CN109299360A - A kind of method that vegetable is recommended - Google Patents
A kind of method that vegetable is recommended Download PDFInfo
- Publication number
- CN109299360A CN109299360A CN201811104765.4A CN201811104765A CN109299360A CN 109299360 A CN109299360 A CN 109299360A CN 201811104765 A CN201811104765 A CN 201811104765A CN 109299360 A CN109299360 A CN 109299360A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- similarity
- characteristic value
- user
- standard
- 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.)
- Granted
Links
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 125
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 3
- 239000013598 vector Substances 0.000 claims description 24
- 239000012141 concentrate Substances 0.000 claims description 7
- 235000013305 food Nutrition 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 235000015277 pork Nutrition 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 239000000052 vinegar Substances 0.000 description 2
- 235000021419 vinegar Nutrition 0.000 description 2
- CZMRCDWAGMRECN-UGDNZRGBSA-N Sucrose Chemical compound O[C@H]1[C@H](O)[C@@H](CO)O[C@@]1(CO)O[C@@H]1[C@H](O)[C@@H](O)[C@H](O)[C@@H](CO)O1 CZMRCDWAGMRECN-UGDNZRGBSA-N 0.000 description 1
- 229930006000 Sucrose Natural products 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000005720 sucrose 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
- 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)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to a kind of vegetable recommended methods, belong to network technique field.The method comprise the steps that obtaining the vegetable that vegetable is concentrated;Obtain the local and permanent residence of user;The vegetable similarity between vegetable concentrated according to the common vegetable and vegetable of user residence obtains recommending vegetable catalogue, and affiliated vegetable similarity is the vegetable attribute difference measurement being calculated according to vegetable self attributes;Using the vegetable in obtained similar menu of ordering dishes as recommendation vegetable.The present invention user can not have history to order dishes when recording to recommend the vegetable for being more conform with user's taste out for user again yet.Compared with prior art, the present invention mainly solving the problems, such as that its taste vegetable can not be met if client is without record of making a reservation for its recommendation, make network meal-ordering more friendly for new user.
Description
Technical field
The present invention relates to a kind of vegetable recommended methods, belong to network technique field.
Background technique
In industry of ordering on the net at present, recommends vegetable to user, be a kind of recurrent behavior.But many feelings
Under condition, the recommendation vegetable of website is often the fast-selling dish of a period of time, and making a reservation on the net perhaps has the recommendation of some vegetables sometimes and be
According to the history of customer orders record and generates, for the user that orders for the first time but without what good recommended method.And
Fast-selling dish or the high dish that scores often do not meet user's taste again.
Summary of the invention
In view of this, the present invention provides a kind of vegetable recommended method, to improve the reasonability of vegetable recommendation.The present invention passes through
According to the similarity between vegetable, vegetable similar with user local vegetable attribute is found, and generate recommendation menu, carries out vegetable
Recommend.Compared with prior art, the present invention its mouth can not be met if client is without record of making a reservation for its recommendation by mainly solving
The problem of taste vegetable, makes network meal-ordering more friendly for new user.
The technical solution adopted by the present invention is that: a kind of vegetable recommended method includes the following steps:
Step1, according to user local location, calculate the feature vector, X of the standard vegetable in arean, wherein each
Characteristic value is respectively X1, X2, X3, X4, X5, X6.........;
The vegetable feature vector, specifically: vector composed by the vegetable characteristic value;
Xn={ X1, X2, X3, X4, X5, X6}
The characteristic value of each vegetable, specifically: the criterion and quantity of each specific object of every course;
The regional standard vegetable characteristic value, specifically: this area's user's history is ordered in record, the feature of all vegetables
The arithmetic average of value;
Step2, the standard vegetable feature vector according to user local location, calculate standard vegetable and vegetable concentrates dish
Similarity in product, the vegetable similarity are the vegetable attribute difference measurements being calculated according to vegetable self attributes;
Step3, by the vegetable in the similar menu of ordering dishes, as recommending vegetable.
Specifically, specific step is as follows by the step1:
Step1.1, according to user local location, obtain the record of ordering dishes of the regional other users in user local;
Step1.2, the record of ordering dishes according to other users extract the characteristic value of every course in record, wherein every course
Feature vector be Xmn, each characteristic value of every course is respectively Xm1, Xm2, Xm3, Xm4, Xm5, Xm6... ..., wherein m=1,
2,3 ... ... M, M order dishes for location and record the quantity of all vegetables;
Xmn={ Xm1, Xm2, Xm3, Xm4, Xm5, Xm6}
Step1.3, the average value for calculating each characteristic value, obtain the feature vector, X of a standard vegetable latern, wherein
Each characteristic value average value is respectively X1, X2, X3, X4, X5, X6... ..., M orders dishes for location and records all vegetables
Quantity;
Specifically, specific step is as follows by the step2:
Step2.1, the characteristic value that vegetable concentrates all vegetables is extracted, obtains the feature vector Y of per pass vegetable in menum,
Wherein each characteristic value is respectively Ym1, Ym2, Ym3, Ym4, Ym5, Ym6... ... wherein m=1,2,3 ... ... N, N are dish
The quantity of all vegetables in list;
Yn={ Ym1, Ym2, Ym3, Ym4, Ym5, Ym6}
Step2.2, this feature vector and the cosine value (cos θ) of this regional standard vegetable feature vector are calculated, then
The similarity of each dish and standard dish in available menu, this value indicate that the similarity between two vegetables, this value are got over
Illustrate that similarity is higher greatly;
Specifically, the vegetable in the Step3 in similar menu, specifically: the standard vegetable and vegetable collection in the area
Highest preceding ten vegetables of similarity in middle vegetable.
The beneficial effects of the present invention are: the present invention is by according to the similarity between vegetable, finding and user local vegetable
The similar vegetable of attribute, and recommendation menu is generated, carry out vegetable recommendation.Compared with prior art, the present invention mainly solve as
The problem of fruit client just can not meet its taste vegetable without record of making a reservation for its recommendation, make network meal-ordering more friendly for new user
It is good.
Detailed description of the invention
Fig. 1 is general flow chart of the present invention;
Fig. 2 is regional feature value figure of the present invention;
Fig. 3 is the obtaining step of regional standard vegetable feature vector.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the present invention is further illustrated.
Embodiment 1: as shown in Figure 1-3, the present invention provides a kind of vegetable recommended method, this method can be applied to customer
Vegetable when can order is recommended.Such as assume a site of ordering, inside there are multiple businessmans, each businessman also provides many differences
Vegetable, these all vegetables can be known as a vegetable collection.When there are registered users to order on the net, can be pushed away to customer
Recommend the vegetable of suitable customer's taste.
Step 1 is one by one sorted out the different characteristic attribute of each vegetable and is extracted
Table 1 is certain vegetable list of feature values
Step 2, quantify
Sugariness quantization, definition
With sugariness of 10% aqueous sucrose solution at 20 DEG C for 1.0, sugarinesses of other sugar then obtain in comparison.By
It is opposite in this sugariness, compares sugariness so being also known as.
Food materials type is classified according to Altitude Regions, and using Beijing's height above sea level as standard height above sea level 1.0, other food materials come
From regional height above sea level compare to obtain quantized value, such as Fig. 2 therewith.
Salt metrization, definition
Salinity when 2 grams of salt are added in 500 grams of vegetables is 1.0.
Peppery metrization, definition
The peppery unit used of spending is Shi Gaoweier unit (Scoville Units), every 1000 Shi Gaoweier unit
The peppery degree of (Scoville Units) is 1 quantization.
Ripe degree, definition
Well done food is 1.0.
Step 3 classifies in area by province.
The history for extracting each regional user is ordered record, and the arithmetic of the characteristic value of vegetable in these historical records is calculated
Average value.
Arithmetic mean is taken, the standard vegetable list of feature values in each area, such as Fig. 3 are made.
Thus the standard vegetable feature vector in each area is obtained.
Step 4 is sorted out user's taste by area according to registration the filled out local of user, chooses the standard vegetable of this area.
Step 5, the similarity based method for calculating vegetable and user's regional standard vegetable are as follows:
The feature value vector of its Plays vegetable are as follows:
(X1, X2, X3, X4, X5, X6)
And vegetable concentrates vegetable feature value vector are as follows:
(Y1, Y2, Y3, Y4, Y5, Y6)
So they press from both sides cosine of an angle and are equal to:
Since each variable is positive number in vector, cosine value is between zero and one, that is to say, that angle is at 0 degree
To between 90 degree.When two vegetable vectorial angle cosines are equal to 1, the angle of the two vectors is zero, and two vegetables are complete
It is identical;So cosine is smaller, angle is bigger, and correlation is smaller;So this value indicates two vegetable similarities with cosine.
Step 6 concentrates each vegetable compared with user's regional standard vegetable with vegetable, obtains each vegetable and standard vegetable
Similarity.
Preceding ten big vegetables of similarity are placed on and are recommended before menu.
Approach described above can be realized in network meal-ordering with a variety of computer languages.
Below with reference to specific example, the present invention is explained in detail.
Example 1: assuming that there is a home address to fill in the new user in Pekinese to order, before system queries Beijing area
It orders record, counts the characteristic value of Beijing area standard vegetable later, it is assumed that are as follows:
Later again it is all can provide vegetable provided by the businessman of vegetable concentrate search similarly spend high vegetable,
As the list of feature values of pork fried with sugar & vinegar dressing is
Compare therewith
X1=1, X2=0.8, X3=1.2, X4=0, X5=0.2, X6=0.55
Y1=1, Y2=0.8, Y3=1.1, Y4=0.1, Y5=0.2, Y6=0.5
It can compare in this way, pork fried with sugar & vinegar dressing is more conform with user's taste, it is proposed that be included in the menu for recommending vegetable.
In conjunction with attached drawing, the embodiment of the present invention is explained in detail above, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (4)
1. a kind of vegetable recommended method, characterized by the following steps:
Step1, according to user local location, calculate the feature vector, X of the standard vegetable in arean, wherein each characteristic value
Respectively X1, X2, X3, X4, X5, X6.........;
The vegetable feature vector, specifically: vector composed by the vegetable characteristic value;
Xn={ X1, X2, X3, X4, X5, X6}
The characteristic value of each vegetable, specifically: the criterion and quantity of each specific object of every course;
The regional standard vegetable characteristic value, specifically: this area's user's history is ordered in record, the characteristic value of all vegetables
Arithmetic average;
Xn={ X1, X2, X3, X4, X5, X6,
Step2, the standard vegetable feature vector according to user local location, calculate standard vegetable and vegetable is concentrated in vegetable
Similarity, the vegetable similarity be calculated according to vegetable self attributes vegetable attribute difference measurement;
Step3, by the vegetable in the similar menu of ordering dishes, as recommending vegetable.
2. according to the method described in claim 1, it is characterized by: the step1 specific step is as follows:
Step1.1, according to user local location, obtain the record of ordering dishes of the regional other users in user local;
Step1.2, the record of ordering dishes according to other users extract the characteristic value of every course in record, wherein the spy of every course
Sign vector is Xmn, each characteristic value of every course is respectively Xm1, Xm2, Xm3, Xm4, Xm5, Xm6... ..., wherein m=1,2,
3 ... ... M, M order dishes for location and record the quantity of all vegetables;
Xmn={ Xm1, Xm2, Xm3, Xm4, Xm5, Xm6}
Step1.3, the average value for calculating each characteristic value, obtain the feature vector, X of a standard vegetable latern, wherein each spy
Value indicative average value is respectively X1, X2, X3, X4, X5, X6... ..., M orders dishes for location and records the quantity of all vegetables;
Xn={ X1, X2, X3, X4, X5, X6,
3. according to the method described in claim 2, it is characterized by: the step2 specific step is as follows:
Step2.1, the characteristic value that vegetable concentrates all vegetables is extracted, obtains the feature vector Y of per pass vegetable in menum, wherein often
A characteristic value is respectively Ym1, Ym2, Ym3, Ym4, Ym5, Ym6... ... wherein m=1,2,3 ... ... N, N are institute in menu
There is the quantity of vegetable;
Yn={ Ym1, Ym2, Ym3, Ym4, Ym5, Ym6}
Step2.2, this feature vector and the cosine value (cos θ) of this regional standard vegetable feature vector are calculated, it then can be with
The similarity of each dish and standard dish in menu is obtained, this value indicates the similarity between two vegetables, the bigger theory of this value
Bright similarity is higher;
Similarity
4. according to the method described in claim 3, it is characterized by: vegetable in the Step3 in similar menu, specifically:
The standard vegetable and vegetable in the area concentrate highest preceding ten vegetables of similarity in vegetable.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811104765.4A CN109299360B (en) | 2018-09-21 | 2018-09-21 | Dish recommending method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811104765.4A CN109299360B (en) | 2018-09-21 | 2018-09-21 | Dish recommending method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109299360A true CN109299360A (en) | 2019-02-01 |
CN109299360B CN109299360B (en) | 2021-10-22 |
Family
ID=65164046
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811104765.4A Active CN109299360B (en) | 2018-09-21 | 2018-09-21 | Dish recommending method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299360B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961357A (en) * | 2019-03-25 | 2019-07-02 | 上海拉扎斯信息科技有限公司 | User data processing method, device, electronic equipment and storage medium |
CN111402013A (en) * | 2020-06-04 | 2020-07-10 | 成都晓多科技有限公司 | Commodity collocation recommendation method, system, device and storage medium |
CN115699069A (en) * | 2020-06-19 | 2023-02-03 | 松下知识产权经营株式会社 | Information providing method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101697162A (en) * | 2009-10-22 | 2010-04-21 | 杭州因豪信息科技开发有限公司 | Method and system for intelligently recommending ordering dishes |
CN104850579A (en) * | 2015-03-20 | 2015-08-19 | 南京邮电大学 | Food and beverage recommendation algorithm based on rating and feature similarity in social network |
CN105426552A (en) * | 2015-12-31 | 2016-03-23 | 山东大学 | Method for intelligently recommending menus and food and application |
WO2016186818A1 (en) * | 2015-05-15 | 2016-11-24 | Foogal Incorporated | Inventory-based tracking, dish recommendation, food freshness notification, and consumption notification from personal food inventory |
CN106447388A (en) * | 2016-08-31 | 2017-02-22 | 广东华邦云计算股份有限公司 | Method and system for recommending dishes |
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 |
CN107977890A (en) * | 2017-12-23 | 2018-05-01 | 临泉县烜槿餐饮管理有限公司 | One kind is based on Auto-matching food and drink menu push system |
CN108288219A (en) * | 2018-03-19 | 2018-07-17 | 口口相传(北京)网络技术有限公司 | The method for pushing and system of food product information |
-
2018
- 2018-09-21 CN CN201811104765.4A patent/CN109299360B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101697162A (en) * | 2009-10-22 | 2010-04-21 | 杭州因豪信息科技开发有限公司 | Method and system for intelligently recommending ordering dishes |
CN104850579A (en) * | 2015-03-20 | 2015-08-19 | 南京邮电大学 | Food and beverage recommendation algorithm based on rating and feature similarity in social network |
WO2016186818A1 (en) * | 2015-05-15 | 2016-11-24 | Foogal Incorporated | Inventory-based tracking, dish recommendation, food freshness notification, and consumption notification from personal food inventory |
CN105426552A (en) * | 2015-12-31 | 2016-03-23 | 山东大学 | Method for intelligently recommending menus and food and application |
CN106447388A (en) * | 2016-08-31 | 2017-02-22 | 广东华邦云计算股份有限公司 | Method and system for recommending dishes |
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 |
CN107977890A (en) * | 2017-12-23 | 2018-05-01 | 临泉县烜槿餐饮管理有限公司 | One kind is based on Auto-matching food and drink menu push system |
CN108288219A (en) * | 2018-03-19 | 2018-07-17 | 口口相传(北京)网络技术有限公司 | The method for pushing and system of food product information |
Non-Patent Citations (2)
Title |
---|
汪丽娟等: "基于Android的菜谱个性化推荐系统的设计与开发", 《电脑知识与技术》 * |
范顺忠等: "基于兴趣感知和时间因子的个性化菜品推荐", 《计算机应用研究》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961357A (en) * | 2019-03-25 | 2019-07-02 | 上海拉扎斯信息科技有限公司 | User data processing method, device, electronic equipment and storage medium |
CN111402013A (en) * | 2020-06-04 | 2020-07-10 | 成都晓多科技有限公司 | Commodity collocation recommendation method, system, device and storage medium |
CN111402013B (en) * | 2020-06-04 | 2020-09-01 | 成都晓多科技有限公司 | Commodity collocation recommendation method, system, device and storage medium |
CN115699069A (en) * | 2020-06-19 | 2023-02-03 | 松下知识产权经营株式会社 | Information providing method |
Also Published As
Publication number | Publication date |
---|---|
CN109299360B (en) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Aguilar et al. | Grab, pay, and eat: Semantic food detection for smart restaurants | |
CN101697162B (en) | Method and system for intelligently recommending ordering dishes | |
CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
CN109299360A (en) | A kind of method that vegetable is recommended | |
CN104794660B (en) | A kind of electronic ordering method, order server and electronic ordering system | |
CN104965889B (en) | Content recommendation method and device | |
CN105989594B (en) | A kind of image region detection method and device | |
CN107404656B (en) | Live video recommended method, device and server | |
KR100997541B1 (en) | The method and apparatus for image recommendation based on user profile using feature based collaborative filtering to resolve new item recommendation | |
CN107391531B (en) | Dish recommendation method and device | |
CN110135957A (en) | A kind of vegetable recommended method, device and the storage medium of intelligent restaurant healthy diet | |
CN110298725A (en) | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities | |
Kitamura et al. | Image processing based approach to food balance analysis for personal food logging | |
CN107862542A (en) | A kind of vegetable recommends method and apparatus | |
CN106447388A (en) | Method and system for recommending dishes | |
CN108897768B (en) | Ordering method and device and electronic equipment | |
CN104200409B (en) | A kind of matching process of taste selection information with application | |
CN107391947A (en) | A kind of health diet commending system and method | |
CN110135646B (en) | Restaurant pre-estimation quick serving method and device and storage medium | |
CN105844357A (en) | Dish combination recommending method and dish combination recommending system based on required heat | |
CN110851571A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
CN110264301A (en) | Recommended method, device, electronic equipment and non-volatile memory medium | |
CN105809275A (en) | Item scoring prediction method and apparatus | |
CN112818222A (en) | Knowledge graph-based personalized diet recommendation method and system | |
CN106886921A (en) | Personalized recommendation method based on user interest |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |