CN103412936A - Dish recommendation system based on data mining and cloud computing service - Google Patents
Dish recommendation system based on data mining and cloud computing service Download PDFInfo
- Publication number
- CN103412936A CN103412936A CN2013103680924A CN201310368092A CN103412936A CN 103412936 A CN103412936 A CN 103412936A CN 2013103680924 A CN2013103680924 A CN 2013103680924A CN 201310368092 A CN201310368092 A CN 201310368092A CN 103412936 A CN103412936 A CN 103412936A
- Authority
- CN
- China
- Prior art keywords
- user
- vegetable
- dining room
- model
- scheme
- 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.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a dish recommendation system based on data mining and cloud computing service. The method comprises the following steps: 1) receiving a recommendation request input by a user; b) judging whether the user selects a restaurant, and if not, recommending at least one restaurant for the user; c) reading a restaurant template according to the selected restaurant or the recommended restaurant, so as to generate at least one dish collocation scheme based on a dish model; d) scoring the generated at least one dish collocation scheme, wherein scoring standards are selected from at least one of special dish matching judgement, user historical behaviour and evaluation judgement, food material repeatability judgement and user collaborative recommendation weighting; e) selecting a scheme with the highest score and recommending the scheme to the user; f) judging whether the user is satisfied with the recommended scheme, and if not, recommending again until the user is satisfied; and g) updating the dish model, the restaurant model and a user model based on the scheme which the user is satisfied with or not.
Description
Technical field
The present invention relates to the vegetable commending system, particularly vegetable commending system and the method for a kind of based on data excavation and cloud computing service.
Background technology
In the service of catering trade, how being the customer recommendation that it is difficult to cater for all tastes makes its satisfied vegetable, is the target that catering trade is pursued always.Due to the special favor difference in every restaurant, eater's preference, the number of having dinner, the standard etc. of having dinner are also had nothing in common with each other, and therefore are difficult to find a kind of blanket method to meet every restaurant and every client's the demand of having dinner.
In the prior art vegetable commending system or method, be often the rule of businessman according to its a set of artificial formulation of summarizing the experience out, this rule, because the too much people that adulterated is the subjective assessment standard, therefore is only suitable in the restaurant of specific period, specific taste type or the crowd that specifically has dinner usually.For some restaurant of newly starting business, these experiences are often also inapplicable.In addition, due to existing restaurant, also can't know client's individual demand when attracting client, therefore same recommendation vegetable may be very blindly, and due to dish amount, price, taste etc. factor and be not suitable for all crowds that have dinner, not only expended the energy in restaurant, and the experience of well having dinner is provided can't for the client that has dinner.
Along with the development of Internet technology and cloud computing technology, more and more traditional experiences of summing up by manpower can be replaced by data mining technology.Data mining (Data mining) is a kind of method in knowledge discovery in database, generally refers to the process that is hidden in the information that special relationship is arranged wherein from automatic search a large amount of data.Data mining is usually relevant with computer science, and realizes above-mentioned target by all multi-methods such as statistics, on-line analysis processing, information retrieval, machine learning, expert system (relying on thumb rule in the past) and pattern-recognitions.Data mining can also be as a kind of decision support processes, it is mainly based on artificial intelligence, machine learning, pattern-recognition, statistics, database, visualization technique etc., analyze the data of enterprise increasingly automatedly, make the reasoning of the property concluded, therefrom excavate potential pattern, aid decision making person adjusts market strategy, reduces risks, and makes correct decision-making.
Therefore, need a kind of vegetable commending system and the method that can utilize data mining technology, can effectively solve vegetable in prior art and recommend the problem of blindness, thereby improve eater's the experience of having a dinner.
Summary of the invention
The object of the present invention is to provide the vegetable recommend method of a kind of based on data excavation and cloud computing service, described method is based on the collected vegetable model of recommended engine, dining room model and user model, and the method comprises the steps: a) to receive the recommendation request of user's input; B) judge whether the user has selected dining room, if non-selected, for the user, recommend at least one dining room; C) according to dining room selected or that recommend, read this dining room masterplate, generate at least one cover vegetable arranging scheme based on the vegetable model; D) at least one cover vegetable scheme generated is given a mark, described marking standard is selected from wherein at least a: the speciality matching judgment; User's historical behavior and evaluation judgement; The judgement of food materials repeatability and user collaborative are recommended weighting; E) select the scheme of top score to recommend the user; F) judge that whether the user is satisfied to the scheme of recommending, if dissatisfied, recommends, again until the user is satisfied; G) or unsatisfied scheme satisfied based on the user, upgrade described vegetable model, dining room model and user model.
Preferably, the recommendation request in described step a) comprises the dining room that the user selects and/or the number of having dinner.
Preferably, in described step b), pass through the current geographical location information of consumer positioning, for the user recommends dining room.
Preferably, it is by the mode of proper vector, to characterize user's taste feature that the user collaborative in described step d) is recommended weighting, then the cosine similarity between the calculated characteristics vector means the taste hobby similarity between two two users.
Preferably, described cosine similarity is greater than at 0.618 o'clock, assert that between two users, taste is similar.
Preferably, in described step f), again scheme is recommended according to user feedback.
Preferably, in described step g), again scheme is recommended according to user feedback.
Preferably, described vegetable model and dining room model are the proper vectors that a plurality of features and evaluation information by vegetable and dining room form.
According to a further aspect of the invention, provide the vegetable commending system of a kind of based on data excavation and cloud computing service, described system comprises: the information acquisition module that gathers vegetable information, dining room information and user profile; Store respectively the database of collected vegetable information, dining room information and user profile; The model database that comprises vegetable model, dining room model and user model based on collected information foundation; Described recommended engine, for the recommendation request of the input of the user according to receiving, judges whether the user has selected dining room, if non-selected, for the user, recommends at least one dining room; According to dining room selected or that recommend, read this dining room masterplate, generate at least one cover vegetable arranging scheme based on the vegetable model; At least one cover vegetable scheme generated is given a mark, and described marking standard is selected from wherein at least a: the speciality matching judgment; User's historical behavior and evaluation judgement; The judgement of food materials repeatability and user collaborative are recommended weighting; Select the scheme of top score to recommend the user; Judge that whether the user is satisfied to the scheme of recommending, if dissatisfied, recommends, again until the user is satisfied; Satisfied or unsatisfied scheme, upgrade described vegetable model, dining room model and user model database based on the user.
According to vegetable commending system of the present invention and recommended engine, can effectively utilize data mining technology vegetable is recommended, can effectively solve the problem that vegetable in prior art is recommended blindness.According to recommend method of the present invention and commending system, have self-learning function, can improve constantly the accuracy of recommendation by user's feedback and collection user's historical behavior information, thereby improve eater's the experience of having a dinner.
The description and the follow-up detailed description that should be appreciated that aforementioned cardinal principle are exemplary illustration and explanation, should not use the restriction of doing the claimed content of the present invention.
The accompanying drawing explanation
With reference to the accompanying drawing of enclosing, the more purpose of the present invention, function and advantage will be illustrated by the following description of embodiment of the present invention, wherein:
Fig. 1 schematically shows the system chart according to the vegetable commending system of the based on data excavation of the embodiment of the present invention and cloud computing service;
The schematically illustrated process flow diagram of recommend method according to recommended engine of the present invention of Fig. 2.
Embodiment
By reference to one exemplary embodiment, purpose of the present invention and function and will be illustrated be used to the method that realizes these purposes and function.Yet the present invention is not limited to following disclosed one exemplary embodiment; Can to it, be realized by multi-form.The essence of instructions is only to help various equivalent modifications Integrated Understanding detail of the present invention.
Hereinafter, embodiments of the invention will be described with reference to the drawings.In the accompanying drawings, identical Reference numeral represents same or similar parts, or same or similar step.
Fig. 1 schematically shows the system chart according to the vegetable commending system of the based on data excavation of the embodiment of the present invention and cloud computing service.
According to the present invention, at server system 120, store the user profile gathered by client 110, essential information, preference information and the historical information in the past etc. that comprise the user, and by the user, pass through mutual or dining room information that directly collect by dining room trade company, vegetable information of client 110 and server system 120 etc., then based on these information, utilize recommended engine to calculate, thereby for the user, recommend to be applicable to the vegetable of its requirement.The user can also be by client upload oneself preference so that server system 120 carries out personalized service, as personalized recommendation etc.
Use the information of client 110 inputs for example to comprise that the user is for the evaluation information in the authentication information of logon server system, vegetable information, the number of having dinner, taste preference, price preference, vegetable or dining room that the user selects etc.The information of client 110 output is such as comprising vegetable information that server system is recommended based on user's selection, dining room information etc.The user can also carry out alternately with server system on the Information base that server system is recommended, further input qualifications, revise partly and recommend vegetable etc., thereby make server system realize recommending more accurately.
Subscriber information module 112 comprises user's essential information, user's preference information and the historical information that the user used this client in the past.Described user basic information is such as comprising user name, identity information, positional information etc.Described user's preference information for example comprises vegetable, the dining room of the taste, hobby of user preferences/do not like/do not like, and commercial circle scope of the price range scope of user preference, preference, dining room type etc.Historical information is such as comprise that information, user that the user estimated dining room, vegetable carried out the vegetable information of having a dinner, dining room information etc. in the past in the past.Preferably, these historical informations can remain on this locality of client 110, in the mode of off-line, preserve, when client 110 and server system 120 carry out when mutual uploading onto the server system 120.
According to the user profile of collecting, vegetable information and dining room information, set up the corresponding model used of recommending, be stored in model database 125, for recommended engine 126, use when to the user, recommending to calculate.Model according to the present invention comprises vegetable model, dining room model and user model.
The vegetable model
The vegetable model is that collected vegetable information is carried out to Data Analysis and excavation, by a plurality of dimensions, vegetable is carried out to characterization and label, in order to set up the masterplate that vegetable is recommended.To the foundation of vegetable model mainly based on naturally semantic technical Analysis and aid in.The method for building up of vegetable model comprises the steps:
At first, set up keyword database.Described key word comprises menu name, vegetable type, taste type, food materials title, condiment title and cooking technology, because the quantity of food materials, condiment and culinary art can be exhaustive, so the key word number comprised in keyword database is limited.Can this keyword database by the mode that network is collected.For example, the vegetable key word can comprise " diced chicken ", " sliced meat ", " mushroom " etc.The type key word can comprise " meat dish ", " vegetable dish ", " soup ", " Sichuan cuisine " etc.The taste key word can comprise " peppery ", " salty ", " sweet " etc.The food materials key word can comprise " chicken ", " beef ", " mushroom " etc.The condiment key word can comprise " vinegar ", " soy sauce ", " salt " etc.The culinary art key word can comprise " stir-fry ", " decocting ", " exploding " etc.Then, extract the food materials that each vegetable key word is corresponding, set up the corresponding relation between vegetable and food materials.For example vegetable key word " diced chicken " corresponding to food materials " chicken ", " mushroom " corresponding to " mushroom ".Be understandable that, this corresponding relation can not be man-to-man corresponding relation, such as " sliced meat " can corresponding " beef ", " chicken ", " pork " etc.
Then collected menu name is carried out to semanteme and disassembles and analyze, based on the key word extracted in step 1, be this menu name additional label, thereby set up the model of this vegetable, namely set up the vegetable model database formed by following proper vector entry:
<numbering: menu name: label 1, label 2, label 3 ..., label n >
For example, " mushroom rape " can disassemble and be labeled as a plurality of labels such as " mushroom ", " mushroom ", " rape ", " vegetables ", " stir-fry ", " vegetable dish ", namely in database, preserves following entry:
<025: the mushroom rape: mushroom, mushroom, rape, vegetables, fry ..., vegetable dish >
Preferably, the label of vegetable can also comprise evaluation information, and namely pouplarity, can present with the form of score, selects when recommending vegetable for recommended engine.
Because identical menu or menu name may be used in different dining rooms, therefore resolve the also vegetable of label and can between different dining rooms, share.
Described keyword database is dynamic updatable, can provide this database is upgraded according to user's input and businessman.The user can be also the vegetable additional label according to the hobby of oneself.
The dining room model
The dining room model is that collected dining room information is carried out to Data Analysis and excavation, by a plurality of dimensions, characterization and label are carried out in dining room, and based on the label in above-mentioned vegetable model and dining room for each dining room analyzes a set of vegetable collocation masterplate, in order to recommend to the user.The method for building up of dining room model comprises the steps:
Dining room data based on original collection are carried out characterization and label to dining room.Based on information include but not limited to the local flavor in dining room, as western-style food, Chinese meal, Hang Bangcai, North-east China cuisine etc., the business hours in dining room, as 24 HOUR ACCESS, provide food etc., the price in dining room, galleryful, speciality, pouplarity (score) etc.Based on these, be characterized as each dining room and tag, set up the model in this dining room, namely set up the dining room model database formed by following proper vector entry:
<numbering: dining room title: label 1, label 2, label 3 ..., label n >
For example, certain dining room can be in model database store items as follows:
<098: Peking Duck Restaurant everyday: Beijing cuisine, roast duck, per capita 100 ..., dinner >
Then, based on the dining room model of setting up, the vegetable information provided from reading this dining room the information database of dining room, for each dining room generates based on difference have dinner the average consumption price in number, this dining room and the recommendation menu scheme masterplate of basic meat and vegetables collocation.The scheme masterplate generated can be adjusted based on a plurality of dimensions again, for example, have dinner type (lunch, dinner or food), collocation style how many based on different price class, taste, dish amount, whether comprise speciality etc., be stored in model database.For example, certain dining room comprises<meat dish 1, meat dish 2, meat dish 3, vegetable dish 1, vegetable dish 2, soup 1 based on the vegetable suggested design masterplate that 4 people generate >, read the dining room label and find that the type in this dining room is North-east China cuisine, the dish amount is larger, therefore this suggested design masterplate is finely tuned, remove meat dish, become<meat dish 1, meat dish 2, vegetable dish 1, vegetable dish 2, soup 1.
When selecting vegetable, can priority be set for the speciality in this dining room and the collocation dish of speciality, namely preferentially select speciality as recommendation.For example in Pekinese's Quanjude, must order roast duck, and roast duck has corresponding garnishes.When recommending template, will first-selected roast duck and the recommendation of garnishes.
The scheme masterplate generated, after the user is recommended in the request according to the user, can also be adjusted according to behavior on user's line.For example, can for the user, provide with dish, subtract dish or change the selection of certain vegetable in client 110.Server system can also be collected user's adjustment information and adjust with inappropriate masterplate that system is generated as feedback data.If the arranging scheme to a set of initial recommendation is a lot of with the user of dish, prove that the vegetable of this masterplate initial setting up is given short measure, otherwise, prove that component is too much.Perhaps, the frequency that certain vegetable is replaced is very high, illustrates that this vegetable is out of favour in this dining room.Therefore, server system can be collected user's operation, carries out suitable correction arranging scheme.Therefore, according to dining room of the present invention model and to recommend masterplate be dynamic updatable and can be self-adjusting.Preferably, can to each masterplate, label or score be set according to user's feedback, to reflect the pouplarity of this masterplate, for recommended engine reference when recommending vegetable.
User model
User model is that collected user profile is carried out to Data Analysis and excavation, by a plurality of dimensions, the user is carried out to characterization and label.For example, user's geographic position commonly used, preference price etc.In addition, user model can also comprise by unirecord under counting user becomes reconciled and comments record, is the vegetable list of each user's generation.From the vegetable list, counting food materials user preference or that ate, style of cooking tendency, in order to characterize a user.
Based on these, be characterized as each user and tag, set up this user's model, namely set up the user model database formed by following entry:
<numbering: user's name: label 1, label 2, label 3 ..., label n >
For example, certain user can be in model database store items as follows:
<098:Mike: Shanghai, 50 yuan, mushroom ..., history places an order >
Fig. 2 shows according to the recommendation process of recommended engine 126 of the present invention and calculates the also process flow diagram of generating recommendations based on user's request.The process that recommended engine according to the present invention is recommended comprises the steps:
A) speciality matching judgment.Read each vegetable comprised in every cover arranging scheme, if certain vegetable conforms to " speciality " in this dining room label, the score of this cover arranging scheme adds the vegetable number of 1x n(n for coupling);
B) user's historical behavior and evaluation judgement.Read each vegetable comprised in every cover arranging scheme, if contain the vegetable that the user once ate or user's favorable comment is crossed in this cover arranging scheme, the score of this cover arranging scheme adds the vegetable number of 1x n(n for coupling); If contain the poor vegetable of commenting of user, the score of this cover arranging scheme subtracts the vegetable number of 1x n(n for coupling);
C) food materials repeatability judgement.For all vegetables in each arranging scheme, scan the label in its vegetable model, if find what food materials repeated, the score of this sets of plan subtracts the number of times of 1x n(n for repeating);
D) user collaborative is recommended weighting.User collaborative recommends to refer to, if two users are more approaching to the taste of vegetable, the vegetable liked of user can more be recommended by the user identical with its taste.That is to say, allow the close user of taste recommend mutually vegetable can more easily allow the user satisfied.This recommend method is specific as follows:
At first, calculate the taste hobby similarity between two two users.At first, for each user, set up the computation model of its different styles of cooking or style, can characterize by the mode of proper vector the taste feature of user to certain style of cooking or local flavor.For example, the proper vector of the meat style of cooking of user A is:
User A={ " pork ": 4, " beef ": 0, " mutton ": 2, " flesh of fish ": 5, " chicken ": 4, " peppery degree ": 3, " salinity ": 4},
The meat style of cooking proper vector of user B is:
User B={ " pork ": 2, " beef ": 3, " mutton ": 3, " flesh of fish ": 0, " chicken ": 4, " peppery degree ": 4, " salinity ": 2}
In above-mentioned proper vector, comprised food materials and taste that the user likes, formed with food materials and corresponding marking value thereof.For example, in above-mentioned example, best result 5 minutes, minimum minute 1 minute, the higher expression of mark user's favorable rating was higher, must be divided into 0 and show countless certificates.This score can be by the recommended behavior of collecting user in the past, user's the acquisitions such as evaluation information.
Cosine similarity between the proper vector of the meat style of cooking of the hobby similarity of the meat style of cooking of user A, B by calculating two users obtains.
A wherein
i, B
i(i=1 ..., n) value of each component in difference respective user proper vector, i.e. marking value in above-mentioned example.With the above-mentioned example that is exemplified as, can calculate user A and user B is 0.707 for the hobby similarity of the meat style of cooking.Similarity is larger, illustrates that two tastes between the user are more similar.
After having calculated the proper vector cosine similarity of two user models, then compare with a predefined threshold value, if higher than threshold value, think that two user's tastes are similar, can carry out mutually with reference to recommending; If lower than threshold value, think two users' taste dissmilarity.Preferably, Threshold is 0.618.
Preferably, can also carry out further optimizing the power of adjusting to above-mentioned Collaborative Recommendation.Particularly, to each user, extract and the immediate x of his a food similarity user, favorite y road vegetable in this x user is extracted, in user's recommendation list, these vegetables are weighted to processing.Concrete weighting scheme is: if certain course in set y, occur n time, the corresponding vegetable weights of user's recommendation list are added to n/y, weighting is the highest is no more than 1.Preferably, x is that 10, y is 10.
In sum, according to vegetable commending system of the present invention and recommended engine, can effectively utilize data mining technology vegetable is recommended, can effectively solve the problem that vegetable in prior art is recommended blindness.According to recommend method of the present invention and commending system, have self-learning function, can improve constantly the accuracy of recommendation by user's feedback and collection user's historical behavior information, thereby improve eater's the experience of having a dinner.
Cross the explanation of the present invention and the practice that in conjunction with here, disclose, other embodiment of the present invention are easy to expect and understand for those skilled in the art.Illustrate with embodiment and only be considered to exemplary, true scope of the present invention and purport limit by claim.
Claims (10)
1. a based on data excavates and the vegetable recommend method of cloud computing service, and described method is based on the collected vegetable model of recommended engine, dining room model and user model, and the method comprises the steps:
A) receive the recommendation request of user's input;
B) judge whether the user has selected dining room, if non-selected, for the user, recommend at least one dining room;
C) according to dining room selected or that recommend, read this dining room masterplate, generate at least one cover vegetable arranging scheme based on the vegetable model;
D) at least one cover vegetable scheme generated is given a mark, described marking standard is selected from wherein at least a: the speciality matching judgment; User's historical behavior and evaluation judgement; The judgement of food materials repeatability and user collaborative are recommended weighting;
E) select the scheme of top score to recommend the user;
F) judge that whether the user is satisfied to the scheme of recommending, if dissatisfied, recommends, again until the user is satisfied;
G) or unsatisfied scheme satisfied based on the user, upgrade described vegetable model, dining room model and user model.
2. vegetable recommend method as claimed in claim 1, the recommendation request in wherein said step a) comprises the dining room that the user selects and/or the number of having dinner.
3. vegetable recommend method as claimed in claim 1, pass through the current geographical location information of consumer positioning, for the user recommends dining room in wherein said step b).
4. vegetable recommend method as claimed in claim 1, it is by the mode of proper vector, to characterize user's taste feature that user collaborative in wherein said step d) is recommended weighting, then the cosine similarity between the calculated characteristics vector means the taste hobby similarity between two two users.
5. vegetable recommend method as claimed in claim 4, wherein said cosine similarity is greater than at 0.618 o'clock, assert that between two users, taste is similar.
6. vegetable recommend method as claimed in claim 1, recommend scheme again according to user feedback in wherein said step f).
7. vegetable recommend method as claimed in claim 1, recommend scheme again according to user feedback in wherein said step g).
8. vegetable recommend method as claimed in claim 1, wherein said vegetable model and dining room model are the proper vectors that a plurality of features and the evaluation information by vegetable and dining room forms.
9. a based on data excavates and the vegetable commending system of cloud computing service, and described system comprises:
Gather the information acquisition module of vegetable information, dining room information and user profile;
Store respectively the database of collected vegetable information, dining room information and user profile;
The model database that comprises vegetable model, dining room model and user model based on collected information foundation;
Described recommended engine, for the recommendation request of the input of the user according to receiving, judges whether the user has selected dining room, if non-selected, for the user, recommends at least one dining room; According to dining room selected or that recommend, read this dining room masterplate, generate at least one cover vegetable arranging scheme based on the vegetable model; At least one cover vegetable scheme generated is given a mark, and described marking standard is selected from wherein at least a: the speciality matching judgment; User's historical behavior and evaluation judgement; The judgement of food materials repeatability and user collaborative are recommended weighting; Select the scheme of top score to recommend the user; Judge that whether the user is satisfied to the scheme of recommending, if dissatisfied, recommends, again until the user is satisfied; Satisfied or unsatisfied scheme, upgrade described vegetable model, dining room model and user model database based on the user.
10. vegetable commending system as claimed in claim 9, it is by the mode of proper vector, to characterize user's taste feature that wherein said user collaborative is recommended weighting, then the cosine similarity between the calculated characteristics vector means the taste hobby similarity between two two users.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103680924A CN103412936A (en) | 2013-08-21 | 2013-08-21 | Dish recommendation system based on data mining and cloud computing service |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103680924A CN103412936A (en) | 2013-08-21 | 2013-08-21 | Dish recommendation system based on data mining and cloud computing service |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103412936A true CN103412936A (en) | 2013-11-27 |
Family
ID=49605948
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013103680924A Pending CN103412936A (en) | 2013-08-21 | 2013-08-21 | Dish recommendation system based on data mining and cloud computing service |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103412936A (en) |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104750745A (en) * | 2013-12-30 | 2015-07-01 | 华为技术有限公司 | Agents and information processing method thereof |
CN105160606A (en) * | 2015-08-30 | 2015-12-16 | 安徽味唯网络科技有限公司 | Automatic food ordering method |
CN105225182A (en) * | 2015-09-07 | 2016-01-06 | 广东欧珀移动通信有限公司 | A kind of dietary recommendations continued method and device thereof |
CN105468630A (en) * | 2014-09-04 | 2016-04-06 | 口碑控股有限公司 | Method and apparatus for providing user information |
CN105469291A (en) * | 2014-09-04 | 2016-04-06 | 口碑控股有限公司 | User information providing method and device |
CN105760541A (en) * | 2016-03-15 | 2016-07-13 | 传成文化传媒(上海)有限公司 | Video food ordering recommendation method and system |
CN105869079A (en) * | 2016-03-25 | 2016-08-17 | 杭州银盒宝成科技有限公司 | Dish-ordering system and method |
WO2016206026A1 (en) * | 2015-06-24 | 2016-12-29 | 程强 | Method for collecting statistics for dish-ordering information, and dish-ordering recording system |
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 |
CN106658078A (en) * | 2016-12-23 | 2017-05-10 | 北京小米移动软件有限公司 | Ordering method and device through television terminal |
CN106815745A (en) * | 2016-12-30 | 2017-06-09 | 北京三快在线科技有限公司 | Vegetable recommends method and system |
CN106886921A (en) * | 2017-02-17 | 2017-06-23 | 正源信用(北京)科技有限公司 | Personalized recommendation method based on user interest |
CN107003978A (en) * | 2014-08-15 | 2017-08-01 | 西尼·尼科尔·爱普斯坦 | For by the system and computer approach of user's vision guide to current interest |
CN107092647A (en) * | 2017-03-10 | 2017-08-25 | 北京小度信息科技有限公司 | A kind of method and device that combination of resources is provided |
CN107194746A (en) * | 2017-06-20 | 2017-09-22 | 京东方科技集团股份有限公司 | One kind dining recommends method and device |
CN107332878A (en) * | 2017-06-05 | 2017-11-07 | 北京三快在线科技有限公司 | Method for pushing and device, the electronic equipment of information |
CN107391531A (en) * | 2017-04-11 | 2017-11-24 | 阿里巴巴集团控股有限公司 | A kind of vegetable recommends method and apparatus |
CN107492015A (en) * | 2017-08-18 | 2017-12-19 | 无锡雅座在线科技股份有限公司 | The recommendation method and apparatus of object |
WO2018006726A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying knowledge point for which user may potentially request help |
CN107682401A (en) * | 2017-09-01 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | Information inspection method and relevant device |
CN107862542A (en) * | 2017-09-28 | 2018-03-30 | 北京三快在线科技有限公司 | A kind of vegetable recommends method and apparatus |
CN107863138A (en) * | 2017-10-31 | 2018-03-30 | 珠海格力电器股份有限公司 | Menu generating means and method |
CN107942750A (en) * | 2017-11-30 | 2018-04-20 | 广东美的厨房电器制造有限公司 | Control device, control method, computer equipment and readable storage medium storing program for executing |
CN108022634A (en) * | 2017-12-28 | 2018-05-11 | 中粮集团有限公司 | A kind of food preparation method and device |
WO2018095307A1 (en) * | 2016-11-25 | 2018-05-31 | 口碑控股有限公司 | Method and device for releasing evaluation information |
CN108304448A (en) * | 2017-12-08 | 2018-07-20 | 无锡雅座在线科技股份有限公司 | Vegetable recommends method and device, storage medium, processor |
CN108389268A (en) * | 2018-02-07 | 2018-08-10 | 浙江莲荷科技有限公司 | Fee payment method, system and equipment |
CN108492213A (en) * | 2018-02-02 | 2018-09-04 | 广州视源电子科技股份有限公司 | Food materials buy the generation method and device, server apparatus, storage medium of inventory |
CN108596789A (en) * | 2018-03-29 | 2018-09-28 | 客如云科技(成都)有限责任公司 | A kind of standardized method of vegetable |
US20180293489A1 (en) * | 2017-04-05 | 2018-10-11 | International Business Machines Corporation | Determining a place where all members of a group will enjoy eating by learning the preferences of individual members and the group |
CN108734552A (en) * | 2018-05-15 | 2018-11-02 | 浙江口碑网络技术有限公司 | User's sense of taste method for establishing model and device |
CN108897768A (en) * | 2018-05-25 | 2018-11-27 | 北京三快在线科技有限公司 | A kind of method of ordering and device, electronic equipment |
CN108958091A (en) * | 2017-05-25 | 2018-12-07 | 中兴通讯股份有限公司 | A kind of method and device, system automating cooking |
CN109285597A (en) * | 2018-10-08 | 2019-01-29 | 北京健康有益科技有限公司 | A kind of dietotherapy recipe recommendation method, apparatus and readable medium |
CN109300059A (en) * | 2018-09-13 | 2019-02-01 | 口口相传(北京)网络技术有限公司 | Vegetable recommended method and device |
CN109299123A (en) * | 2018-09-29 | 2019-02-01 | 口碑(上海)信息技术有限公司 | Vegetable feature database synchronous method and device |
CN109471973A (en) * | 2018-10-31 | 2019-03-15 | 深圳市元征科技股份有限公司 | A kind of restaurant intelligent recommendation method, apparatus, equipment and storage medium |
CN109522482A (en) * | 2018-11-13 | 2019-03-26 | Oppo广东移动通信有限公司 | Game application classification page display method, device, storage medium and terminal |
CN109615428A (en) * | 2018-12-10 | 2019-04-12 | 拉扎斯网络科技(上海)有限公司 | Trade company's recommended method, device, system and server |
CN109766364A (en) * | 2019-01-31 | 2019-05-17 | 珠海优特智厨科技有限公司 | A kind of method and device of the single taste label of determining menu |
CN109840296A (en) * | 2019-01-31 | 2019-06-04 | 珠海优特智厨科技有限公司 | A kind of method and device of determining menu composite flavor label |
CN109934658A (en) * | 2017-12-19 | 2019-06-25 | 阿里巴巴集团控股有限公司 | A kind of data processing method, display methods and calculate equipment |
CN110210999A (en) * | 2018-02-28 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Catering information processing method, apparatus and system |
CN111158803A (en) * | 2018-11-07 | 2020-05-15 | 财团法人工业技术研究院 | Virtual assistant negotiation system and method thereof |
CN111859188A (en) * | 2020-07-03 | 2020-10-30 | 美味不用等(上海)信息科技股份有限公司 | Restaurant recommendation method and system based on hierarchical analysis of large-scale matrix |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120116915A1 (en) * | 2010-11-08 | 2012-05-10 | Yahoo! Inc. | Mobile-Based Real-Time Food-and-Beverage Recommendation System |
CN102651052A (en) * | 2012-03-29 | 2012-08-29 | 陶杰 | Intelligent combo type dish ordering method |
CN102663265A (en) * | 2012-05-04 | 2012-09-12 | 庄燕滨 | Catering service platform system based on cloud computing platform and working method thereof |
US20120278252A1 (en) * | 2011-04-27 | 2012-11-01 | Sethna Shaun B | System and method for recommending establishments and items based on consumption history of similar consumers |
-
2013
- 2013-08-21 CN CN2013103680924A patent/CN103412936A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120116915A1 (en) * | 2010-11-08 | 2012-05-10 | Yahoo! Inc. | Mobile-Based Real-Time Food-and-Beverage Recommendation System |
US20120278252A1 (en) * | 2011-04-27 | 2012-11-01 | Sethna Shaun B | System and method for recommending establishments and items based on consumption history of similar consumers |
CN102651052A (en) * | 2012-03-29 | 2012-08-29 | 陶杰 | Intelligent combo type dish ordering method |
CN102663265A (en) * | 2012-05-04 | 2012-09-12 | 庄燕滨 | Catering service platform system based on cloud computing platform and working method thereof |
Non-Patent Citations (1)
Title |
---|
张春永等: "一种基于LBS的移动个性化推荐系统", 《科学技术与工程》 * |
Cited By (65)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110543945A (en) * | 2013-12-30 | 2019-12-06 | 华为技术有限公司 | method for processing information by intelligent agent and intelligent agent |
CN104750745A (en) * | 2013-12-30 | 2015-07-01 | 华为技术有限公司 | Agents and information processing method thereof |
US11200509B2 (en) | 2013-12-30 | 2021-12-14 | Huawei Technologies Co., Ltd. | Method for processing information by intelligent agent and intelligent agent |
CN110543945B (en) * | 2013-12-30 | 2023-05-23 | 华为技术有限公司 | Method for processing information by intelligent agent and intelligent agent |
CN107003978A (en) * | 2014-08-15 | 2017-08-01 | 西尼·尼科尔·爱普斯坦 | For by the system and computer approach of user's vision guide to current interest |
CN107003978B (en) * | 2014-08-15 | 2021-01-22 | 西尼·尼科尔·爱普斯坦 | System and computer method for visually guiding a user to a current interest |
CN105468630A (en) * | 2014-09-04 | 2016-04-06 | 口碑控股有限公司 | Method and apparatus for providing user information |
CN105469291A (en) * | 2014-09-04 | 2016-04-06 | 口碑控股有限公司 | User information providing method and device |
WO2016206026A1 (en) * | 2015-06-24 | 2016-12-29 | 程强 | Method for collecting statistics for dish-ordering information, and dish-ordering recording system |
CN105160606A (en) * | 2015-08-30 | 2015-12-16 | 安徽味唯网络科技有限公司 | Automatic food ordering method |
CN105225182A (en) * | 2015-09-07 | 2016-01-06 | 广东欧珀移动通信有限公司 | A kind of dietary recommendations continued method and device thereof |
CN105760541A (en) * | 2016-03-15 | 2016-07-13 | 传成文化传媒(上海)有限公司 | Video food ordering recommendation method and system |
CN105869079A (en) * | 2016-03-25 | 2016-08-17 | 杭州银盒宝成科技有限公司 | Dish-ordering system and method |
WO2018006726A1 (en) * | 2016-07-08 | 2018-01-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying knowledge point for which user may potentially request help |
CN107608979A (en) * | 2016-07-08 | 2018-01-19 | 阿里巴巴集团控股有限公司 | Identify the method and device of the potential knowledge point sought help of user |
TWI686750B (en) * | 2016-07-08 | 2020-03-01 | 香港商阿里巴巴集團服務有限公司 | Method and device for identifying user's potential knowledge points for help |
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 |
WO2018095307A1 (en) * | 2016-11-25 | 2018-05-31 | 口碑控股有限公司 | Method and device for releasing evaluation information |
CN106658078A (en) * | 2016-12-23 | 2017-05-10 | 北京小米移动软件有限公司 | Ordering method and device through television terminal |
CN106815745A (en) * | 2016-12-30 | 2017-06-09 | 北京三快在线科技有限公司 | Vegetable recommends method and system |
CN106886921A (en) * | 2017-02-17 | 2017-06-23 | 正源信用(北京)科技有限公司 | Personalized recommendation method based on user interest |
CN107092647A (en) * | 2017-03-10 | 2017-08-25 | 北京小度信息科技有限公司 | A kind of method and device that combination of resources is provided |
CN107092647B (en) * | 2017-03-10 | 2020-09-22 | 北京星选科技有限公司 | Method and device for providing resource combination |
US10769523B2 (en) * | 2017-04-05 | 2020-09-08 | International Business Machines Corporation | Using analytics to determine dining venue based on group preferences |
US20180293489A1 (en) * | 2017-04-05 | 2018-10-11 | International Business Machines Corporation | Determining a place where all members of a group will enjoy eating by learning the preferences of individual members and the group |
CN107391531B (en) * | 2017-04-11 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Dish recommendation method and device |
CN107391531A (en) * | 2017-04-11 | 2017-11-24 | 阿里巴巴集团控股有限公司 | A kind of vegetable recommends method and apparatus |
CN108958091A (en) * | 2017-05-25 | 2018-12-07 | 中兴通讯股份有限公司 | A kind of method and device, system automating cooking |
CN107332878B (en) * | 2017-06-05 | 2020-08-07 | 北京三快在线科技有限公司 | Information pushing method and device and electronic equipment |
CN107332878A (en) * | 2017-06-05 | 2017-11-07 | 北京三快在线科技有限公司 | Method for pushing and device, the electronic equipment of information |
CN107194746A (en) * | 2017-06-20 | 2017-09-22 | 京东方科技集团股份有限公司 | One kind dining recommends method and device |
CN107492015A (en) * | 2017-08-18 | 2017-12-19 | 无锡雅座在线科技股份有限公司 | The recommendation method and apparatus of object |
CN107682401A (en) * | 2017-09-01 | 2018-02-09 | 深圳市盛路物联通讯技术有限公司 | Information inspection method and relevant device |
CN107862542A (en) * | 2017-09-28 | 2018-03-30 | 北京三快在线科技有限公司 | A kind of vegetable recommends method and apparatus |
CN107863138A (en) * | 2017-10-31 | 2018-03-30 | 珠海格力电器股份有限公司 | Menu generating means and method |
CN107863138B (en) * | 2017-10-31 | 2023-07-14 | 珠海格力电器股份有限公司 | Menu generating device and method |
CN107942750B (en) * | 2017-11-30 | 2020-01-31 | 广东美的厨房电器制造有限公司 | Control device, control method, computer apparatus, and readable storage medium |
CN107942750A (en) * | 2017-11-30 | 2018-04-20 | 广东美的厨房电器制造有限公司 | Control device, control method, computer equipment and readable storage medium storing program for executing |
CN108304448B (en) * | 2017-12-08 | 2021-12-17 | 无锡雅座在线科技股份有限公司 | Dish recommendation method and device, storage medium and processor |
CN108304448A (en) * | 2017-12-08 | 2018-07-20 | 无锡雅座在线科技股份有限公司 | Vegetable recommends method and device, storage medium, processor |
CN109934658A (en) * | 2017-12-19 | 2019-06-25 | 阿里巴巴集团控股有限公司 | A kind of data processing method, display methods and calculate equipment |
CN108022634A (en) * | 2017-12-28 | 2018-05-11 | 中粮集团有限公司 | A kind of food preparation method and device |
CN108492213A (en) * | 2018-02-02 | 2018-09-04 | 广州视源电子科技股份有限公司 | Food materials buy the generation method and device, server apparatus, storage medium of inventory |
CN108389268A (en) * | 2018-02-07 | 2018-08-10 | 浙江莲荷科技有限公司 | Fee payment method, system and equipment |
CN108389268B (en) * | 2018-02-07 | 2021-10-19 | 浙江莲荷科技有限公司 | Payment method, system and equipment |
CN110210999A (en) * | 2018-02-28 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Catering information processing method, apparatus and system |
CN108596789A (en) * | 2018-03-29 | 2018-09-28 | 客如云科技(成都)有限责任公司 | A kind of standardized method of vegetable |
CN108596789B (en) * | 2018-03-29 | 2022-08-30 | 时时同云科技(成都)有限责任公司 | Dish standardization method |
CN108734552A (en) * | 2018-05-15 | 2018-11-02 | 浙江口碑网络技术有限公司 | User's sense of taste method for establishing model and device |
CN108897768A (en) * | 2018-05-25 | 2018-11-27 | 北京三快在线科技有限公司 | A kind of method of ordering and device, electronic equipment |
CN109300059A (en) * | 2018-09-13 | 2019-02-01 | 口口相传(北京)网络技术有限公司 | Vegetable recommended method and device |
CN109300059B (en) * | 2018-09-13 | 2020-11-17 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
CN109299123A (en) * | 2018-09-29 | 2019-02-01 | 口碑(上海)信息技术有限公司 | Vegetable feature database synchronous method and device |
CN109299123B (en) * | 2018-09-29 | 2020-11-03 | 口碑(上海)信息技术有限公司 | Dish feature library synchronization method and device |
CN109285597A (en) * | 2018-10-08 | 2019-01-29 | 北京健康有益科技有限公司 | A kind of dietotherapy recipe recommendation method, apparatus and readable medium |
CN109471973A (en) * | 2018-10-31 | 2019-03-15 | 深圳市元征科技股份有限公司 | A kind of restaurant intelligent recommendation method, apparatus, equipment and storage medium |
CN111158803B (en) * | 2018-11-07 | 2024-05-10 | 财团法人工业技术研究院 | Virtual assistant negotiation system and method thereof |
CN111158803A (en) * | 2018-11-07 | 2020-05-15 | 财团法人工业技术研究院 | Virtual assistant negotiation system and method thereof |
CN109522482A (en) * | 2018-11-13 | 2019-03-26 | Oppo广东移动通信有限公司 | Game application classification page display method, device, storage medium and terminal |
CN109522482B (en) * | 2018-11-13 | 2021-03-12 | Oppo广东移动通信有限公司 | Game application classification page display method and device, storage medium and terminal |
CN109615428A (en) * | 2018-12-10 | 2019-04-12 | 拉扎斯网络科技(上海)有限公司 | Trade company's recommended method, device, system and server |
CN109840296A (en) * | 2019-01-31 | 2019-06-04 | 珠海优特智厨科技有限公司 | A kind of method and device of determining menu composite flavor label |
CN109766364A (en) * | 2019-01-31 | 2019-05-17 | 珠海优特智厨科技有限公司 | A kind of method and device of the single taste label of determining menu |
CN111859188A (en) * | 2020-07-03 | 2020-10-30 | 美味不用等(上海)信息科技股份有限公司 | Restaurant recommendation method and system based on hierarchical analysis of large-scale matrix |
CN111859188B (en) * | 2020-07-03 | 2024-03-12 | 美之味(上海)信息技术有限公司 | Restaurant recommendation method and system based on hierarchical analysis of large-scale matrix |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103412936A (en) | Dish recommendation system based on data mining and cloud computing service | |
CN106303955B (en) | For carrying out matched method and apparatus to hotspot and POI | |
CN103559636B (en) | Restaurant management system based on cloud computing and intelligent analysis | |
CN107704586B (en) | User portrait method, device and system based on user activity address | |
AU2017232140A1 (en) | System and method for providing flavor advisement and enhancement | |
CN106056399B (en) | Information pushing method and device | |
Elahi et al. | Interaction design in a mobile food recommender system | |
CN107368483B (en) | Information recommendation method and device and server | |
KR101982240B1 (en) | Method for providing recipe service for making and sharing recipe contents | |
JP6291145B2 (en) | Information processing apparatus, information processing method, program, and storage medium | |
US9817559B2 (en) | Predictive food logging | |
CN104919481A (en) | Spotting trends by identifying influential consumers | |
KR102327845B1 (en) | Service system and method for providing subdivided food material based on user costomized recipe | |
US9064018B2 (en) | Information providing system that provides information based on strenghth of desire and current situation | |
Trattner et al. | Investigating and predicting online food recipe upload behavior | |
CN106547365A (en) | The method and apparatus of commercial product recommending | |
CN109741125A (en) | Recommend method and device, the storage medium, electronic device of vegetable | |
CN110502702A (en) | User's behavior prediction method and device | |
Tuček et al. | Forest vulnerability zones in the Czech Republic | |
CN110020152B (en) | Application recommendation method and device | |
CN109684548A (en) | A kind of data recommendation method based on user's map | |
KR20170137345A (en) | Method for providing customized recipe service | |
Zhang et al. | Improving augmented reality using recommender systems | |
CN109446206A (en) | User's dietary data update method and more new system | |
CN105681089B (en) | Networks congestion control clustering method, device and terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131127 |
|
RJ01 | Rejection of invention patent application after publication |