) * 2020-06-15 2022-11-25 合肥美的电冰箱有限公司 饮食信息推荐方法及装置、电子设备及介质
CN111859121A (zh) * 2020-07-01 2020-10-30 海尔优家智能科技（北京）有限公司 用于菜谱推荐的方法及装置、设备
CN112035737B (zh) * 2020-08-05 2024-04-19 海尔优家智能科技（北京）有限公司 用于菜谱推荐的方法及装置、电子设备
CN112199593A (zh) * 2020-10-14 2021-01-08 珠海格力电器股份有限公司 一种菜谱的推荐方法以及装置
CN112232917B (zh) * 2020-10-23 2022-05-13 杭州拼便宜网络科技有限公司 电商平台的商品推荐方法、装置及设备
CN112417272A (zh) * 2020-11-11 2021-02-26 珠海格力电器股份有限公司 一种菜谱推荐方法、装置、电子设备及存储介质
CN113378042B (zh) * 2021-06-01 2022-11-18 青岛海尔空调器有限总公司 基于空调的点餐方法、装置和智能空调
CN113436034A (zh) * 2021-06-23 2021-09-24 青岛海尔科技有限公司 菜谱数据处理方法和装置
CN113488142A (zh) * 2021-07-28 2021-10-08 珠海格力电器股份有限公司 一种菜谱推荐方法、装置、存储介质以及设备
CN113672806A (zh) * 2021-08-04 2021-11-19 陈泽南 一种菜谱的推荐方法及装置、智能烹饪机器人
CN114741588A (zh) * 2022-03-04 2022-07-12 添可智能科技有限公司 目标电子菜谱的推荐方法、装置、烹饪设备及终端设备
WO2023165269A1 (zh) * 2022-03-04 2023-09-07 添可智能科技有限公司 目标电子菜谱的推荐方法、对象的参数确定方法、电子菜谱的参数确定方法、烹饪设备、终端设备、以及烹饪控制方法和装置
CN115104863A (zh) * 2022-08-22 2022-09-27 广东海新智能厨房股份有限公司 基于图像识别的智能橱柜及橱柜智能提示方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160029980A (ko) * 2014-09-05 2016-03-16 주식회사 디맨드 맞춤형 건강 식단 정보를 참조로 하여 자동으로 식재료를 주문하는 방법, 단말 및 컴퓨터 판단 가능한 기록 매체
CN106288634A (zh) * 2016-08-04 2017-01-04 海信集团有限公司 菜谱推荐方法、装置及智能冰箱
CN107992583A (zh) * 2017-12-07 2018-05-04 合肥美的智能科技有限公司 信息推送方法及信息推送装置、设备和存储介质
CN108769159A (zh) * 2018-05-16 2018-11-06 北京豆果信息技术有限公司 一种电子菜谱智能推荐方法
CN108806770A (zh) * 2018-05-16 2018-11-13 北京豆果信息技术有限公司 一种基于用户的膳食推荐方法
CN110335118A (zh) * 2019-07-04 2019-10-15 合肥美的电冰箱有限公司 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10068273B2 (en) * 2013-03-13 2018-09-04 Creator, Inc. Method for delivering a custom sandwich to a patron
US10474987B2 (en) * 2015-08-05 2019-11-12 Whirlpool Corporation Object recognition system for an appliance and method for managing household inventory of consumables
CN107423421A (zh) * 2017-07-31 2017-12-01 京东方科技集团股份有限公司 菜谱推荐方法、装置和冰箱
CN109815420A (zh) * 2019-03-27 2019-05-28 海信（山东）冰箱有限公司 一种信息推送方法及设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160029980A (ko) * 2014-09-05 2016-03-16 주식회사 디맨드 맞춤형 건강 식단 정보를 참조로 하여 자동으로 식재료를 주문하는 방법, 단말 및 컴퓨터 판단 가능한 기록 매체
CN106288634A (zh) * 2016-08-04 2017-01-04 海信集团有限公司 菜谱推荐方法、装置及智能冰箱
CN107992583A (zh) * 2017-12-07 2018-05-04 合肥美的智能科技有限公司 信息推送方法及信息推送装置、设备和存储介质
CN108769159A (zh) * 2018-05-16 2018-11-06 北京豆果信息技术有限公司 一种电子菜谱智能推荐方法
CN108806770A (zh) * 2018-05-16 2018-11-13 北京豆果信息技术有限公司 一种基于用户的膳食推荐方法
CN110335118A (zh) * 2019-07-04 2019-10-15 合肥美的电冰箱有限公司 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质

Also Published As

Publication number Publication date
CN110335118A (zh) 2019-10-15

Similar Documents

Publication Publication Date Title
WO2021000521A1 (zh) 菜谱推荐方法、菜谱推荐装置以及机器可读存储介质
CN106288634B (zh) 菜谱推荐方法、装置及智能冰箱
CN107871532A (zh) 一种饮食健康管理系统
US6975910B1 (en) Managing an electronic cookbook
WO2020098120A1 (zh) 订餐信息推荐方法、装置、电子设备及存储介质
US20110318717A1 (en) Personalized Food Identification and Nutrition Guidance System
WO2013047638A1 (ja) 店舗情報提供システム
CN110162688A (zh) 一种基于智能家居的冰箱食物推荐方法
CN106529158B (zh) 推荐饮食信息的方法及装置
US20170365182A1 (en) Indirect bio-feedback health and fitness management system
US11899738B2 (en) Methods and apparatus for recipe discovery and consumption logging
JP7411901B2 (ja) 情報提示方法、プログラム、及び情報提示システム
KR102189232B1 (ko) 생활 습관을 기반으로 콘텐츠를 제공하는 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체
US20190347707A1 (en) System and Method for Recommending Restaurant Food Items
Schäfer et al. User nutrition modelling and recommendation: Balancing simplicity and complexity
CN112951373A (zh) 一种食材推荐方法、设备、智能冰箱和智能终端
WO2007069118A2 (en) Context aware food intake logging
CN113158018A (zh) 食谱推荐方法、冰箱、计算机可读存储介质
CN113742579A (zh) 冰箱的食物推荐方法、食物推荐装置、存储介质及冰箱
US20210391051A1 (en) Information processing apparatus, information processing method, and program
JP2018084884A (ja) 情報処理装置、食材選択方法及びプログラム
CN116843403A (zh) 基于深度学习算法的学生餐饮偏好推荐系统
US20200118221A1 (en) System and method for making group decisions
WO2019123728A1 (ja) 食事履歴蓄積システム
US20220405335A1 (en) Information presentation method, recording medium, and information presentation system

Legal Events

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

Ref document number: 19936439

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19936439

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19936439

Country of ref document: EP

Kind code of ref document: A1