CN107992583B - Information pushing method, information pushing device, equipment and storage medium - Google Patents
Information pushing method, information pushing device, equipment and storage medium Download PDFInfo
- Publication number
- CN107992583B CN107992583B CN201711286498.2A CN201711286498A CN107992583B CN 107992583 B CN107992583 B CN 107992583B CN 201711286498 A CN201711286498 A CN 201711286498A CN 107992583 B CN107992583 B CN 107992583B
- Authority
- CN
- China
- Prior art keywords
- label
- recipe
- food material
- weight
- user
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000000463 material Substances 0.000 claims abstract description 376
- 235000013305 food Nutrition 0.000 claims abstract description 368
- 235000005911 diet Nutrition 0.000 claims abstract description 140
- 230000037213 diet Effects 0.000 claims abstract description 140
- 238000010411 cooking Methods 0.000 claims abstract description 139
- 235000019640 taste Nutrition 0.000 claims description 128
- 230000006399 behavior Effects 0.000 claims description 123
- 230000036541 health Effects 0.000 claims description 67
- 235000020785 dietary preference Nutrition 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 5
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 219
- 235000013311 vegetables Nutrition 0.000 description 13
- 210000002784 stomach Anatomy 0.000 description 11
- 241000219112 Cucumis Species 0.000 description 7
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 description 7
- FJJCIZWZNKZHII-UHFFFAOYSA-N [4,6-bis(cyanoamino)-1,3,5-triazin-2-yl]cyanamide Chemical compound N#CNC1=NC(NC#N)=NC(NC#N)=N1 FJJCIZWZNKZHII-UHFFFAOYSA-N 0.000 description 7
- 235000009508 confectionery Nutrition 0.000 description 7
- 230000029087 digestion Effects 0.000 description 7
- 235000013399 edible fruits Nutrition 0.000 description 7
- 230000002708 enhancing effect Effects 0.000 description 7
- 235000021384 green leafy vegetables Nutrition 0.000 description 7
- 230000036039 immunity Effects 0.000 description 7
- 230000001737 promoting effect Effects 0.000 description 7
- 238000012163 sequencing technique Methods 0.000 description 7
- 238000005728 strengthening Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 235000013372 meat Nutrition 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000003796 beauty Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 244000144972 livestock Species 0.000 description 4
- 244000291564 Allium cepa Species 0.000 description 3
- 235000002732 Allium cepa var. cepa Nutrition 0.000 description 3
- 244000046052 Phaseolus vulgaris Species 0.000 description 3
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 3
- 244000061458 Solanum melongena Species 0.000 description 3
- 235000002597 Solanum melongena Nutrition 0.000 description 3
- 241000404975 Synchiropus splendidus Species 0.000 description 3
- 235000013330 chicken meat Nutrition 0.000 description 3
- 235000014571 nuts Nutrition 0.000 description 3
- 235000020986 nuts and seeds Nutrition 0.000 description 3
- 235000013594 poultry meat Nutrition 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 235000002568 Capsicum frutescens Nutrition 0.000 description 2
- 206010016946 Food allergy Diseases 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 2
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 2
- 241000018646 Pinus brutia Species 0.000 description 2
- 235000011613 Pinus brutia Nutrition 0.000 description 2
- 244000013123 dwarf bean Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 235000019643 salty taste Nutrition 0.000 description 2
- 235000019654 spicy taste Nutrition 0.000 description 2
- 235000019605 sweet taste sensations Nutrition 0.000 description 2
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 1
- 241001247145 Sebastes goodei Species 0.000 description 1
- 235000015278 beef Nutrition 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000021331 green beans Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 235000013622 meat product Nutrition 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an information pushing method, which comprises the following steps: calculating a diet preference portrait of the user according to historical behavior data of the user; receiving a keyword input by a user to search an initial push list matched with the keyword in a cooking material database; determining the popularity index of each food material and/or recipe contained in the initial push list according to the diet preference portrait; sorting the food materials and/or recipes in the initial push list according to the popularity indexes of the food materials and/or recipes to obtain a target push list; and sending the target push list to the user. Correspondingly, the invention also provides an information pushing device, computer equipment and a computer readable storage medium. According to the technical scheme, the search keywords input by the user are intelligently prompted in a personalized mode according to the diet preference images of different users, and information push with clear purpose and high efficiency is achieved, so that the user experience is improved.
Description
Technical Field
The present invention relates to the field of information push technologies, and in particular, to an information push method, an information push apparatus, a computer device, and a computer-readable storage medium.
Background
At present, the existing keyword intelligent prompting scheme generally establishes a keyword library in advance, then performs screening in the keyword library after obtaining search keywords input by a user, and sorts screening results according to the sequence of pinyin initials, the keywords screened by the method do not predict search contents which may be really interesting to the user, and the degree of interest of the user is not considered in the sorting of the screening results, so that the screening results can have a condition which is not in accordance with the expectation of the user, and the user experience is low.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art or the related art.
Therefore, one purpose of the present invention is to provide a new information push method, which performs personalized intelligent prompting on search keywords input by a user according to diet preference pictures of different users, so as to realize purpose-specific and efficient information push, thereby improving user experience.
Another object of the present invention is to provide an information pushing apparatus, a computer device and a computer-readable storage medium.
To achieve at least one of the above objects, according to a first aspect of the present invention, there is provided an information pushing method, including: calculating a diet preference portrait of the user according to historical behavior data of the user; receiving a keyword input by a user to search an initial push list matched with the keyword in a cooking material database; determining the popularity index of each food material and/or recipe contained in the initial push list according to the diet preference portrait; sorting the food materials and/or recipes in the initial push list according to the popularity indexes of the food materials and/or recipes to obtain a target push list; and sending the target push list to the user.
In the technical scheme, in order to accurately push the really interested search content to the user when pushing the search content to the user, the dietary preference portrait of the user can be determined according to the past historical behavior data of the user, after an initial push list matched with a keyword is searched and determined in a cooking material number database according to the keyword input by the user, the popularity index of each food material and/or recipe contained in the initial push list is determined by combining the dietary preference portrait of the user, a target push list obtained by sequencing each food material and/or recipe according to the popularity index is further taken as a final push list to be sent to the user, so that the food material and/or recipe list according with the user interest is screened out based on the dietary preference portrait of the user and is pushed to the user after the list is sequenced according to the user interest program level, therefore, personalized intelligent prompting of the search keywords input by the user is achieved according to the diet preference pictures of different users, and clear and efficient information pushing is achieved, so that the user experience is improved.
In the above technical solution, preferably, the step of calculating the diet preference profile of the user according to the historical behavior data of the user includes: acquiring user behavior parameters contained in historical behavior data; determining behavior weight and behavior statistics times corresponding to each user behavior parameter to calculate the recipe weight of each recipe contained in the historical behavior data; calculating the recipe label weight corresponding to each recipe label and the food material weight corresponding to each food material contained in the historical behavior data according to the recipe weight of each recipe; calculating the food material category weight corresponding to each food material category contained in the historical behavior data according to the food material weight of each food material; and determining the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label.
In this technical solution, a recipe weight of each recipe included in the historical behavior data may be specifically calculated according to a behavior weight and a behavior statistics frequency corresponding to each user behavior parameter included in the historical behavior data of the user, and then a recipe label weight of each recipe label included in all recipe labels included in the historical behavior data and a food material weight of each food material included in all food materials included in the historical behavior data may be correspondingly calculated according to the recipe weights respectively corresponding to all recipes, and a food material category weight of each food material category included in all food material categories included in the historical behavior data may be correspondingly calculated according to the food material weights respectively corresponding to all food materials, that is, each recipe included in the historical behavior data of the user, each recipe label corresponding to the recipe, each contained food material, each food material, and a food material category included in the historical behavior data of the user, The food material categories corresponding to each food material have respective weights, and further, the diet preference portrait of the user can be accurately determined based on the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label, so that the contents to be pushed, which are screened according to the keywords input by the user, can be intelligently sequenced according to the interest of the user.
In any of the above technical solutions, preferably, the recipe label includes: taste label, cooking difficulty rating label, efficacy label; and the step of determining the diet preference portrait of the user according to the food material category weight of each food material category and the label weight of each recipe label comprises the following steps: determining a taste preference label of the user according to the weight of the recipe label corresponding to each taste label; determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty grade label; determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label; and determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
In the technical scheme, the recipe labels corresponding to each recipe included in the historical behavior data of the user may be one or more of a taste label, a cooking difficulty level label, and an efficacy label, and of course, the recipe labels include, but are not limited to, the taste label, the cooking difficulty level label, and the efficacy label, and may be specifically adjusted by adding according to the specific needs of the user.
Further, specifically, each taste label has a respective recipe label weight, for example, the taste labels of sour, sweet, bitter, spicy, salty and the like have corresponding recipe label weights, and then the taste preference label of the user for diet can be screened out based on the corresponding recipe label weights; each cooking difficulty level label has a respective recipe label weight, for example, the easy, general and difficult cooking difficulty level labels respectively have corresponding recipe label weights, and then the cooking skill label corresponding to the user can be determined based on the weights; each efficacy label has respective recipe label weight, for example, efficacy labels for strengthening stomach, promoting digestion, enhancing immunity, maintaining beauty, keeping young, nourishing stomach and the like have corresponding recipe label weight, so that a health attribute preference label of the user to diet can be determined based on the efficacy labels; and each food material category has a respective recipe label weight, for example, food material categories such as livestock meat and products thereof, stem and leaf vegetables and products thereof, melon and fruit vegetables and products thereof and the like have corresponding food material category weights, so that a food material preference label of a user for diet can be determined based on the food material category weights, and further, a diet preference portrait of the user can be clearly and accurately determined according to the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label of the user.
Further, when the recipe labels include, but are not limited to, the aforementioned taste label, cooking difficulty level label, and efficacy label, the corresponding diet preference profile of the user is also not limited to the aforementioned taste preference label, cooking skill label, and health attribute preference label.
In any of the above technical solutions, preferably, the step of determining the taste preference label of the user according to the recipe label weight corresponding to each taste label specifically includes: determining a target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as a taste preference label; the step of determining the cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty level label specifically comprises the following steps: determining a corresponding cooking skill label according to a target cooking difficulty grade label corresponding to the target recipe label with the largest weight; the step of determining the health attribute preference label of the user according to the recipe label weight corresponding to each efficacy label specifically comprises the following steps: determining a corresponding health attribute preference label according to a target efficacy label corresponding to the target recipe label weight with the weight larger than the average weight of the health attribute; the step of determining the food material preference tag of the user according to the food material category weight corresponding to each food material category specifically comprises the following steps: and determining the target food material category corresponding to the target food material category weight with the weight larger than the average weight of the food material categories as the food material preference label.
In the technical scheme, when the taste preference label of the user is determined according to each taste label and the corresponding weight of the recipe label, the weight of the recipe label corresponding to each taste label can be respectively compared with the preset average weight of the taste label, and the target taste label corresponding to the target weight of the recipe label which is larger than the average weight of the taste label is determined as the taste preference label which can accurately reflect the food and drink taste preference of the user; when the cooking skill label of the user is determined according to each cooking difficulty level label and the corresponding recipe label weight, the recipe label weight corresponding to each cooking difficulty level label can be compared pairwise, and the target cooking difficulty level label corresponding to the target recipe label weight with the largest weight is determined as the cooking skill label capable of accurately representing the real cooking skill level of the user; when the health attribute preference label of the user is determined according to each efficacy label and the corresponding recipe label weight, the recipe label weight corresponding to each efficacy label can be respectively compared with the preset health attribute average weight, and the target efficacy label corresponding to the target recipe label weight which is larger than the health attribute average weight is determined as the health attribute preference label which can accurately reflect the diet health attribute preference of the user; and when determining the food material preference tag of the user according to each food material category and the food material category weight corresponding to the food material category, comparing the food material category weight corresponding to each food material category with a preset food material category average weight, and determining the food material preference tag capable of accurately embodying the food material category preference of the user according to the target food material category weight which is greater than the food material category average weight. By the scheme, the label parameters for accurately describing the dietary preference of the user can be efficiently and accurately obtained.
In any of the above technical solutions, preferably, the step of determining the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe tag weight corresponding to each recipe tag further includes: acquiring a diet taboo label of a user; and taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
In the technical scheme, considering that different users have different constitutions and may not eat certain types of food under various objective conditions, in order to more accurately determine the diet preference portrait of the user, the diet taboo label of the user can be added into the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label determined according to the historical behavior data analysis of the user, so that a more complete diet preference portrait of the user is formed.
In any of the above technical solutions, preferably, the step of determining the popularity index of each food material and/or recipe included in the initial push list according to the diet preference profile includes: deleting the target food materials and/or recipes which are matched with the diet taboo labels and are contained in the initial push list to obtain a middle push list; setting a pushing index corresponding to each preference label in the rest preference labels except the diet taboo label in the diet preference portrait; and calculating the popularity index of each food material and/or recipe in the middle pushing list according to the weight corresponding to each preference label and the pushing index.
In the technical scheme, after the dietary preference portrait of the user is determined, the popularity index of each food material and/or recipe contained in the initial push list which is searched in the cooking material database and matched with the keyword input by the user can be determined according to the popularity index, so that the content in the target push list pushed to the user can truly reflect the interest degree of the user, the user can conveniently and efficiently screen, and the user experience is effectively improved.
Specifically, the diet taboo label in the diet preference portrait of the user has a vote rejection power, that is, the initial push list contains the target food material and/or recipe matched with the diet taboo label, and the target food material and/or recipe can be directly removed from the initial push list to obtain an intermediate push list; further, push indexes corresponding to each of the remaining preference labels, such as a taste preference label, a cooking skill label, a health attribute preference label, a food material category preference label and the like, in the diet preference portrait can be set, specifically, the push indexes can be set according to the attention or the watching intensity of the user on each preference label, and then the popularity index of each food material and/or recipe in the middle push list can be determined according to the push index and the weight corresponding to each of the remaining preference labels, and then the food materials and/or recipes can be sorted according to the interest program height of the user based on the popularity index of each food material and/or recipe to obtain a target recommendation list more meeting the user's expectation.
According to a second aspect of the present invention, there is provided an information pushing apparatus, comprising: the calculation module is used for calculating the diet preference portrait of the user according to the historical behavior data of the user; the search module is used for receiving keywords input by a user so as to search an initial push list matched with the keywords in the cooking material database; the determining module is used for determining the popularity index of each food material and/or recipe contained in the initial push list according to the diet preference portrait; the sorting module is used for sorting the food materials and/or the recipes in the initial push list according to the popularity indexes of the food materials and/or the recipes to obtain a target push list; and the pushing module is used for sending the target pushing list to the user.
In the technical scheme, in order to accurately push the really interested search content to the user when pushing the search content to the user, the dietary preference portrait of the user can be determined according to the past historical behavior data of the user, after an initial push list matched with a keyword is searched and determined in a cooking material number database according to the keyword input by the user, the popularity index of each food material and/or recipe contained in the initial push list is determined by combining the dietary preference portrait of the user, a target push list obtained by sequencing each food material and/or recipe according to the popularity index is further taken as a final push list to be sent to the user, so that the food material and/or recipe list according with the user interest is screened out based on the dietary preference portrait of the user and is pushed to the user after the list is sequenced according to the user interest program level, therefore, personalized intelligent prompting of the search keywords input by the user is achieved according to the diet preference pictures of different users, and clear and efficient information pushing is achieved, so that the user experience is improved.
In the above technical solution, preferably, the calculation module includes: the obtaining submodule is used for obtaining user behavior parameters contained in historical behavior data; the first determining submodule is used for determining the behavior weight and the behavior statistical frequency corresponding to each user behavior parameter so as to calculate the recipe weight of each recipe contained in the historical behavior data; the first calculation submodule is used for calculating the recipe label weight corresponding to each recipe label and the food material weight corresponding to each food material contained in the historical behavior data according to the recipe weight of each recipe; the second calculating submodule is used for calculating the food material category weight corresponding to each food material category contained in the historical behavior data according to the food material weight of each food material; and the second determining submodule is used for determining the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label.
In this technical solution, a recipe weight of each recipe included in the historical behavior data may be specifically calculated according to a behavior weight and a behavior statistics frequency corresponding to each user behavior parameter included in the historical behavior data of the user, and then a recipe label weight of each recipe label included in all recipe labels included in the historical behavior data and a food material weight of each food material included in all food materials included in the historical behavior data may be correspondingly calculated according to the recipe weights respectively corresponding to all recipes, and a food material category weight of each food material category included in all food material categories included in the historical behavior data may be correspondingly calculated according to the food material weights respectively corresponding to all food materials, that is, each recipe included in the historical behavior data of the user, each recipe label corresponding to the recipe, each contained food material, each food material, and a food material category included in the historical behavior data of the user, The food material categories corresponding to each food material have respective weights, and further, the diet preference portrait of the user can be accurately determined based on the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label, so that the contents to be pushed, which are screened according to the keywords input by the user, can be intelligently sequenced according to the interest of the user.
In any of the above technical solutions, preferably, the recipe label includes: taste label, cooking difficulty rating label, efficacy label; and the second determination submodule is specifically configured to: determining a taste preference label of the user according to the weight of the recipe label corresponding to each taste label; determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty grade label; determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label; and determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
In the technical scheme, the recipe labels corresponding to each recipe included in the historical behavior data of the user may be one or more of a taste label, a cooking difficulty level label, and an efficacy label, and of course, the recipe labels include, but are not limited to, the taste label, the cooking difficulty level label, and the efficacy label, and may be specifically adjusted by adding according to the specific needs of the user.
Further, specifically, each taste label has a respective recipe label weight, for example, the taste labels of sour, sweet, bitter, spicy, salty and the like have corresponding recipe label weights, and then the taste preference label of the user for diet can be screened out based on the corresponding recipe label weights; each cooking difficulty level label has a respective recipe label weight, for example, the easy, general and difficult cooking difficulty level labels respectively have corresponding recipe label weights, and then the cooking skill label corresponding to the user can be determined based on the weights; each efficacy label has respective recipe label weight, for example, efficacy labels for strengthening stomach, promoting digestion, enhancing immunity, maintaining beauty, keeping young, nourishing stomach and the like have corresponding recipe label weight, so that a health attribute preference label of the user to diet can be determined based on the efficacy labels; and each food material category has a respective recipe label weight, for example, food material categories such as livestock meat and products thereof, stem and leaf vegetables and products thereof, melon and fruit vegetables and products thereof and the like have corresponding food material category weights, so that a food material preference label of a user for diet can be determined based on the food material category weights, and further, a diet preference portrait of the user can be clearly and accurately determined according to the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label of the user.
Further, when the recipe labels include, but are not limited to, the aforementioned taste label, cooking difficulty level label, and efficacy label, the corresponding diet preference profile of the user is also not limited to the aforementioned taste preference label, cooking skill label, and health attribute preference label.
In any of the above technical solutions, preferably, the second determining submodule is specifically configured to: determining a target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as a taste preference label; determining a corresponding cooking skill label according to a target cooking difficulty grade label corresponding to the target recipe label with the largest weight; determining a corresponding health attribute preference label according to a target efficacy label corresponding to the target recipe label weight with the weight larger than the average weight of the health attribute; and determining the target food material category corresponding to the target recipe label weight with the weight larger than the average weight of the food material category as a food material preference label.
In the technical scheme, when the taste preference label of the user is determined according to each taste label and the corresponding weight of the recipe label, the weight of the recipe label corresponding to each taste label can be respectively compared with the preset average weight of the taste label, and the target taste label corresponding to the target weight of the recipe label which is larger than the average weight of the taste label is determined as the taste preference label which can accurately reflect the food and drink taste preference of the user; when the cooking skill label of the user is determined according to each cooking difficulty level label and the corresponding recipe label weight, the recipe label weight corresponding to each cooking difficulty level label can be compared pairwise, and the target cooking difficulty level label corresponding to the target recipe label weight with the largest weight is determined as the cooking skill label capable of accurately representing the real cooking skill level of the user; when the health attribute preference label of the user is determined according to each efficacy label and the corresponding recipe label weight, the recipe label weight corresponding to each efficacy label can be respectively compared with the preset health attribute average weight, and the target efficacy label corresponding to the target recipe label weight which is larger than the health attribute average weight is determined as the health attribute preference label which can accurately reflect the diet health attribute preference of the user; and when determining the food material preference tag of the user according to each food material category and the food material category weight corresponding to the food material category, comparing the food material category weight corresponding to each food material category with a preset food material category average weight, and determining the food material preference tag capable of accurately embodying the food material category preference of the user according to the target food material category weight which is greater than the food material category average weight. By the scheme, the label parameters for accurately describing the dietary preference of the user can be efficiently and accurately obtained.
In any one of the above technical solutions, preferably, the information pushing apparatus further includes: the acquisition module is used for acquiring the diet taboo label of the user when the second determination sub-module determines the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label; and the calculation module is specifically configured to: and taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
In the technical scheme, considering that different users have different constitutions and may not eat certain types of food under various objective conditions, in order to more accurately determine the diet preference portrait of the user, the diet taboo label of the user can be added into the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label determined according to the historical behavior data analysis of the user, so that a more complete diet preference portrait of the user is formed.
In any one of the above technical solutions, preferably, the determining module includes: the deletion submodule is used for deleting the target food materials and/or recipes which are contained in the initial push list and matched with the diet taboo labels to obtain an intermediate push list; the setting submodule is used for setting a pushing index corresponding to each preference label in the rest preference labels except the diet taboo label in the diet preference portrait; and the third calculation submodule is used for calculating the popularity index of each food material and/or recipe in the middle pushing list according to the weight corresponding to each preference label and the pushing index.
In the technical scheme, after the dietary preference portrait of the user is determined, the popularity index of each food material and/or recipe contained in the initial push list which is searched in the cooking material database and matched with the keyword input by the user can be determined according to the popularity index, so that the content in the target push list pushed to the user can truly reflect the interest degree of the user, the user can conveniently and efficiently screen, and the user experience is effectively improved.
Specifically, the diet taboo label in the diet preference portrait of the user has a vote rejection power, that is, the initial push list contains the target food material and/or recipe matched with the diet taboo label, and the target food material and/or recipe can be directly removed from the initial push list to obtain an intermediate push list; further, push indexes corresponding to each of the remaining preference labels, such as a taste preference label, a cooking skill label, a health attribute preference label, a food material category preference label and the like, in the diet preference portrait can be set, specifically, the push indexes can be set according to the attention or the watching intensity of the user on each preference label, and then the popularity index of each food material and/or recipe in the middle push list can be determined according to the push index and the weight corresponding to each of the remaining preference labels, and then the food materials and/or recipes can be sorted according to the interest program height of the user based on the popularity index of each food material and/or recipe to obtain a target recommendation list more meeting the user's expectation.
According to a third aspect of the present invention, there is provided a computer device comprising: a processor; a memory for storing executable instructions of the processor, wherein the processor is configured to implement the steps of the information pushing method according to any one of the above-mentioned solutions of the first aspect when the processor is configured to execute the executable instructions stored in the memory.
According to a fourth aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the information push method according to any one of the above-mentioned solutions of the first aspect.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 shows a flow chart of an information pushing method according to a first embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for calculating a diet preference profile of a user according to historical behavior data of the user according to a first embodiment of the present invention;
fig. 3 is a flowchart illustrating a method for determining a diet preference portrait of a user according to a food material category weight corresponding to each food material category and a recipe tag weight corresponding to each recipe tag according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for determining a popularity index of each food material and/or recipe contained in an initial push list according to a diet preference profile according to an embodiment of the present invention;
fig. 5 shows a flow chart of an information pushing method according to a second embodiment of the present invention;
FIG. 6 is a flowchart illustrating a method for calculating a diet preference profile of a user based on historical behavior data of the user according to a second embodiment of the present invention;
FIG. 7 is a diagram illustrating a push display effect of an embodiment of the present invention;
FIG. 8 shows a schematic block diagram of an information recommendation apparatus of an embodiment of the present invention;
FIG. 9 shows a schematic block diagram of the computation module shown in FIG. 8;
FIG. 10 shows a schematic block diagram of the determination module shown in FIG. 8;
FIG. 11 shows a schematic block diagram of a computer apparatus of an embodiment of the invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
The information push method according to the first embodiment of the present invention is specifically described below with reference to fig. 1 to 4.
As shown in fig. 1, the information push method according to the first embodiment of the present invention specifically includes the following steps:
And 104, receiving keywords input by a user to search an initial push list matched with the keywords in the cooking material database.
And 108, determining the popularity index of each food material and/or recipe contained in the initial push list according to the diet preference portrait.
And 110, sequencing the food materials and/or the recipes in the initial push list according to the popularity indexes of the food materials and/or the recipes to obtain a target push list.
And step 112, sending the target push list to the user.
In the embodiment, in order to accurately push the search content really interested by the user when pushing the search content to the user, the dietary preference portrait of the user can be determined according to the past historical behavior data of the user, after an initial push list matched with the keyword is searched and determined in a cooking material number database according to the keyword input by the user, the popularity index of each food material and/or recipe contained in the initial push list is determined by combining the dietary preference portrait of the user, and then a target push list obtained by sequencing each food material and/or recipe according to the popularity index is sent to the user as a final push list, so that the food material and/or recipe list conforming to the interest of the user is screened out based on the dietary preference portrait of the user, and the list is pushed to the user after sequencing according to the user interest program level, so that the search keyword input by the user is personalized according to the dietary preference portrait of different users The intelligent prompt realizes the information push with clear and efficient purpose so as to improve the user experience.
Further, for the step 102 in the foregoing embodiment, the flow steps shown in fig. 2 may be implemented, and specifically include:
step S202, user behavior parameters contained in the historical behavior data are acquired.
Step S204, determining the behavior weight and the behavior statistics frequency corresponding to each user behavior parameter so as to calculate the recipe weight of each recipe contained in the historical behavior data.
Step S206, calculating the recipe label weight corresponding to each recipe label and the food material weight corresponding to each food material contained in the historical behavior data according to the recipe weight of each recipe.
Step S208, calculating the weight of the food material category corresponding to each food material category contained in the historical behavior data according to the weight of the food material of each food material.
Step S210, determining a diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label.
In this embodiment, a recipe weight of each recipe included in the historical behavior data may be specifically calculated according to a behavior weight and a behavior statistics frequency corresponding to each user behavior parameter included in the historical behavior data of the user, and then a recipe label weight of each recipe label in all recipe labels included in the historical behavior data and a food material weight of each food material in all food materials included in the historical behavior data may be correspondingly calculated according to the recipe weights respectively corresponding to all recipes, and a food material category weight of each food material category in all food material categories included in the historical behavior data may be correspondingly calculated according to the food material weights respectively corresponding to all food materials, that is, each recipe included in the historical behavior data of the user, each recipe label corresponding to the recipe, and each food material category included in the historical behavior data of the user, The food material categories corresponding to each food material have respective weights, and further, the diet preference portrait of the user can be accurately determined based on the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label, so that the contents to be pushed, which are screened according to the keywords input by the user, can be intelligently sequenced according to the interest of the user.
Further, in the above embodiment, the recipe label includes: taste label, cooking difficulty rating label, efficacy label.
In this embodiment, the recipe labels corresponding to each recipe included in the historical behavior data of the user may be one or more of a taste label, a cooking difficulty level label, and an efficacy label, and of course, the recipe labels include, but are not limited to, the taste label, the cooking difficulty level label, and the efficacy label, and may be specifically adjusted by adding according to the specific needs of the user.
Further, step S210 in the above embodiment may be implemented as the flow step shown in fig. 3, and specifically includes:
step S302, determining taste preference labels of the user according to the recipe label weight corresponding to each taste label.
It can be understood that, each taste label has a respective recipe label weight, and for example, the taste labels of sour, sweet, bitter, spicy, salty, and the like have corresponding recipe label weights, so that the taste preference label of the user for diet can be screened out based on the corresponding recipe label weights.
Further, the step S302 may be specifically executed as: and determining the target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as the taste preference label.
It can be understood that, when determining the taste preference tag of the user according to each taste tag and the corresponding recipe tag weight, the recipe tag weight corresponding to each taste tag may be compared with the preset taste tag average weight, and the target taste tag corresponding to the target recipe tag weight greater than the taste tag average weight is determined as the taste preference tag capable of accurately embodying the food taste preference of the user.
Step S304, determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty level label.
It can be understood that each cooking difficulty level label has a respective recipe label weight, for example, each cooking difficulty level label such as easy, general and difficult has a corresponding recipe label weight, and a cooking skill label corresponding to the user can be determined based on the weights, for example, the cooking skill labels corresponding to easy, general and difficult can be respectively poor, general and strong, that is, if the user only wants the cooking difficulty level label to be the recipe easily corresponding to indicate that the user is not good at cooking skill, and if the user wants the cooking difficulty level label to be the recipe hardly corresponding to indicate that the user is strong at cooking skill.
Further, the step S304 may be specifically executed as: and determining a corresponding cooking skill label according to the target cooking difficulty grade label corresponding to the target recipe label with the maximum weight.
It can be understood that, when the cooking skill tag of the user is determined according to each cooking difficulty level tag and the recipe tag weight corresponding to the cooking difficulty level tag, the recipe tag weights corresponding to each cooking difficulty level tag may be compared pairwise, and the target cooking difficulty level tag corresponding to the target recipe tag weight with the largest weight is determined as the cooking skill tag capable of accurately representing the real cooking skill level of the user.
And S306, determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label.
It can be understood that, each specific efficacy label has a respective recipe label weight, and for example, efficacy labels for strengthening stomach, promoting digestion, enhancing immunity, maintaining beauty, keeping young, nourishing stomach and the like have corresponding recipe label weights, and a health attribute preference label of the user for diet can be determined based on the corresponding recipe label weights.
Further, the step S306 may be specifically executed as: and determining a corresponding health attribute preference label according to a target efficacy label corresponding to the target recipe label weight with the weight larger than the average weight of the health attribute.
It can be understood that, when the health attribute preference label of the user is determined according to each efficacy label and the recipe label weight corresponding to the efficacy label, the recipe label weight corresponding to each efficacy label can be respectively compared with the preset health attribute average weight, and the target efficacy label corresponding to the target recipe label weight larger than the health attribute average weight is determined as the health attribute preference label capable of accurately embodying the diet health attribute preference which the user pays more attention to.
Step S308, determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
It can be understood that each food material category has a respective recipe label weight, for example, food material categories such as livestock meat and products thereof, stem and leaf vegetables and products thereof, and melon and fruit vegetables and products thereof respectively have corresponding food material category weights, and then a food material preference label of a user for diet can be determined based on the food material category weights.
Further, this step S308 may be specifically executed as: and determining the target food material category corresponding to the target food material category weight with the weight larger than the average weight of the food material categories as the food material preference label.
It can be understood that, when determining the food material preference tag of the user according to each food material category and the food material category weight corresponding to the food material category, the food material category weight corresponding to each food material category can be respectively compared with the preset food material category average weight, and the target food material category corresponding to the target food material category weight greater than the food material category average weight is determined to be the food material preference tag capable of accurately embodying the food material category preference of the user
In summary, in the embodiments of the present invention, the tag parameter for accurately describing the dietary preference of the user can be efficiently and accurately obtained, and further, the dietary preference portrait of the user can be clearly and accurately determined according to the taste preference tag, the cooking skill tag, the health attribute preference tag, and the food material preference tag of the user.
Further, when the recipe labels include, but are not limited to, the aforementioned taste label, cooking difficulty level label, and efficacy label, the corresponding diet preference profile of the user is also not limited to the aforementioned taste preference label, cooking skill label, and health attribute preference label.
Further, in the above embodiment, when the step S210 is executed, the following steps may also be executed: acquiring a diet taboo label of a user; and taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
In this embodiment, in consideration of different constitutions of different users, some types of food may not be eaten due to various objective conditions, so in order to determine the diet preference profile of the user more accurately, the diet taboo tag of the user may be added to the taste preference tag, the culinary art tag, the health attribute preference tag and the food material preference tag determined according to the historical behavior data analysis of the user, thereby forming a more complete diet preference profile of the user.
Further, step 108 in the foregoing embodiment may be specifically implemented as the flow step shown in fig. 4, and specifically includes:
in step S402, the target food materials and/or recipes matching the diet taboo tag included in the initial push list are deleted to obtain an intermediate push list.
Step S404, setting pushing indexes corresponding to each kind of the rest preference labels except the diet taboo label in the diet preference portrait.
Step S406, calculating the popularity index of each food material and/or recipe in the middle pushing list according to the weight corresponding to each preference label and the pushing index.
In the embodiment, after the diet preference portrait of the user is determined, the popularity index of each food material and/or recipe contained in the initial push list matched with the keyword input by the user and searched in the cooking material database can be determined according to the popularity index, so that the content in the target push list pushed to the user can truly reflect the interest level of the user, the user can conveniently and efficiently screen, and the user experience is effectively improved.
Specifically, the diet taboo label in the diet preference portrait of the user has a vote rejection power, that is, the initial push list contains the target food material and/or recipe matched with the diet taboo label, and the target food material and/or recipe can be directly removed from the initial push list to obtain an intermediate push list; further, push indexes corresponding to each of the remaining preference labels, such as a taste preference label, a cooking skill label, a health attribute preference label, a food material category preference label and the like, in the diet preference portrait can be set, specifically, the push indexes can be set according to the attention or the watching intensity of the user on each preference label, and then the popularity index of each food material and/or recipe in the middle push list can be determined according to the push index and the weight corresponding to each of the remaining preference labels, and then the food materials and/or recipes can be sorted according to the interest program height of the user based on the popularity index of each food material and/or recipe to obtain a target recommendation list more meeting the user's expectation.
The information push method according to the second embodiment of the present invention is specifically described below with reference to fig. 5 to 7.
As shown in fig. 5, the information push method according to the second embodiment of the present invention specifically includes the following steps:
At step 504, a representation of the user's dietary preferences is calculated based on the behavioral data.
Further, the step may be specifically executed as the flow step described in fig. 6, and specifically includes:
step S602, a user behavior parameter in the behavior data is obtained.
Step S604, calculating the recipe weight of each recipe included in the behavior data according to the weight and the statistical frequency corresponding to the user behavior parameter.
Specifically, the weight (i.e., the behavior weight) of each user behavior parameter may be determined by using an Analytic Hierarchy Process (AHP), and the number of times that each user behavior parameter occurs within a specified time period (i.e., the behavior statistics number) is counted, for example, the user behavior parameter of the recipe a and the corresponding weight and number are shown in table 1 below:
TABLE 1
User behavior parameters | Browsing | Searching | Like points | Comments | Collection method | Upload to |
Weight (AHP method) | 2 | 1 | 3 | 4 | 4 | 5 |
Times (statistics) | 10 | 5 | 1 | 2 | 1 | 0 |
Then, from the data shown in the above table, the recipe weight of the recipe a can be determined to be 2 × 10+1 × 5+3 × 1+4 × 2+4 × 1+5 × 0 or 40.
Step S606, the recipe name, the recipe weight, the recipe label, and the recipe containing food material are correlated.
For example, if the behavior data of the user includes three recipes and the weights of the recipes are determined, the correspondence relationship may be specifically shown in the following table 2:
TABLE 2
As shown in table 2 above, the recipe labels include taste labels, cooking difficulty labels and efficacy labels, the recipe weight of the recipe of the skewered spicy chicken is 39, the food materials include chicken, chili and onion, and the recipe labels are spicy, general and immunity-enhancing respectively; the weight of the recipe of the fried eggplant slice is 50, the food material comprises eggplants, and each recipe label corresponds to salty, easy, stomach-invigorating and digestion-promoting respectively; the recipe weight of the Mandarin fish recipe is 20, the food materials comprise Mandarin fish, pine nuts and green beans, and each recipe label corresponds to sweet, difficult and none respectively.
In step S608, the weight of each food material and each food material category is calculated.
For example, according to the data in table 2, the weight of each food material can be determined according to the recipe weight, and the weight of the food material category to which each food material belongs is shown in table 3 and table 4 below:
TABLE 3
Food material | Weight of | Categories |
Chicken meat | 39 | Poultry meat and its products |
Chili pepper | 39 | Stem and leaf vegetable and its product |
Onion (onion) | 39 | Root vegetable and its products |
Eggplant | 50 | Melon and fruit vegetables and products thereof |
Mandarin fish | 20 | Aquatic products and products thereof |
Pine nut | 20 | Nuts and seeds |
Green bean | 20 | Bean vegetable and its product |
As shown in table 3 above, the food materials included in the three recipes, the food material weights corresponding to the food materials, and the food material categories to which the food materials belong are shown.
TABLE 4
Categories | Weight of |
Melon and fruit vegetables and products thereof | 50 |
Poultry meat and its products | 39 |
Stem and leaf vegetable and its product | 39 |
Root vegetable and its products | 39 |
Bean vegetable and its product | 20 |
Aquatic products and products thereof | 20 |
Nuts and seeds | 20 |
As shown in table 4 above, the food material category weights of the food material categories to which the food materials included in the three recipes belong are shown.
Step S610, calculating a corresponding user dietary preference tag.
TABLE 5
As shown in table 5 above, if the taste labels generally include seven categories, i.e., sour, sweet, bitter, spicy, salty, fresh and light, the average weight of the taste labels is 100% ÷ 7% ═ 14.3%, and further, the sweet, spicy and salty taste label weights of the three taste labels can be determined according to the data in table 2, and further, when determining the taste preference label of the user, by comparing the sweet, spicy and salty taste label weights of 18.35%, 35.78% and 45.87%, respectively, with 14.3%, the taste label weight corresponding to the taste label weight greater than the average weight is determined as the taste preference label of the user, in this specific embodiment, the taste of the user is preferred to sweet, spicy and salty.
TABLE 6
As shown in table 6 above, the cooking difficulty labels of the recipes generally include three types of easy, general and difficult types, and further the corresponding cooking difficulty labels may be respectively poor, general and strong, so that the weights of the three cooking difficulty labels corresponding to the three recipes can be respectively determined according to the data in table 2, that is, the weights of the recipe labels corresponding to the easy, general and difficult recipes are respectively 45.87%, 35.78% and 18.35%, and further the cooking difficulty label with the largest weight of the recipe label can be determined as the cooking skill label of the user, which indicates that the user is good at the recipe with low cooking difficulty and the cooking skill is not good, that is, not good at the cooking skill.
TABLE 7
As shown in table 7 above, the efficacy labels generally include 28 types, such as enhancing immunity, strengthening stomach and promoting digestion, and the average weight of the efficacy labels is 100% ÷ 28% ~ 3.57%, and further, the weight of the recipe label corresponding to the two efficacy labels of the three recipes, such as enhancing immunity, strengthening stomach and promoting digestion, can be determined according to the data in table 2, and further when determining the efficacy preference label of the user, the weight of the recipe label corresponding to enhancing immunity, strengthening stomach and promoting digestion, 35.78% and 45.87% are compared with 3.57%, respectively, and then the efficacy label corresponding to the weight of the recipe label greater than the average weight is determined as the efficacy preference label of the user.
TABLE 8
As shown in table 8 above, when the food material categories include 12 types such as meat and meat products, nuts, and seeds, the average weight of the food material categories is 100% ÷ 12 ÷ 8.33%, and further, according to the data in table 4, the recipe label weights corresponding to the 7 food material categories corresponding to the three recipes can be determined, and further when the food material category preference of the user is determined, so as to compare the weight of the recipe label corresponding to each of the 7 food material categories with 8.33%, determining the food material category corresponding to the food material category weight larger than the average weight as the food material preference label of the user, in this embodiment, the preferences of the user for the food material category are poultry and products thereof, nuts and seeds, stem and leaf vegetables and products thereof, root vegetables and products thereof, melon and fruit vegetables and products thereof, bean vegetables and products thereof, and aquatic products and products thereof.
Step S612, generating a user diet preference portrait.
In this step, contraindication tags in the aspect of user diet, such as seafood allergy, can be comprehensively considered in addition to the above taste preference tag, culinary art tag, efficacy preference tag and food material preference tag, and the diet preference profile of the user in this specific embodiment can be shown in table 9:
TABLE 9
In this manner, a representation of the user's dietary preferences, including the tags and their corresponding weights, is determined based on the user's historical behavioral data.
For example, taking the input keyword "beef" as an example, the specifically obtained food material and/or recipe list _1 may be as shown in the following table 10:
watch 10
The two steps of step 502, step 504 and step 506, and step 508 may be executed simultaneously, or step 502 and step 504 may be executed first, and then step 506 and step 508 may be executed, or step 506 and step 508 may be executed first, and then step 502 and step 504 may be executed.
TABLE 11
As shown in the above table 11, the diet taboo label "seafood allergy" of the user has a negative power, the push indexes (i.e., "weight" in the table) of other preference labels are all 1, and different values can be set according to the preference of the user, so that the popularity index of each recipe in the list _1 obtained according to the weight corresponding to each preference label and the push index is shown in the following table 12:
TABLE 12
Watch 13
In summary, according to the embodiment, personalized intelligent prompting is performed on the currently input search keyword of the user according to personalized user diet preference pictures of different users, specifically, the user diet preference picture is calculated according to previous behavior data of the user, the currently input keyword of the user is screened in the word bank according to the current input keyword of the user, then the screened keyword list is ranked according to the screening result and the user diet preference picture, and keyword search prompting is performed according to the ranking result, so that the user experience degree is improved.
Further, the efficacy labels, the efficacy preference labels of the user (i.e., the health attribute preference labels), the food material categories, the food material preference labels, and other labels mentioned in the above embodiment are only examples, and the labels are not limited thereto, and more labels may be defined according to actual requirements.
The information pushing apparatus according to the embodiment of the present invention will be specifically described below with reference to fig. 8 to 10.
As shown in fig. 8, the information pushing apparatus 80 according to the embodiment of the present invention includes: a calculation module 802, a search module 804, a determination module 806, a ranking module 808, and a push module 810.
Wherein, the calculating module 802 is configured to calculate a diet preference portrait of the user according to the historical behavior data of the user; the search module 804 is used for receiving keywords input by a user so as to search an initial push list matched with the keywords in the cooking material database; the determining module 806 is configured to determine a popularity index of each food material and/or recipe contained in the initial pushed list according to the diet preference profile; the sorting module 808 is configured to sort the food materials and/or the recipes in the initial push list according to the popularity index of each food material and/or recipe, so as to obtain a target push list; the push module 810 is configured to send the target push list to the user.
In the embodiment, in order to accurately push the search content really interested by the user when pushing the search content to the user, the dietary preference portrait of the user can be determined according to the past historical behavior data of the user, after an initial push list matched with the keyword is searched and determined in a cooking material number database according to the keyword input by the user, the popularity index of each food material and/or recipe contained in the initial push list is determined by combining the dietary preference portrait of the user, and then a target push list obtained by sequencing each food material and/or recipe according to the popularity index is sent to the user as a final push list, so that the food material and/or recipe list conforming to the interest of the user is screened out based on the dietary preference portrait of the user, and the list is pushed to the user after sequencing according to the user interest program level, so that the search keyword input by the user is personalized according to the dietary preference portrait of different users The intelligent prompt realizes the information push with clear and efficient purpose so as to improve the user experience.
Further, the calculating module 802 in the above embodiment includes: an acquisition sub-module 8020, a first determination sub-module 8022, a first computation sub-module 8024, a second computation sub-module 8026, and a second determination sub-module 8028, as shown in fig. 9.
The obtaining sub-module 8020 is configured to obtain a user behavior parameter included in the historical behavior data; the first determining submodule 8022 is configured to determine a behavior weight and a behavior statistics number corresponding to each user behavior parameter, so as to calculate a recipe weight of each recipe included in the historical behavior data; the first calculating submodule 8024 is configured to calculate, according to the recipe weight of each recipe, a recipe label weight corresponding to each recipe label and a food material weight corresponding to each food material included in the historical behavior data; the second calculating submodule 8026 is configured to calculate, according to the weight of each food material, a weight of a food material category corresponding to each food material category included in the historical behavior data; the second determining sub-module 8028 is configured to determine the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe tag weight corresponding to each recipe tag.
In this embodiment, a recipe weight of each recipe included in the historical behavior data may be specifically calculated according to a behavior weight and a behavior statistics frequency corresponding to each user behavior parameter included in the historical behavior data of the user, and then a recipe label weight of each recipe label in all recipe labels included in the historical behavior data and a food material weight of each food material in all food materials included in the historical behavior data may be correspondingly calculated according to the recipe weights respectively corresponding to all recipes, and a food material category weight of each food material category in all food material categories included in the historical behavior data may be correspondingly calculated according to the food material weights respectively corresponding to all food materials, that is, each recipe included in the historical behavior data of the user, each recipe label corresponding to the recipe, and each food material category included in the historical behavior data of the user, The food material categories corresponding to each food material have respective weights, and further, the diet preference portrait of the user can be accurately determined based on the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label, so that the contents to be pushed, which are screened according to the keywords input by the user, can be intelligently sequenced according to the interest of the user.
Further, in the above embodiment, the recipe label includes: taste label, cooking difficulty rating label, efficacy label.
In this embodiment, the recipe labels corresponding to each recipe included in the historical behavior data of the user may be one or more of a taste label, a cooking difficulty level label, and an efficacy label, and of course, the recipe labels include, but are not limited to, the taste label, the cooking difficulty level label, and the efficacy label, and may be specifically adjusted by adding according to the specific needs of the user.
Further, in the above embodiment, the second determining sub-module 8028 is specifically configured to: determining a taste preference label of the user according to the weight of the recipe label corresponding to each taste label; determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty grade label; determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label; and determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
In this embodiment, specifically, each taste label has its own recipe label weight, for example, the taste labels of sour, sweet, bitter, spicy, salty, etc. have their corresponding recipe label weights, so that the taste preference label of the user for diet can be screened out based on the corresponding recipe label weights; each cooking difficulty level label has a respective recipe label weight, for example, the easy, general and difficult cooking difficulty level labels have corresponding recipe label weights, the cooking skill label corresponding to the user can be determined based on the weights, for example, the cooking skill labels corresponding to the easy, general and difficult cooking skill labels can be respectively poor, general and strong, that is, if the user only can use the cooking difficulty level label as the recipe easy to correspond to indicate that the user is poor in cooking skill, and if the user can use the cooking difficulty level label as the difficult to correspond to indicate that the user is strong in cooking skill; each efficacy label has respective recipe label weight, for example, efficacy labels for strengthening stomach, promoting digestion, enhancing immunity, maintaining beauty, keeping young, nourishing stomach and the like have corresponding recipe label weight, so that a health attribute preference label of the user to diet can be determined based on the efficacy labels; and each food material category has a respective recipe label weight, for example, food material categories such as livestock meat and products thereof, stem and leaf vegetables and products thereof, melon and fruit vegetables and products thereof and the like have corresponding food material category weights, so that a food material preference label of a user for diet can be determined based on the food material category weights, and further, a diet preference portrait of the user can be clearly and accurately determined according to the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label of the user.
Further, when the recipe labels include, but are not limited to, the aforementioned taste label, cooking difficulty level label, and efficacy label, the corresponding diet preference profile of the user is also not limited to the aforementioned taste preference label, cooking skill label, and health attribute preference label.
Further, in the above embodiment, the second determining sub-module 8028 is specifically configured to: determining a target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as a taste preference label; determining a corresponding cooking skill label according to a target cooking difficulty grade label corresponding to the target recipe label with the largest weight; determining a corresponding health attribute preference label according to a target efficacy label corresponding to the target recipe label weight with the weight larger than the average weight of the health attribute; and determining the target food material category corresponding to the target recipe label weight with the weight larger than the average weight of the food material category as a food material preference label.
In this embodiment, when determining the taste preference tag of the user according to each taste tag and the corresponding weight of the recipe tag, the weight of the recipe tag corresponding to each taste tag may be compared with the preset average weight of the taste tag, and the target taste tag corresponding to the target weight of the recipe tag greater than the average weight of the taste tag is determined as the taste preference tag capable of accurately embodying the food taste preference of the user; when the cooking skill label of the user is determined according to each cooking difficulty level label and the corresponding recipe label weight, the recipe label weight corresponding to each cooking difficulty level label can be compared pairwise, and the target cooking difficulty level label corresponding to the target recipe label weight with the largest weight is determined as the cooking skill label capable of accurately representing the real cooking skill level of the user; when the health attribute preference label of the user is determined according to each efficacy label and the corresponding recipe label weight, the recipe label weight corresponding to each efficacy label can be respectively compared with the preset health attribute average weight, and the target efficacy label corresponding to the target recipe label weight which is larger than the health attribute average weight is determined as the health attribute preference label which can accurately reflect the diet health attribute preference of the user; and when determining the food material preference tag of the user according to each food material category and the food material category weight corresponding to the food material category, comparing the food material category weight corresponding to each food material category with a preset food material category average weight, and determining the food material preference tag capable of accurately embodying the food material category preference of the user according to the target food material category weight which is greater than the food material category average weight. By the scheme, the label parameters for accurately describing the dietary preference of the user can be efficiently and accurately obtained.
Further, in the above embodiment, as shown in fig. 8, the information pushing device 80 further includes: an obtaining module 812, configured to obtain a diet taboo label of the user when the second determining sub-module 8028 determines the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label; and the calculation module 802 is specifically configured to: and taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
In this embodiment, in consideration of different constitutions of different users, some types of food may not be eaten due to various objective conditions, so in order to determine the diet preference profile of the user more accurately, the diet taboo tag of the user may be added to the taste preference tag, the culinary art tag, the health attribute preference tag and the food material preference tag determined according to the historical behavior data analysis of the user, thereby forming a more complete diet preference profile of the user.
Further, the determining module 806 in the above embodiment includes: delete sub-module 8062, set sub-module 8064, and third compute sub-module 8066, as shown in fig. 10.
The deletion submodule 8062 is configured to delete a target food material and/or a recipe, which are contained in the initial push list and are matched with the diet taboo tag, so as to obtain an intermediate push list; the setting submodule 8064 is used for setting a pushing index corresponding to each of the remaining preference labels except the diet taboo label in the diet preference portrait; the third calculating sub-module 8066 is configured to calculate a popularity index of each food material and/or recipe in the intermediate push list according to the weight corresponding to each preference tag and the push index.
In the embodiment, after the diet preference portrait of the user is determined, the popularity index of each food material and/or recipe contained in the initial push list matched with the keyword input by the user and searched in the cooking material database can be determined according to the popularity index, so that the content in the target push list pushed to the user can truly reflect the interest level of the user, the user can conveniently and efficiently screen, and the user experience is effectively improved.
Specifically, the diet taboo label in the diet preference portrait of the user has a vote rejection power, that is, the initial push list contains the target food material and/or recipe matched with the diet taboo label, and the target food material and/or recipe can be directly removed from the initial push list to obtain an intermediate push list; further, push indexes corresponding to each of the remaining preference labels, such as a taste preference label, a cooking skill label, a health attribute preference label, a food material category preference label and the like, in the diet preference portrait can be set, specifically, the push indexes can be set according to the attention or the watching intensity of the user on each preference label, and then the popularity index of each food material and/or recipe in the middle push list can be determined according to the push index and the weight corresponding to each of the remaining preference labels, and then the food materials and/or recipes can be sorted according to the interest program height of the user based on the popularity index of each food material and/or recipe to obtain a target recommendation list more meeting the user's expectation.
FIG. 11 shows a schematic block diagram of a computer apparatus of an embodiment of the invention.
As shown in fig. 11, the computer device 110 according to the embodiment of the present invention includes a processor 1102 and a memory 1104, wherein the memory 1104 stores a computer program that can run on the processor 1102, wherein the memory 1104 and the processor 1102 can be connected by a bus, and the processor 1102 is configured to implement the steps of the information pushing method as described in the above embodiment when executing the computer program stored in the memory 1104.
The steps in the information pushing method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs.
The information pushing apparatus and the units in the computer device 110 according to the embodiments of the present invention may be merged, divided, and deleted according to actual needs.
According to an embodiment of the present invention, a computer-readable storage medium is proposed, on which a computer program is stored, which, when being executed by a processor, implements the steps of the information push method as described in the above embodiments.
Further, it will be understood that any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and that the scope of the preferred embodiments of the present invention includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc.; and the aforementioned computer device 110 may be a server.
The technical scheme of the invention is described in detail in combination with the drawings, and personalized intelligent prompt is carried out on the search keywords input by the user according to the diet preference pictures of different users, so that clear and efficient information push can be realized, and the user experience is improved.
In the embodiments of the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance, and specific meanings of the above terms in the embodiments of the present invention may be understood according to specific situations by those of ordinary skill in the art.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art 5. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. An information pushing method, comprising:
calculating a diet preference portrait of a user according to historical behavior data of the user;
receiving keywords input by the user to search an initial push list matched with the keywords in a cooking material database;
determining a popularity index of each food material and/or recipe contained in the initial push list according to the diet preference portrait;
sorting the food materials and/or recipes in the initial push list according to the popularity index of the food materials and/or recipes to obtain a target push list;
sending the target push list to the user;
the step of calculating a representation of the user's dietary preferences based on historical behavioral data of the user comprises:
acquiring user behavior parameters contained in the historical behavior data;
determining behavior weight and behavior statistics times corresponding to each user behavior parameter so as to calculate the recipe weight of each recipe contained in the historical behavior data;
calculating the recipe label weight corresponding to each recipe label and the food material weight corresponding to each food material contained in the historical behavior data according to the recipe weight of each recipe;
calculating the food material category weight corresponding to each food material category contained in the historical behavior data according to the food material weight of each food material;
and determining the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label.
2. The information pushing method according to claim 1, wherein the recipe label comprises: taste label, cooking difficulty rating label, efficacy label; and
the step of determining the diet preference portrait of the user according to the food material category weight of each food material category and the tag weight of each recipe tag comprises the following steps:
determining a taste preference label of the user according to the weight of the recipe label corresponding to each taste label;
determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty grade label;
determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label;
and determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
3. The information pushing method according to claim 2,
the step of determining the taste preference label of the user according to the recipe label weight corresponding to each taste label specifically comprises: determining a target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as the taste preference label;
the step of determining the cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty level label specifically comprises the following steps: determining the corresponding cooking skill label according to the target cooking difficulty grade label corresponding to the target recipe label with the maximum weight;
the step of determining the health attribute preference label of the user according to the recipe label weight corresponding to each efficacy label specifically includes: determining a corresponding health attribute preference label according to a target efficacy label corresponding to a target recipe label weight with the weight larger than the average weight of the health attribute;
the step of determining the food material preference tag of the user according to the food material category weight corresponding to each food material category specifically comprises: and determining the target food material category corresponding to the target food material category weight with the weight larger than the average weight of the food material categories as the food material preference label.
4. The information pushing method according to claim 2 or 3, wherein the step of determining the diet preference profile of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label further comprises:
acquiring a diet taboo label of a user;
taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
5. The information push method according to claim 4, wherein the step of determining a popularity index of each food material and/or recipe contained in the initial push list from the diet preference profile comprises:
deleting the target food materials and/or recipes which are matched with the diet taboo labels and are contained in the initial push list to obtain an intermediate push list;
setting a pushing index corresponding to each of the rest preference labels except the diet taboo label in the diet preference portrait;
and calculating the popularity index of each food material and/or recipe in the intermediate pushing list according to the weight corresponding to each preference label and the pushing index.
6. An information pushing apparatus, comprising:
the calculation module is used for calculating the diet preference portrait of the user according to historical behavior data of the user;
the searching module is used for receiving the keywords input by the user so as to search an initial pushing list matched with the keywords in a cooking material database;
a determining module, configured to determine a popularity index of each food material and/or recipe included in the initial push list according to the diet preference profile;
the sorting module is used for sorting the food materials and/or the recipes in the initial push list according to the popularity indexes of the food materials and/or the recipes to obtain a target push list;
the pushing module is used for sending the target pushing list to the user;
the calculation module comprises:
the obtaining submodule is used for obtaining user behavior parameters contained in the historical behavior data;
the first determining submodule is used for determining the behavior weight and the behavior statistical frequency corresponding to each user behavior parameter so as to calculate the recipe weight of each recipe contained in the historical behavior data;
the first calculation submodule is used for calculating the recipe label weight corresponding to each recipe label and the food material weight corresponding to each food material contained in the historical behavior data according to the recipe weight of each recipe;
the second calculating submodule is used for calculating the food material category weight corresponding to each food material category contained in the historical behavior data according to the food material weight of each food material;
and the second determining submodule is used for determining the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe label weight corresponding to each recipe label.
7. The information push device according to claim 6, wherein the recipe tag comprises: taste label, cooking difficulty rating label, efficacy label; and
the second determining submodule is specifically configured to:
determining a taste preference label of the user according to the weight of the recipe label corresponding to each taste label;
determining a cooking skill label of the user according to the recipe label weight corresponding to each cooking difficulty grade label;
determining health attribute preference labels of the users according to the recipe label weight corresponding to each efficacy label;
and determining the food material preference label of the user according to the food material category weight corresponding to each food material category.
8. The information pushing apparatus according to claim 7, wherein the second determining submodule is specifically configured to:
determining a target taste label corresponding to the target recipe label weight with the weight larger than the average weight of the taste labels as the taste preference label;
determining the corresponding cooking skill label according to the target cooking difficulty grade label corresponding to the target recipe label with the maximum weight;
determining a corresponding health attribute preference label according to a target efficacy label corresponding to a target recipe label weight with the weight larger than the average weight of the health attribute;
and determining the target food material category corresponding to the target food material category weight with the weight larger than the average weight of the food material categories as the food material preference label.
9. The information pushing apparatus according to claim 7 or 8, further comprising:
an obtaining module, configured to obtain a diet taboo tag of the user when the second determining sub-module determines the diet preference portrait of the user according to the food material category weight corresponding to each food material category and the recipe tag weight corresponding to each recipe tag; and
the calculation module is specifically configured to: taking the diet taboo label, the taste preference label, the cooking skill label, the health attribute preference label and the food material preference label as the diet preference portrait of the user.
10. The information pushing apparatus according to claim 9, wherein the determining module comprises:
a deletion submodule, configured to delete a target food material and/or a recipe, which is included in the initial push list and matches the diet taboo tag, so as to obtain an intermediate push list;
the setting sub-module is used for setting a pushing index corresponding to each preference label in the rest preference labels except the diet taboo label in the diet preference portrait;
and the third calculation sub-module is used for calculating the popularity index of each food material and/or recipe in the middle pushing list according to the weight corresponding to each preference label and the pushing index.
11. A computer device, comprising:
a processor;
memory for storing executable instructions of the processor, wherein the processor is configured to implement the steps of the information pushing method according to any one of claims 1 to 5 when executing the executable instructions stored in the memory.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the information pushing method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711286498.2A CN107992583B (en) | 2017-12-07 | 2017-12-07 | Information pushing method, information pushing device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711286498.2A CN107992583B (en) | 2017-12-07 | 2017-12-07 | Information pushing method, information pushing device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107992583A CN107992583A (en) | 2018-05-04 |
CN107992583B true CN107992583B (en) | 2020-09-04 |
Family
ID=62036740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711286498.2A Active CN107992583B (en) | 2017-12-07 | 2017-12-07 | Information pushing method, information pushing device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107992583B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769159A (en) * | 2018-05-16 | 2018-11-06 | 北京豆果信息技术有限公司 | A kind of electronic cookbook intelligent recommendation method |
CN108806770A (en) * | 2018-05-16 | 2018-11-13 | 北京豆果信息技术有限公司 | A kind of diet recommendation method based on user |
CN109492159A (en) * | 2018-10-31 | 2019-03-19 | 深圳市轱辘汽车维修技术有限公司 | A kind of content delivery method, content push device and electronic equipment |
CN110060760A (en) * | 2019-04-17 | 2019-07-26 | 商洛学院 | A kind of information processing method and electronic equipment |
CN110223757A (en) * | 2019-04-23 | 2019-09-10 | 平安科技(深圳)有限公司 | The recommended method of recipe scheme, device, medium, electronic equipment |
CN110335118A (en) * | 2019-07-04 | 2019-10-15 | 合肥美的电冰箱有限公司 | Menu recommended method, menu recommendation apparatus and machine readable storage medium |
CN111787042B (en) * | 2019-09-19 | 2022-09-06 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
CN110688578A (en) * | 2019-09-28 | 2020-01-14 | 北京字节跳动网络技术有限公司 | Screen locking wallpaper recommendation method and device and electronic equipment |
CN110909043A (en) * | 2019-11-15 | 2020-03-24 | 上海易点时空网络有限公司 | Violation data query method and system based on fuzzy query key words |
CN111067369A (en) * | 2019-12-20 | 2020-04-28 | 珠海格力电器股份有限公司 | Fire control method, device, equipment and medium of intelligent stove |
CN111415328B (en) * | 2020-02-20 | 2023-07-11 | 北京三快在线科技有限公司 | Method and device for determining article analysis data and electronic equipment |
CN111475710A (en) * | 2020-03-06 | 2020-07-31 | 珠海格力电器股份有限公司 | Policy recommendation method and device, electronic equipment and computer readable medium |
JP2021157390A (en) * | 2020-03-26 | 2021-10-07 | 東芝テック株式会社 | Food material inquiry system, food material inquiry method, and food material inquiry program |
CN111863193A (en) * | 2020-07-23 | 2020-10-30 | 青岛海尔科技有限公司 | Method, device and equipment for recipe recommendation |
CN112820379B (en) * | 2021-01-26 | 2024-02-02 | 吾征智能技术(北京)有限公司 | Intelligent diet recommendation method and system integrating user images |
CN114140205A (en) * | 2021-12-02 | 2022-03-04 | 河北雄安三千科技有限责任公司 | Commodity screening method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105653699A (en) * | 2015-12-30 | 2016-06-08 | 青岛海尔股份有限公司 | Recipe based information pushing method and apparatus |
CN106548006A (en) * | 2016-10-09 | 2017-03-29 | 浙江大学 | A kind of meals based on user's typical case's taste recommend method |
CN107341350A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Food materials intelligent management and device, server, intelligent refrigerator, storage medium |
-
2017
- 2017-12-07 CN CN201711286498.2A patent/CN107992583B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105653699A (en) * | 2015-12-30 | 2016-06-08 | 青岛海尔股份有限公司 | Recipe based information pushing method and apparatus |
CN106548006A (en) * | 2016-10-09 | 2017-03-29 | 浙江大学 | A kind of meals based on user's typical case's taste recommend method |
CN107341350A (en) * | 2017-07-05 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Food materials intelligent management and device, server, intelligent refrigerator, storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107992583A (en) | 2018-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107992583B (en) | Information pushing method, information pushing device, equipment and storage medium | |
US20220005376A1 (en) | Systems and methods to mimic target food items using artificial intelligence | |
Aguilar et al. | Grab, pay, and eat: Semantic food detection for smart restaurants | |
Ueda et al. | User’s food preference extraction for personalized cooking recipe recommendation | |
Carlucci et al. | Certification labels versus convenience formats: What drives the market in aquaculture products? | |
CN103810284A (en) | Kitchen management method and device | |
CN110851571B (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
Kazama et al. | A neural network system for transformation of regional cuisine style | |
CN110223757A (en) | The recommended method of recipe scheme, device, medium, electronic equipment | |
CN109801138A (en) | The searching method and device of commodity picture | |
CN111949889A (en) | Sharing platform intelligent recommendation method and system based on big data and readable storage medium | |
Metwally et al. | Learning personal food preferences via food logs embedding | |
CN112102922B (en) | Information recommendation method and device | |
CN110838356A (en) | Data processing method and device and storage medium | |
Altosaar et al. | RankFromSets: Scalable set recommendation with optimal recall | |
KR102277653B1 (en) | Nutrient Profiling-based Pet Food Recommendation System | |
CN108416628A (en) | A kind of dining room vegetable intelligent recommendation system of the fusion more relations on attributes of food | |
CN114882973A (en) | Daily nutrient intake analysis method and system based on standard food recognition | |
CN114388102A (en) | Diet recommendation method and device and electronic equipment | |
Tang et al. | Healthy Recipe Recommendation using Nutrition and Ratings Models | |
CN117541359B (en) | Dining recommendation method and system based on preference analysis | |
Hakguder et al. | Smart Diet Management through Food Image and Cooking Recipe Analysis | |
CN108228771A (en) | One kind is based on user tag algorithm | |
Syaifudin et al. | An Implementation of Recipe Recommendation System Based on Ingredients Availability Using Content-based and Collaborative Filtering | |
CN113220977B (en) | Menu recommendation method, refrigerator and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 230088 Building No. 198, building No. 198, Mingzhu Avenue, Anhui high tech Zone, Anhui Applicant after: Hefei Hualing Co.,Ltd. Address before: 230601 R & D building, No. 176, Jinxiu Road, Hefei economic and Technological Development Zone, Anhui 501 Applicant before: Hefei Hualing Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |