CN106447388A - Method and system for recommending dishes - Google Patents
Method and system for recommending dishes Download PDFInfo
- Publication number
- CN106447388A CN106447388A CN201610795995.4A CN201610795995A CN106447388A CN 106447388 A CN106447388 A CN 106447388A CN 201610795995 A CN201610795995 A CN 201610795995A CN 106447388 A CN106447388 A CN 106447388A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- score value
- user
- score
- label
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013499 data model Methods 0.000 claims abstract description 57
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 235000013311 vegetables Nutrition 0.000 claims description 393
- 230000008878 coupling Effects 0.000 claims description 76
- 238000010168 coupling process Methods 0.000 claims description 76
- 238000005859 coupling reaction Methods 0.000 claims description 76
- 230000003862 health status Effects 0.000 claims description 32
- 230000013011 mating Effects 0.000 claims description 9
- 239000000203 mixture Substances 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 2
- 235000021189 garnishes Nutrition 0.000 claims 1
- 238000003672 processing method Methods 0.000 abstract description 2
- 235000015067 sauces Nutrition 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 241000287828 Gallus gallus Species 0.000 description 6
- 238000010411 cooking Methods 0.000 description 5
- 235000015277 pork Nutrition 0.000 description 4
- 235000013555 soy sauce Nutrition 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 240000002234 Allium sativum Species 0.000 description 2
- 240000004307 Citrus medica Species 0.000 description 2
- 235000001938 Citrus medica Nutrition 0.000 description 2
- 235000002555 Citrus medica var sarcodactylis Nutrition 0.000 description 2
- 239000000571 coke Substances 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 239000000796 flavoring agent Substances 0.000 description 2
- 235000019634 flavors Nutrition 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 235000004611 garlic Nutrition 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 244000304337 Cuminum cyminum Species 0.000 description 1
- 235000007129 Cuminum cyminum Nutrition 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention is applicable to the technical field of intelligent catering, and provides a method and system for recommending dishes. The method comprises the steps of acquiring a dish label related to a user; matching the label with a dish data model, and obtaining matched dishes; performing multidimensional scoring on the matched dishes, and obtaining a recommendation total score of each matched dish; orderly outputting relevant information of the matched dishes according to the recommendation total score from high to low, and obtaining recommended dishes; and acquiring feedback information of a quality score of the user for consumed dishes and a merchant service quality score, and inputting the feedback information to the dish data model and updating the data model. According to the method for recommending the dishes provided by the invention, by using a data model processing method and a collaborative filtering recommendation algorithm, the recommended dishes not only meet the needs of users in category, and specific dishes which are more suitable for the user can be matched from user personalized information, so that dishes matching can be more humanized and accurate.
Description
Technical field
The invention belongs to intelligent technical field of catering, more particularly, to a kind of vegetable recommendation method and system.
Background technology
With growth in the living standard, increasing people selects to have dinner in dining room, hotel, or is entered using carryout service
Row is ordered and is had dinner, and with the development of network, using network reference and understanding dining room or hotel, then orders food.But to beautiful jade
Vegetable and limited vegetable storehouse information that thinkling sound meets the eye on every side, a lot of users feel embarrassed to ordering dishes it is not known that how oneself selects properly.
Existing vegetable recommends method mainly according to restaurant, the position of user, purchaser record, browsing the information such as record will
User recommended by corresponding vegetable, but the vegetable recommended is often the demand that can meet user in category, its matching degree precision
Not high also not hommization.
Content of the invention
The embodiment of the present invention aims to provide a kind of vegetable and recommends method and system, to solve vegetable recommendation side in prior art
The vegetable that method is recommended is often the demand that can meet user in category, the problem of the not high also not hommization of matching degree precision.
In order to solve above-mentioned technical problem, in a first aspect, embodiments providing a kind of vegetable to recommend method, bag
Include：
Obtain the vegetable label related to active user, described vegetable label includes described active user and defines the inputting
One vegetable label and the second vegetable label possessing the user input of similar features with described active user；
Described first vegetable label and the second vegetable label are mated with default vegetable data model respectively, is obtained
First coupling vegetable and the second coupling vegetable；
By described default vegetable data model, various dimensions scoring is carried out to described coupling vegetable, to obtain per pass institute
State the recommendation total score of coupling vegetable；
Described first coupling vegetable and the second coupling vegetable are sequentially output from high to low according to described recommendation total score respectively
The relevant information of described coupling vegetable, obtains the first kind and recommends vegetable and Equations of The Second Kind to recommend vegetable, so that described active user's root
Vegetable of recommending according to output determines the vegetable of consumption；
Gather the quality score of the vegetable to described consumption for the described active user and the feedback letter of merchant service quality score
Breath, inputs to described default vegetable data model, to be updated to described default vegetable data model.
Further, before obtaining the vegetable label related to active user, described method also includes：
Whether detection user is registered users：
If registered users, the first vegetable label and user's geographical location information that receive user definition inputs, and add
Plus user geographical position is to data model；
If non-registered users, point out user to be registered, and input user library information to data model.
Further, described second vegetable label includes：
Described second vegetable label is all dishes of the user input possessing similar features after rejecting the first vegetable label
Product label.
Described feedback storehouse information includes：The vegetable quality score information of the vegetable to consumption for all users and to business
Family's service quality score information.
Further, the composition of described data model includes：User library information, vegetable storehouse information, businessman's storehouse information and anti-
Feedback storehouse information.
Further, described various dimensions scoring is carried out to described coupling vegetable by described default vegetable data model,
Included with the recommendation total score obtaining mating vegetable described in per pass：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, businessman in the described first coupling vegetable
Service quality scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value
Calculated and sued for peace, drawn the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the second coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, disappear
Expense ability scoring score value, health status matching degree scoring score value and geographical position calculating score value are updated to collaborative filtering respectively and push away
Recommend and in algorithm, calculate corresponding score value, then plus the summation of every score value, show that total score recommended by vegetable.
Second aspect, embodiments provides a kind of dish recommendation system, including：
Acquiring unit, for obtaining the vegetable label related to active user, described vegetable label includes described current use
First vegetable label of family definition input and the second vegetable label possessing the user input of similar features with described active user；
Matching unit, for by described first vegetable label and the second vegetable label respectively with default vegetable data model
Mated, obtained the first coupling vegetable and the second coupling vegetable；
Scoring unit, for by described default vegetable data model, various dimensions scoring being carried out to described coupling vegetable,
To obtain mating the recommendation total score of vegetable described in per pass；
Recommendation unit, for recommending total score from height according to described respectively to the described first coupling vegetable and the second coupling vegetable
To the low relevant information being sequentially output described coupling vegetable, obtain the first kind and recommend vegetable and Equations of The Second Kind to recommend vegetable, so that institute
State active user and the vegetable of consumption is determined according to the vegetable of recommending of output.
Feedback unit, for gathering quality score and the merchant service quality of the vegetable to described consumption for the described active user
The feedback information of scoring, inputs to described default vegetable data model, to carry out more to described default vegetable data model
Newly.
Further, before described acquiring unit, described method also includes：
User's detector unit, for detecting whether user is registered users：
First collecting unit, if for registered users, the first vegetable label of receive user definition input and user
Geographical location information, and add user geographical position to data model；
Second collecting unit, if non-registered users, points out user to be registered, and inputs user library information to data mould
Type.
Further, described second vegetable label includes：
Described second vegetable label is all dishes of the user input possessing similar features after rejecting the first vegetable label
Product label.
Further, the composition of described data model includes：User library information, vegetable storehouse information, businessman's storehouse information and anti-
Feedback storehouse information.
Further, described scoring unit specifically for：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, businessman in the described first coupling vegetable
Service quality scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value
Calculated and sued for peace, drawn the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the second coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, disappear
Expense ability scoring score value, health status matching degree scoring score value and geographical position calculating score value are updated to collaborative filtering respectively and push away
Recommend and in algorithm, calculate corresponding score value, then plus the summation of every score value, show that total score recommended by vegetable.
In embodiments of the present invention, by the first vegetable label to active user's definition input simultaneously and current with described
User possess the second vegetable label of the user input of similar features recommendation vegetable process, and consider simultaneously tag match,
The impact of the factors such as vegetable quality, merchant service quality, consuming capacity, health status and geographical position, and disappear in user
Expense also collects the feedback information of this consumption of user after terminating, according to the feedback information input data model collected so that pushing away
The vegetable recommended is merely not only the demand meeting user in category, more can mate from user personalized information and be more suitable for user
Personal concrete vegetable is so that more humane during coupling vegetable more refine.
Brief description
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to embodiment or description of the prior art
In required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
The flowchart of method recommended by a kind of Fig. 1 vegetable provided in an embodiment of the present invention；
Fig. 2 is the style of cooking provided in an embodiment of the present invention-local tag match model schematic；
Fig. 3 is that consuming capacity provided in an embodiment of the present invention divides schematic diagram；
Fig. 4 is the detailed differentiation schematic diagram of vegetable kind provided in an embodiment of the present invention；
Fig. 5 is the computation rule of the tag match degree that user-defined label provided in an embodiment of the present invention is defined with businessman
Schematic diagram；
Fig. 6 is the matching degree computation rule of user-defined label provided in an embodiment of the present invention and the label of system definition
Schematic diagram；
Fig. 7 is vegetable quality score information provided in an embodiment of the present invention and scoring score value rule of correspondence schematic diagram；
Fig. 8 is merchant service quality score information provided in an embodiment of the present invention and scoring score value rule of correspondence schematic diagram；
Fig. 9 is that customer consumption ability rating provided in an embodiment of the present invention is shown with the partly rule of the vegetable price rule of correspondence
It is intended to；
Figure 10 is that the health status of user provided in an embodiment of the present invention is shown with the partly rule of the vegetable species rule of correspondence
It is intended to；
Figure 11 is that user geographical position provided in an embodiment of the present invention is illustrated with the merchant entities shop geographical position rule of correspondence
Figure；
Figure 12 is the preferred embodiment schematic diagram ordered of a user of invention；
Figure 13 is a kind of structured flowchart of dish recommendation system provided in an embodiment of the present invention.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right
The present invention is further described in detail.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and
It is not used in the restriction present invention.
The embodiment of the present invention obtains the vegetable label related to active user, and described vegetable label includes described active user
First vegetable label of definition input and the second vegetable label possessing the user input of similar features with described active user；Will
Described first vegetable label and the second vegetable label are mated with default vegetable data model respectively, obtain the first coupling dish
Product and the second coupling vegetable；By described default vegetable data model, various dimensions scoring is carried out to described coupling vegetable, with
To the recommendation total score mating vegetable described in per pass；To the described first coupling vegetable and the second coupling vegetable respectively according to described recommendation
Total score is sequentially output the relevant information of described coupling vegetable from high to low, obtains the first kind and recommends vegetable and Equations of The Second Kind to recommend dish
Product, so that described active user determines the vegetable of consumption according to the vegetable of recommending of output；Gather described active user to disappear to described
The quality score of the vegetable taking and the feedback information of merchant service quality score, input to described default vegetable data model,
To be updated to described default vegetable data model.
Fig. 1 shows that the flowchart of method recommended by a kind of vegetable provided in an embodiment of the present invention, and details are as follows：
In S101, obtain the vegetable label related to active user, it is fixed that described vegetable label includes described active user
First vegetable label of justice input and the second vegetable label possessing the user input of similar features with described active user.
Before the vegetable label that described acquisition is related to active user, including：
Whether detection user is registered users：
If registered users, the first vegetable label and user's geographical location information that receive user definition inputs, and add
Plus user geographical position is to data model；
If non-registered users, point out user to be registered, and input user library information to data model.
If described registered users, when the label of input definition is with user's geographical location information：If not inputting geographical position
Put, be not then used geographical position to recommend the reference score value of vegetable as this；
Described non-registered users, after the completion of having inputted information registering, need not log in and can directly input the demand of ordering and ground
Reason position.
First vegetable label of described front user's definition input, refers to：
Oneself commodity interested can be indicated, such as by the label of definition during user input：Light, chop, tide
State, user can define one or more labels simultaneously.Accuracy rate during coupling can be strengthened so that recommending by the label of definition
Result be more suitable for individual subscriber, more hommization.
In S102, described first vegetable label and the second vegetable label are entered by root respectively with default vegetable data model
Row coupling, obtains the first coupling vegetable and the second coupling vegetable.
Described first vegetable label and the second vegetable label are carried out by described piece respectively with default vegetable data model
Also include before joining：Label between setting between tag match model and businessman and the user between vegetable and user
Matching Model, sets corresponding match index relation.
Described Matching Model and match index refer to：Related vegetable is mated with the label in user, such as the style of cooking-family
Township and vegetable-taste, and enter row index formulation by both actual match degree, such as Guangdong dishes come for the user that local is Guangzhou
Say, match index highest, and for the Chengdu of local, match index is minimum, by that analogy.As shown in Fig. 2 being the present invention
The style of cooking-local tag match model schematic that embodiment provides.Closed using the tag match setting between vegetable and user
Tag match model between system and businessman and user and match index carry out vegetable screening, choose match index
Big vegetable is as recommendation vegetable.
In S103, by described default vegetable data model, various dimensions scoring is carried out to described coupling vegetable, with
To the recommendation total score mating vegetable described in per pass.
For first coupling vegetable, from tag match, vegetable quality, merchant service quality, consuming capacity, health status with
And the various dimensions factor angle such as geographical position, go to calculate adjustment and recommend the vegetable of vegetable to recommend total score.
For second coupling vegetable from tag match, vegetable quality, merchant service quality, consuming capacity, health status with
And the various dimensions factor angle such as geographical position, go to calculate every score value that vegetable is recommended in adjustment；
Using Collaborative Filtering Recommendation Algorithm, the every score value recommending vegetable is converted and sued for peace, shown that vegetable is recommended total
Point.
In S104, total score is recommended from high to low according to described respectively to the described first coupling vegetable and the second coupling vegetable
It is sequentially output the relevant information of described coupling vegetable, obtain the first kind and recommend vegetable and Equations of The Second Kind to recommend vegetable, so that described work as
Front user determines the vegetable of consumption according to the vegetable of recommending of output.
The described first kind recommends vegetable to refer to the vegetable Query Result obtaining for the label of user input, and Equations of The Second Kind is recommended
Vegetable refers to and pushes the vegetable result that user may like.Part I content is directed to the label of user's definition input
Carry out processing, and the content of Part II then cannot immediately arrive at, the present invention using to described active user possess similar
Second vegetable label of the user input of feature carries out data processing and draws.
Described offer recommends vegetable can also be pushed to user in modes such as mail or wechat, needs the user of this service to need
Additionally fill in the contact methods such as its mail or wechat in registration.
In S104, gather quality score and the merchant service quality score of the vegetable to described consumption for the described active user
Feedback information, input to described default vegetable data model, to be updated to described default vegetable data model.
This consumption of described user refers to the feedback information of vegetable quality score and merchant service quality score：In consumption
At the end of, may require that vegetable that user consumes to this and merchant service carry out Star rating.
Described by feedback information input data model so that data model feeds back the consumption that storehouse information can follow user in real time
And update.
Further, described second vegetable label：
Described second vegetable label is all dishes of the user input possessing similar features after rejecting the first vegetable label
Product label.
Described second vegetable label：Choose the part similar users most like with information in user library information, concrete selection
How many similar users, can be determined according to the actual requirements.The second described vegetable label refers to all for similar users marks
The vegetable label recorded a demerit all proposes, and after rejecting all vegetable labels of the marked mistake of wherein active user, remaining dish
Product label.
Further, the composition of described data model includes：User library information, vegetable storehouse information, businessman's storehouse information and anti-
Feedback storehouse information；
Described user library information specifically includes user's：Local, taste, age, position, city, income, health status letter
The essential informations such as breath, geographical position, and the label extracting from essential information, such as light, consuming capacity is high-end, three
Height, Shenzhen Huaqiang north etc.；
In described user library information, essential information is by user's input in registration, but geography information is user when ordering
Real-time geographical locations operation it is allowed to user modifies manually.Described label information is to enter process by essential information to extract
Out, as the extraction of consuming capacity needs to refer to the information such as position, city and the income of user, build consuming capacity model,
Thus consuming capacity is carried out with high-end, middle and high end, middle-end, low and middle-end, the division of low side, as shown in Figure 3.
Described vegetable storehouse information specifically includes every each vegetable：The style of cooking, cooking methods, vegetable detailed catalogue, taste, etc. basic believe
Breath, and the label extracting from essential information, such as Guangdong dishes, Sichuan cuisine, braised in soy sauce, fried, spicy, spiced, deep-fried chicken, Buddha's hand
Chop etc.；
Described vegetable storehouse information, by following 4 dimensions, is classified to vegetable label：
1) big class-style of cooking：As Suxi Cuisine Sichuan cuisine, Guangdong dishes, Jiangsu cuisine and Shandong cuisine；
2) class-cooking methods in：As decocted, frying, explode, braise in soy sauce, boil, steam, roast；
3) group-taste：As sour-sweet peppery, salty fragrant, bitter fresh, curried, spicy, cumin, light etc.；
4) vegetable detailed catalogue：Detailed differentiation to vegetable kind, including menu name, such as deep-fried chicken.As shown in Figure 4.
Described businessman storehouse information includes：Solid shop/brick and mortar store better address information and location tags, to this businessman all vegetables label
Definition, such as label is defined to Buddha's hand chop：Guangdong dishes, boil, light.
Dish information in described businessman storehouse information, be by businessman when added is carried out to vegetable input to data model
, for the vegetable feature of clearly sale, vegetable is added to carry out vegetable tag definition simultaneously carrying out for businessman, and merchant entities shop
Better address information and location tags are then to carry out first inputting to Mathematical Modeling when vegetable is added by businessman.
Described feedback storehouse information includes：The vegetable quality score information of the vegetable to consumption for all users and to business
Family's service quality score information.
Further, described various dimensions scoring is carried out to described coupling vegetable by described default vegetable data model,
Included with the recommendation total score obtaining mating vegetable described in per pass：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, businessman in the described first coupling vegetable
Service quality scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value
Calculated and sued for peace, drawn the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the second coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, disappear
Expense ability scoring score value, health status matching degree scoring score value and geographical position calculating score value are updated to collaborative filtering respectively and push away
Recommend and in algorithm, calculate corresponding score value, then plus the summation of every score value, show that total score recommended by vegetable.
Each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the described vegetable to recommendation
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate and sue for peace, draw the recommendation total score recommending each vegetable in vegetable, comprise the following steps that：
1st, the computation rule of the tag match degree of the label according to user's definition concern and businessman's definition, user-defined mark
Sign the matching degree computation rule calculating tag match score value with the label of system definition；
2nd, the vegetable quality score of all feedbacks is carried out with statistical computation average, according to vegetable quality score information and scoring
The score value rule of correspondence obtains recommending vegetable corresponding vegetable quality score score value；
3rd, the service quality score information of all feedbacks is carried out with statistical computation average, believed according to merchant service quality score
Breath obtains recommending vegetable corresponding merchant service quality score score value with the scoring score value rule of correspondence；
4th, according to customer consumption ability rating and the vegetable price rule of correspondence, whether the vegetable price of inquiry falls user's
In the range of the normal distribution of consuming capacity, and obtain recommending vegetable corresponding customer consumption ability scoring score value；
5th, the health status according to user and the vegetable species rule of correspondence, inquiry vegetable is if appropriate for active user's body shape
Condition, and obtain recommending vegetable corresponding health status matching degree scoring score value；
6th, according to user geographical position and the merchant entities shop geographical position rule of correspondence, optimize and recommend vegetable order.By away from
Distance from user current location to calculate score value.From user more close to, score value is bigger, obtain geographical position calculate score value.This step
Suddenly it is optional step, user can independently choose whether to add this with reference to score value；
7th, to the recommendation corresponding above-mentioned tag match score value of each vegetable of vegetable kind, vegetable quality score score value, businessman's clothes
Business quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and enter
Row summation, show that total score recommended by vegetable；
The label of described user's definition concern and the computation rule of tag match degree of businessman's definition, user-defined label
With the matching degree computation rule of label of system definition, vegetable quality score information and the scoring score value rule of correspondence with, businessman's clothes
Business quality score information and the scoring score value rule of correspondence and user geographical position are divided with the merchant entities shop geographical position rule of correspondence
Dui Ying not schematic diagram as shown in Fig. 5-8, Figure 11.
The health status of described customer consumption ability rating and the vegetable price rule of correspondence and user and vegetable species pair
Should illustrate to correspond to respectively Fig. 9, Figure 10 by the partly regular of rule.
Described mates each vegetable corresponding tag match score value, vegetable quality score score value, business in vegetable to second
Family's service quality scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculating point
Value is calculated, as Computational Methods above.
Described Collaborative Filtering Recommendation Algorithm:Firstly the need of finding out the K user most like with targeted customer u, with set S
(u, K) represents, the vegetable of marked for user in S this label of mistake all extracted, and removes u this label labeled
Vegetable.For each candidate vegetable i, user u degree equation below interested in it calculates：
Wherein rviRepresent that user v likes degree to i.
Based on the corresponding embodiment of Figure 12, it is the preferred embodiment that a user of the present invention orders, details are as follows：
This user king five is registered users, when ordering, inputs the food label that it wants to eat, such as spareribs with brown sauce, cola
Chop；According to the label spareribs with brown sauce of king five input definition, carry out the coupling screening of vegetable, obtain recommending vegetable：Braised in soy sauce
Chop, laughable chop, sweet and sour spareribs, Mulse pork ribs, deep fried spareribs with garlic flavour, spicy chop etc.；Tieed up according to health status, geographical position etc.
Degree factor, calculates the recommendation total score of each vegetable；According in user library with king five people of five similarity highests, extract the second dish
Product label is corresponding to recommend vegetable：Pork braised in brown sauce, coke chicken wing, Braised chicken in brown sauce, stewed fish with brown sauce etc.；Further according to health status, geographical position etc.
Dimension factor, calculates the corresponding recommendation total score recommending vegetable of the second vegetable label；Two are recommended vegetable respectively in accordance with recommendation
Total score sorts from high to low, show that the final first kind recommends vegetable：Spareribs with brown sauce, laughable chop, spicy chop, Mulse pork ribs
Sweet and sour spareribs, deep fried spareribs with garlic flavour etc., Equations of The Second Kind recommends vegetable：Pork braised in brown sauce, Braised chicken in brown sauce, stewed fish with brown sauce, coke chicken wing etc., export described two
Class recommends the relevant information of vegetable and vegetable；Consumption terminates rear king five and the vegetable quality of final consumption and merchant service need to be carried out
Scoring.
In a preferred embodiment of the invention, from two sides of the second vegetable label of user-defined label and similar users
To setting out, obtain the vegetable Query Result being respectively directed to that the definition label of user input obtains respectively, and push user can
The vegetable result that can like, and when using default two kinds of labels of disposal methods, taken into full account tag match, vegetable
The various dimensions factors such as quality, merchant service quality, consuming capacity, health status matching degree and geographical position, from various dimensions pair
Default processing method is corrected, and collects the feedback information of consumption every time, and dynamic corrections data model is so that recommend vegetable
Matching degree precision is greatly improved and more recommends to hommization the vegetable that user is suitable for its people.
Personal identification method described in corresponding foregoing embodiments, Figure 13 shows a kind of vegetable provided in an embodiment of the present invention
The structured flowchart of commending system.
With reference to Figure 13, this system includes：
Acquiring unit 131, for obtaining the vegetable label related to active user, described vegetable label includes described current
First vegetable label of user's definition input and the second vegetable mark possessing the user input of similar features with described active user
Sign；
Matching unit 132, for by described first vegetable label and the second vegetable label respectively with default vegetable data
Model is mated, and obtains the first coupling vegetable and the second coupling vegetable；
Scoring unit 133, for by described default vegetable data model, carrying out various dimensions to described coupling vegetable and commenting
Point, to obtain mating the recommendation total score of vegetable described in per pass；
Recommendation unit 134, for mating vegetable respectively according to described recommendation total score to the described first coupling vegetable and second
It is sequentially output the relevant information of described coupling vegetable from high to low, obtain the first kind and recommend vegetable and Equations of The Second Kind to recommend vegetable, with
Described active user is made to determine the vegetable of consumption according to the vegetable of recommending of output.
Feedback unit 135, for gathering quality score and the merchant service of the vegetable to described consumption for the described active user
The feedback information of quality score, inputs to described default vegetable data model, to enter to described default vegetable data model
Row updates.
Further, before acquiring unit 131, described method also includes：
User's detector unit, for detecting whether user is registered users：
First collecting unit, if for registered users, the first vegetable label of receive user definition input and user
Geographical location information, and add user geographical position to data model；
Second collecting unit, if non-registered users, points out user to be registered, and inputs user library information to data mould
Type.
Further, the second vegetable label includes：
Described second label is all vegetable marks of the user input possessing similar features after rejecting the first vegetable label
Sign.
Further, the composition of described data model includes：User library information, vegetable storehouse information, businessman's storehouse information and anti-
Feedback storehouse information；
Further, described scoring unit specifically for：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, businessman in the described first coupling vegetable
Service quality scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value
Calculated and sued for peace, drawn the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the second coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, disappear
Expense ability scoring score value, health status matching degree scoring score value and geographical position calculating score value are updated to collaborative filtering respectively and push away
Recommend and in algorithm, calculate corresponding score value, then plus the summation of every score value, show that total score recommended by vegetable.
Embodiment described above is only used for, so that technical scheme to be described, being not intended to limit；Although with reference to front
State embodiment the present invention has been described in detail, it will be understood by those within the art that：It still can be to front
State the technical scheme described in each embodiment to modify, or equivalent is carried out to wherein some technical characteristics；And these are repaiied
Change or replace, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme, all should
It is included within protection scope of the present invention.
Claims (10)
1. a kind of vegetable recommends method it is characterised in that including：
Obtain the vegetable label related to active user, described vegetable label includes the first dish of described active user's definition input
Product label and the second vegetable label possessing the user input of similar features with described active user；
Described first vegetable label and the second vegetable label are mated with default vegetable data model respectively, is obtained first
Coupling vegetable and the second coupling vegetable；
By described default vegetable data model, various dimensions scoring is carried out to described coupling vegetable, to obtain described in per pass
The recommendation total score of garnishes product；
Described first coupling vegetable and the second coupling vegetable are sequentially output respectively from high to low described according to described recommendation total score
The relevant information of coupling vegetable, obtains the first kind and recommends vegetable and Equations of The Second Kind to recommend vegetable, so that described active user is according to defeated
The vegetable of recommending going out determines the vegetable of consumption；
Gather the quality score of the vegetable to described consumption for the described active user and the feedback information of merchant service quality score, defeated
Enter to described default vegetable data model, to be updated to described default vegetable data model.
2. the method for claim 1 is it is characterised in that before obtaining the vegetable label related to active user, institute
The method stated also includes：
Whether detection user is registered users：
If registered users, the first vegetable label and user's geographical location information that receive user definition inputs, and add use
Family geographical position is to data model；
If non-registered users, point out user to be registered, and input user library information to data model.
3. the method for claim 1 it is characterised in that described second vegetable label be reject the first vegetable label after
Possess all vegetable labels of the user input of similar features.
4. the method for claim 1 is it is characterised in that the composition of described data model includes：User library information, vegetable
Storehouse information, businessman's storehouse information and feedback storehouse information.
5. the method for claim 1 it is characterised in that described by described default vegetable data model, to described
Coupling vegetable carries out various dimensions scoring, is included with the recommendation total score obtaining mating vegetable described in per pass：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the described first coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate and sue for peace, draw the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service quality in the second coupling vegetable
Scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and are calculated；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, consumption energy
Power scoring score value, health status matching degree scoring score value and geographical position calculate score value and are updated to collaborative filtering recommending calculation respectively
Calculate corresponding score value in method, then plus the summation of every score value, show that total score recommended by vegetable.
6. a kind of dish recommendation system is it is characterised in that include：
Acquiring unit, for obtaining the vegetable label related to active user, it is fixed that described vegetable label includes described active user
First vegetable label of justice input and the second vegetable label possessing the user input of similar features with described active user；
Matching unit, for carrying out described first vegetable label and the second vegetable label respectively with default vegetable data model
Coupling, obtains the first coupling vegetable and the second coupling vegetable；
Scoring unit, for by described default vegetable data model, various dimensions scoring being carried out to described coupling vegetable, with
To the recommendation total score mating vegetable described in per pass；
Recommendation unit, for recommending total score from high to low according to described respectively to the described first coupling vegetable and the second coupling vegetable
It is sequentially output the relevant information of described coupling vegetable, obtain the first kind and recommend vegetable and Equations of The Second Kind to recommend vegetable, so that described work as
Front user determines the vegetable of consumption according to the vegetable of recommending of output.
Feedback unit, for gathering quality score and the merchant service quality score of the vegetable to described consumption for the described active user
Feedback information, input to described default vegetable data model, to be updated to described default vegetable data model.
7. system as claimed in claim 6 is it is characterised in that described system also includes：
User's detector unit, for detecting whether user is registered users：
First collecting unit, if for registered users, the first vegetable label of receive user definition input is geographical with user
Positional information, and add user geographical position to data model；
Second collecting unit, if non-registered users, points out user to be registered, and inputs user library information to data model.
8. system as claimed in claim 6 it is characterised in that described second vegetable label be reject the first vegetable label after
Possess all vegetable labels of the user input of similar features.
9. system as claimed in claim 6 is it is characterised in that the composition of described data model includes：User library information, vegetable
Storehouse information, businessman's storehouse information and feedback storehouse information.
10. system as claimed in claim 6 it is characterised in that described scoring unit specifically for：
When for the described first coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service in the described first coupling vegetable
Quality score score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and carry out
Calculate and sue for peace, draw the recommendation total score recommending each vegetable in vegetable；
When for the second coupling vegetable：
To each vegetable corresponding tag match score value, vegetable quality score score value, merchant service quality in the second coupling vegetable
Scoring score value, consuming capacity scoring score value, health status matching degree scoring score value and geographical position calculate score value and are calculated；
By corresponding for each vegetable tag match score value, vegetable quality score score value, merchant service quality score score value, consumption energy
Power scoring score value, health status matching degree scoring score value and geographical position calculate score value and are updated to collaborative filtering recommending calculation respectively
Calculate corresponding score value in method, then plus the summation of every score value, show that total score recommended by vegetable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610795995.4A CN106447388A (en) | 2016-08-31 | 2016-08-31 | Method and system for recommending dishes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610795995.4A CN106447388A (en) | 2016-08-31 | 2016-08-31 | Method and system for recommending dishes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447388A true CN106447388A (en) | 2017-02-22 |
Family
ID=58165384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610795995.4A Pending CN106447388A (en) | 2016-08-31 | 2016-08-31 | Method and system for recommending dishes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447388A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016567A (en) * | 2017-03-09 | 2017-08-04 | 成都视达科信息技术有限公司 | A kind of food and drink resource recommendation method and system based on Video Applications |
| 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 |
| 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 |
| CN107731281A (en) * | 2017-11-06 | 2018-02-23 | 北京戴纳实验科技有限公司 | A kind of method for recommending dining |
| 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 |
| 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 |
| CN108416628A (en) * | 2018-03-15 | 2018-08-17 | 重庆大学 | A kind of dining room vegetable intelligent recommendation system of the fusion more relations on attributes of food |
| CN108416705A (en) * | 2018-04-28 | 2018-08-17 | 广西宜州市联森网络科技有限公司 | A kind of intelligent menuing system |
| CN108491377A (en) * | 2018-03-06 | 2018-09-04 | 中国计量大学 | A kind of electric business product comprehensive score method based on multi-dimension information fusion |
| 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 |
| CN108805653A (en) * | 2018-04-28 | 2018-11-13 | 广西宜州市联森网络科技有限公司 | A kind of formula order dishes system |
| CN109299360A (en) * | 2018-09-21 | 2019-02-01 | 昆明理工大学 | A kind of method that vegetable is recommended |
| 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 |
| CN109829111A (en) * | 2019-01-30 | 2019-05-31 | 珠海优特智厨科技有限公司 | The method and apparatus that the production of user's taste label and menu are recommended |
| CN110490768A (en) * | 2019-07-05 | 2019-11-22 | 浙江口碑网络技术有限公司 | Processing method, device and its system for information of ordering |
| CN110544160A (en) * | 2019-09-09 | 2019-12-06 | 中山职业技术学院 | Dish recommending method |
| CN111007744A (en) * | 2019-12-23 | 2020-04-14 | 普琅德智能装备科技(江苏)有限公司 | Automatic cooking system |
| CN111738809A (en) * | 2020-07-31 | 2020-10-02 | 浙江口碑网络技术有限公司 | Dish information pushing method and device, storage medium and computer equipment |
| CN112016582A (en) * | 2019-05-31 | 2020-12-01 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
| CN112288532A (en) * | 2020-10-30 | 2021-01-29 | 广州富港万嘉智能科技有限公司 | Dish ordering method, computer-readable storage medium, server and intelligent dish ordering system |
| CN115699069A (en) * | 2020-06-19 | 2023-02-03 | 松下知识产权经营株式会社 | Information providing method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398805A (en) * | 2007-09-27 | 2009-04-01 | 王娅然 | Electronic dish ordering system with intelligent recommendation function |
| US20110208617A1 (en) * | 2010-02-19 | 2011-08-25 | Chris Weiland | System and method for locality and user preference based food recommendations |
| CN102542490A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Commodity recommendation method based on model matching |
| CN103345699A (en) * | 2013-07-10 | 2013-10-09 | 湖南大学 | Personalized food recommendation method based on commodity forest system |
-
2016
- 2016-08-31 CN CN201610795995.4A patent/CN106447388A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398805A (en) * | 2007-09-27 | 2009-04-01 | 王娅然 | Electronic dish ordering system with intelligent recommendation function |
| US20110208617A1 (en) * | 2010-02-19 | 2011-08-25 | Chris Weiland | System and method for locality and user preference based food recommendations |
| CN102542490A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Commodity recommendation method based on model matching |
| CN103345699A (en) * | 2013-07-10 | 2013-10-09 | 湖南大学 | Personalized food recommendation method based on commodity forest system |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016567A (en) * | 2017-03-09 | 2017-08-04 | 成都视达科信息技术有限公司 | A kind of food and drink resource recommendation method and system based on Video Applications |
| 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 |
| 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 |
| CN107731281A (en) * | 2017-11-06 | 2018-02-23 | 北京戴纳实验科技有限公司 | A kind of method for recommending dining |
| 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 |
| 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 |
| 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 |
| CN108491377B (en) * | 2018-03-06 | 2021-10-08 | 中国计量大学 | E-commerce product comprehensive scoring method based on multi-dimensional information fusion |
| CN108491377A (en) * | 2018-03-06 | 2018-09-04 | 中国计量大学 | A kind of electric business product comprehensive score method based on multi-dimension information fusion |
| CN108416628A (en) * | 2018-03-15 | 2018-08-17 | 重庆大学 | A kind of dining room vegetable intelligent recommendation system of the fusion more relations on attributes of food |
| CN108416628B (en) * | 2018-03-15 | 2020-07-07 | 重庆大学 | Restaurant dish intelligent recommendation system integrating food multi-attribute relationship |
| CN108805653A (en) * | 2018-04-28 | 2018-11-13 | 广西宜州市联森网络科技有限公司 | A kind of formula order dishes system |
| CN108416705A (en) * | 2018-04-28 | 2018-08-17 | 广西宜州市联森网络科技有限公司 | A kind of intelligent menuing system |
| 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 |
| CN109299360B (en) * | 2018-09-21 | 2021-10-22 | 昆明理工大学 | Dish recommending method |
| CN109299360A (en) * | 2018-09-21 | 2019-02-01 | 昆明理工大学 | A kind of method that vegetable is recommended |
| 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 |
| CN109829111A (en) * | 2019-01-30 | 2019-05-31 | 珠海优特智厨科技有限公司 | The method and apparatus that the production of user's taste label and menu are recommended |
| CN112016582B (en) * | 2019-05-31 | 2023-11-24 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
| CN112016582A (en) * | 2019-05-31 | 2020-12-01 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
| CN110490768A (en) * | 2019-07-05 | 2019-11-22 | 浙江口碑网络技术有限公司 | Processing method, device and its system for information of ordering |
| CN110544160A (en) * | 2019-09-09 | 2019-12-06 | 中山职业技术学院 | Dish recommending method |
| CN111007744A (en) * | 2019-12-23 | 2020-04-14 | 普琅德智能装备科技(江苏)有限公司 | Automatic cooking system |
| CN111007744B (en) * | 2019-12-23 | 2023-05-12 | 普琅德智能装备科技(江苏)有限公司 | Automatic cooking system |
| CN115699069A (en) * | 2020-06-19 | 2023-02-03 | 松下知识产权经营株式会社 | Information providing method |
| CN111738809A (en) * | 2020-07-31 | 2020-10-02 | 浙江口碑网络技术有限公司 | Dish information pushing method and device, storage medium and computer equipment |
| CN112288532A (en) * | 2020-10-30 | 2021-01-29 | 广州富港万嘉智能科技有限公司 | Dish ordering method, computer-readable storage medium, server and intelligent dish ordering system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106447388A (en) | Method and system for recommending dishes | |
| CN103559636B (en) | Restaurant management system based on cloud computing and intelligent analysis | |
| CN103246980B (en) | Information output method and server | |
| CN102254043B (en) | Semantic mapping-based clothing image retrieving method | |
| CN101697162B (en) | Method and system for intelligently recommending ordering dishes | |
| CN107391531B (en) | Dish recommendation method and device | |
| WO2019056661A1 (en) | Search term pushing method and device, and terminal | |
| CN103489008B (en) | Image product information extracting method and device | |
| CN106408377A (en) | Shopping recommended method and system | |
| CN111400507B (en) | Entity matching method and device | |
| CN105608650A (en) | Dish collocation recommending method and system | |
| CN106649383A (en) | Clothes management method and system | |
| CN103858142A (en) | Store information provision system | |
| CN105844357A (en) | Dish combination recommending method and dish combination recommending system based on required heat | |
| CN105631722A (en) | Service information push method, service information push system and terminal | |
| CN106548006A (en) | A kind of meals based on user's typical case's taste recommend method | |
| CN104112217A (en) | Taste selection information marking method and application method | |
| CN110956508A (en) | Big data management method and big data management system | |
| CN108876930A (en) | A kind of personal image management application method and system | |
| CN107220334A (en) | Similarity calculating method, device and the equipment of name of firm | |
| CN104991908B (en) | A kind of identifying processing method and device of target item | |
| CN110264301A (en) | Recommended method, device, electronic equipment and non-volatile memory medium | |
| CN110287410A (en) | The fusion method of a variety of proposed algorithms of user under a kind of O2O electric business scene | |
| CN111597434B (en) | Takeout recommendation method, system, device and medium based on user portrait | |
| CN109615466A (en) | The mixed method of commending contents and collaborative filtering recommending towards mobile ordering system |
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: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |