CN107862542A - A kind of vegetable recommends method and apparatus - Google Patents
A kind of vegetable recommends method and apparatus Download PDFInfo
- Publication number
- CN107862542A CN107862542A CN201710898816.4A CN201710898816A CN107862542A CN 107862542 A CN107862542 A CN 107862542A CN 201710898816 A CN201710898816 A CN 201710898816A CN 107862542 A CN107862542 A CN 107862542A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- preference
- meal
- personnel
- group
- 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
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 528
- 238000000034 method Methods 0.000 title claims abstract description 50
- 235000012054 meals Nutrition 0.000 claims abstract description 168
- 238000009826 distribution Methods 0.000 claims abstract description 39
- 241000894007 species Species 0.000 description 22
- 235000013305 food Nutrition 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 235000015277 pork Nutrition 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 5
- 241000287828 Gallus gallus Species 0.000 description 5
- 239000002253 acid Substances 0.000 description 5
- 235000009508 confectionery Nutrition 0.000 description 5
- 235000013616 tea Nutrition 0.000 description 5
- 244000269722 Thea sinensis Species 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000977 initiatory effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010411 cooking Methods 0.000 description 3
- 235000013372 meat Nutrition 0.000 description 3
- 235000002722 Dioscorea batatas Nutrition 0.000 description 2
- 235000006536 Dioscorea esculenta Nutrition 0.000 description 2
- 240000001811 Dioscorea oppositifolia Species 0.000 description 2
- 235000003416 Dioscorea oppositifolia Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 235000015067 sauces Nutrition 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 235000001366 vegetable intake Nutrition 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 244000291564 Allium cepa Species 0.000 description 1
- 235000002732 Allium cepa var. cepa Nutrition 0.000 description 1
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 235000002566 Capsicum Nutrition 0.000 description 1
- 240000008574 Capsicum frutescens Species 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 240000000851 Vaccinium corymbosum Species 0.000 description 1
- 235000003095 Vaccinium corymbosum Nutrition 0.000 description 1
- 235000017537 Vaccinium myrtillus Nutrition 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 235000013527 bean curd Nutrition 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 235000021014 blueberries Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000001390 capsicum minimum Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 235000013555 soy sauce Nutrition 0.000 description 1
- 238000005303 weighing Methods 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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)
- Finance (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiments of the invention provide a kind of vegetable to recommend method and apparatus, and methods described includes：The acquisition personnel of having meal with order historical information, have meal with personnel's preference information and businessman's menu information；Ordered historical information according to the personnel of having meal with, dish list and non-recommended dish list are recommended in generation；According to personnel's preference information of having meal with, generation group preference distribution information；According to the list of recommendation dish, the list of non-recommended dish and group's preference distribution information, determine that target recommends vegetable from businessman's menu information.In embodiments of the present invention, target recommends the generation method of vegetable, it with reference to order historical information and the preference information of all personnel that have meal with, it disclosure satisfy that the preference demand of most of user, and target recommends menu to be automatically generated by network ordering platform, the time that the personnel that have meal with work out vegetable order is shortened, the time of ordering is shortened, disclosure satisfy that user determines down the demand ordered in a short time.
Description
Technical field
The present invention relates to technical field of data processing, recommends method and a kind of vegetable to recommend dress more particularly to a kind of vegetable
Put.
Background technology
With the development of network ordering, increasing businessman has entered network ordering platform, and user can order in network
Single dining is subscribed in meal platform and more people have dinner.
In more people have dinner scene, order and critical role is occupied during whole dining, the resonable degree of vegetable collocation
The dining experience of user can be directly influenced, and then has influence on the public praise of businessman.
A kind of typical method of ordering is to determine all vegetables by a few peoples (such as 1-2 people), but this method can
It can not look after proprietary preference demand.Another method is that everyone selects the vegetable oneself liked, and is then adjusted again
It is whole, but such case takes more, the situation of unsuitable meal time anxiety.
The content of the invention
In view of the above problems, it is proposed that the embodiment of the present invention overcomes above mentioned problem or at least in part to provide one kind
A kind of vegetable to solve the above problems recommends method and a kind of corresponding vegetable recommendation apparatus.
In order to solve the above problems, the embodiment of the invention discloses a kind of vegetable to recommend method, including：
The acquisition personnel of having meal with order historical information, have meal with personnel's preference information and businessman's menu information；
Ordered historical information according to the personnel of having meal with, dish list and non-recommended dish list are recommended in generation；
According to personnel's preference information of having meal with, generation group preference distribution information；
According to the list of recommendation dish, the list of non-recommended dish and group's preference distribution information, believe from businessman's menu
Determine that target recommends vegetable in breath.
Preferably, group's preference distribution information includes：Have meal with personnel to preset vegetable attribute group's preference value；Institute
State according to the list of recommendation dish, the list of non-recommended dish and group's preference distribution information, it is true from businessman's menu information
The step of the recommending vegetable that set the goal includes：
The vegetable for belonging to non-recommended dish list in businessman's menu information is rejected；
Using the default vegetable attribute as dimension, the vegetable vector of each vegetable in candidate's vegetable set is generated；
Using the default vegetable attribute as dimension, using it is described have meal with personnel to preset vegetable attribute group's preference value,
Generate group's preference vector；
The recommendation extent index calculated using the vegetable of group's preference vector and each vegetable vector；
Improve the weighted value for the recommendation extent index for belonging to the vegetable for recommending dish list in businessman's menu information；
In businessman's menu information, recommend vegetable according to recommending extent index to choose target.
Preferably, it is described to recommend dish list, the list of non-recommended dish and group's preference distribution information according to described, from
Determine that the step of target recommends vegetable also includes in businessman's menu information：
After according to recommending extent index to choose a target recommendation vegetable, recommend the vegetable vector of vegetable using target,
Update group's preference vector；
Return to the recommendation extent index calculated using the vegetable of group's preference vector and each vegetable vector
The step of.
Preferably, it is described in businessman's menu information, wrapped according to recommending extent index to choose the step of target recommends vegetable
Include：
Acquisition is had meal with personnel amount；
According to personnel amount of having meal with, the vegetable number of target vegetable species and target vegetable species is determined；
The candidate's vegetable set for belonging to the target vegetable species is determined from commodity menu information；
From candidate's vegetable set, recommend vegetable according to recommending extent index to choose target, until the mesh chosen
Mark recommends the quantity of vegetable to reach the vegetable number of target vegetable species.
Preferably, described the step of recommending the vegetable of vegetable vectorial using target, updating group's preference vector, includes：
Calculate the vector differentials that target recommends the vegetable vector and group's preference vector of vegetable；
In each dimension difference for determining vector differentials, minimum dimension difference；
The value of each dimension of vector differentials is all subtracted into the minimum dimension difference, obtains new group's preference vector.
Preferably, personnel's preference information of having meal with includes：Have meal with personnel to preset vegetable attribute personal preference value；Institute
The step of stating according to personnel's preference information of having meal with, generating group's preference distribution information includes：
Using the personnel that have meal with to presetting the personal preference value of vegetable attribute, the certain preference of each vegetable attribute is calculated
Value；
Determine the relating attribute of vegetable attribute；
Place is normalized using the certain preference value of the certain preference value of vegetable attribute, and corresponding relating attribute
Reason, obtains group preference value of the personnel of having meal with to vegetable attribute.
Preferably, the personnel that have meal with are determined as follows to the personal preference value for presetting vegetable attribute：
Count the vegetable and overall consumption number of user's history post-consumer in a period of time；
To the vegetable of each post-consumer, the overall consumption number of vegetable of the statistics comprising a certain vegetable attribute；
By the overall consumption number divided by overall consumption number of the vegetable comprising a certain vegetable attribute, user is obtained to the vegetable category
The personal preference value of property.
Preferably, the personnel's of having meal with historical information of ordering includes：Have meal with personnel consumption vegetable and corresponding vegetable scoring
Value；The step of personnel of having meal with described in the basis order historical information, and dish list and non-recommended dish list are recommended in generation includes：
Calculate the average value of all vegetable score values of consumption vegetable, the recommendation score value as the consumption vegetable；
By the recommendation score value of each consumption vegetable compared with preset first threshold value and default Second Threshold；It is described
Preset first threshold value is more than the default Second Threshold；
If the recommendation score value of consumption vegetable is more than or equal to the first threshold, the consumption vegetable is included in recommendation dish
List；
If the recommendation score value of consumption vegetable is less than or equal to the Second Threshold, the consumption vegetable is included in non-recommended
Dish list.
The embodiment of the invention also discloses a kind of vegetable recommendation apparatus, including：
Have meal with data obtaining module, for obtain the personnel of having meal with order historical information, have meal with personnel's preference information and business
Family's menu information；
Vegetable List Generating Module, ordered historical information for the personnel of having meal with according to, dish list and non-is recommended in generation
Recommend dish list；
Group's preference distribution information generating module, for according to personnel's preference information of having meal with, generation group preference distribution letter
Breath；
Target recommends vegetable determining module, for according to the list of recommendation dish, the list of non-recommended dish and the group
Preference distribution information, determine that target recommends vegetable from businessman's menu information.
Preferably, group's preference distribution information includes：Have meal with personnel to preset vegetable attribute group's preference value；Institute
Stating target recommends vegetable determining module to include：
Vegetable rejects submodule, for the vegetable for belonging to non-recommended dish list in businessman's menu information to be rejected；
Vegetable vector generation submodule, it is each in candidate's vegetable set for using the default vegetable attribute as dimension, generating
The vegetable vector of individual vegetable；
Group preference vector generation submodule, for using the default vegetable attribute as dimension, using the personnel that have meal with
Group's preference value to presetting vegetable attribute, generation group preference vector；
Recommend extent index calculating sub module, for the vegetable vector using group's preference vector and each vegetable
The recommendation extent index of calculating；
Recommend extent index to carry power submodule, belong to pushing away for the vegetable for recommending dish list in businessman's menu information for improving
Recommend the weighted value of extent index；
Target recommends vegetable to choose submodule, in businessman's menu information, target to be chosen according to extent index is recommended
Recommend vegetable.
Preferably, the target recommends vegetable determining module also to include：
Group preference vector renewal submodule, for according to recommending extent index to choose after a target recommends vegetable,
Recommend the vegetable vector of vegetable, renewal group preference vector using target；
Return submodule, for call it is described recommendation extent index calculating sub module, use group's preference vector with
And the recommendation extent index that the vegetable vector of each vegetable calculates.
Preferably, the target, which recommends vegetable to choose submodule, includes：
Have meal with personnel's number obtainment unit, for obtaining personnel amount of having meal with；
Vegetable number of species determining unit, for according to personnel amount of having meal with, determining target vegetable species and target vegetable
The vegetable number of species；
Candidate's vegetable set determining unit, for determining the candidate for belonging to the target vegetable species from commodity menu information
Vegetable set；
Target recommends vegetable to choose unit, for from candidate's vegetable set, target to be chosen according to extent index is recommended
Recommend vegetable, until the target chosen recommends the quantity of vegetable to reach the vegetable number of target vegetable species.
Preferably, group's preference vector renewal submodule includes：
Vector differentials computing unit, the vector difference for recommending the vegetable vector and group's preference vector of vegetable for calculating target
Value；
Smallest dimension difference value determining unit, in each dimension difference for determining vector differentials, minimum dimension difference；
Group's preference vector updating block, it is poor for the value of each dimension of vector differentials all to be subtracted into the minimum dimension
Value, obtains new group's preference vector.
Preferably, personnel's preference information of having meal with includes：Have meal with personnel to preset vegetable attribute personal preference value；Institute
Stating group's preference distribution information generating module includes：
Certain preference value calculating sub module, for had meal with described in use personnel to preset vegetable attribute personal preference value,
Calculate the certain preference value of each vegetable attribute；
Relating attribute determination sub-module, for determining the relating attribute of vegetable attribute；
Group's preference value calculating sub module, for the certain preference value using vegetable attribute, and corresponding relating attribute
Certain preference value be normalized, obtain group preference value of the personnel of having meal with to vegetable attribute.
Preferably, the personnel that have meal with are determined to the personal preference value for presetting vegetable attribute by following module：
Consumption statistic module, for counting the vegetable of user's history post-consumer and overall consumption number in a period of time；
Vegetable statistics of attributes module, for the vegetable to each post-consumer, statistics includes the vegetable of a certain vegetable attribute
Overall consumption number；
Personal preference value computing module, for by the overall consumption number of the vegetable comprising a certain vegetable attribute divided by overall consumption
Number, obtain personal preference value of the user to the vegetable attribute.
Preferably, the personnel's of having meal with historical information of ordering includes：Have meal with personnel consumption vegetable and corresponding vegetable scoring
Value；The vegetable List Generating Module includes：
Recommendation score value calculating sub module, the average value of all vegetable score values for calculating consumption vegetable, is used as this
Consume the recommendation score value of vegetable；
Threshold value comparison sub-module, for by recommendation score value and the preset first threshold value of each consumption vegetable and default the
Two threshold values are compared；The preset first threshold value is more than the default Second Threshold；
Dish list is recommended to be included in submodule, if being more than or equal to first threshold for the recommendation score value for consuming vegetable
Value, then the consumption vegetable is included in and recommends dish list；
Non-recommended dish list is included in submodule, if being less than or equal to second threshold for the recommendation score value for consuming vegetable
Value, then be included in non-recommended dish list by the consumption vegetable.
The embodiment of the invention also discloses a kind of device, including：
One or more processors；With
One or more machine readable medias of instruction are stored thereon with, when by one or more of computing devices
When so that described device performs one or more method as described above.
The embodiment of the invention also discloses one or more machine readable medias, are stored thereon with instruction, when by one or
During multiple computing devices so that device performs one or more method as described above.
The embodiment of the present invention includes advantages below：
In embodiments of the present invention, network ordering platform is ordered historical information according to the personnel of having meal with, and dish list is recommended in generation
With non-recommended dish list；According to personnel's preference information of having meal with, generation group preference distribution information；According to recommending dish list, non-push away
Dish list and group's preference distribution information are recommended, determines that target recommends vegetable from businessman's menu information.Target recommends vegetable
Generation method, order historical information and the preference information of all personnel that have meal with is with reference to, disclosure satisfy that the preference of most of user
Demand, and target recommends menu to be automatically generated by network ordering platform, shortens the time that the personnel that have meal with work out vegetable order,
The time of ordering is shortened, disclosure satisfy that user determines down the demand ordered in a short time.
Brief description of the drawings
Fig. 1 is that a kind of vegetable of the present invention recommends the step flow chart of embodiment of the method 1；
Fig. 2 is that a kind of vegetable of the present invention recommends the step flow chart of embodiment of the method 2；
Fig. 3 is a kind of structured flowchart of vegetable recommendation apparatus embodiment of the present invention.
Embodiment
In order to facilitate the understanding of the purposes, features and advantages of the present invention, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is further detailed explanation.
In embodiments of the present invention, network ordering platform is provided with the function of initiating more people's dining.Specifically, initiation of having meal with
People can be first in the selected businessman for providing food and drink of network ordering platform；The promoter that has meal with can be directed to the businessman and create the group that has meal with
Group, and request of having meal with is initiated to good friend based on the friend relation chain of user, invite good friend to add group of having meal with；Good friend receives to have meal with
After request, group creating of having meal with is completed.Afterwards, network ordering platform can be to the user in group that has meal with, there is provided pushes away accordingly
Vegetable is recommended, for selection by the user.One of the core concepts of the embodiments of the present invention is, according to the information of user in group of having meal with,
Generation meets that the recommendation vegetable of user preferences selects for user；After user confirms, placed an order according to confirmation result.
Reference picture 1, show that a kind of vegetable of the present invention recommends the step flow chart of embodiment of the method 1, can specifically wrap
Include following steps：
Step 101, the personnel of having meal with are obtained to order historical information, have meal with personnel's preference information and businessman's menu information；
When having meal with, promoter initiates request of having meal with network ordering platform, and component is had meal with after group.Network ordering platform obtains
Order historical information and the preference information of each personnel that have meal with group of having meal with is taken, while also obtains the dish for the businessman that food and drink is provided
Single information.
Historical information of ordering can be included in the vegetable of user's once post-consumer, vegetable consumption number of times, vegetable scoring, vegetable
The information such as consumption time.
Preference information can include preference information of the user to the vegetable attribute such as taste, food materials, culinary art.
The menu information for providing the businessman of food and drink includes the information for the vegetable that businessman can provide.
, can be to each user's distributing user ID (user's mark) for network ordering platform.Network ordering platform can
So that order historical information and the preference information of the personnel that have meal with are extracted from database according to ID.
Step 102, ordered historical information according to the personnel of having meal with, dish list and non-recommended dish list are recommended in generation；
Network ordering platform is ordered historical information according to the personnel of having meal with, and from the vegetable for having meal with personnel's post-consumer, is determined
Recommend dish composition to recommend dish list, and determine that non-recommended dish forms non-recommended dish list.
Step 103, according to personnel's preference information of having meal with, generation group preference distribution information；
Network ordering platform is according to the preference information of each personnel that have meal with, group preference distribution of the generation for whole group
Information.Group's preference distribution information, most of preference of the personnel to vegetable attribute of having meal with can be reacted.
Step 104, according to the list of recommendation dish, the list of non-recommended dish and group's preference distribution information, from business
Determine that target recommends vegetable in family's menu information.
Network ordering platform is according to dish list, the list of non-recommended dish and group's preference distribution information is recommended, from businessman's dish
Determine that target recommends vegetable in single information.Target can be recommended vegetable by network ordering platform, be presented to have meal with promoter or institute
Have meal with personnel, by having meal with promoter or all personnel that have meal with are adjusted (for example, increase vegetable or reduce vegetable) to vegetable.
After having meal with promoter or all personnel that have meal with confirm to vegetable, network ordering platform creates order, and completion is had meal with initiation process.
In embodiments of the present invention, network ordering platform is ordered historical information according to the personnel of having meal with, and dish list is recommended in generation
With non-recommended dish list；According to personnel's preference information of having meal with, generation group preference distribution information；According to recommending dish list, non-push away
Dish list and group's preference distribution information are recommended, determines that target recommends vegetable from businessman's menu information.Target recommends vegetable
Generation method, order historical information and the preference information of all personnel that have meal with is with reference to, disclosure satisfy that the preference of most of user
Demand, and target recommends menu to be automatically generated by network ordering platform, shortens the time that the personnel that have meal with work out vegetable order,
The time of ordering is shortened, disclosure satisfy that user determines down the demand ordered in a short time.
Reference picture 2, show that a kind of vegetable of the present invention recommends the step flow chart of embodiment of the method 2, can specifically wrap
Include following steps：
Step 201, the personnel of having meal with are obtained to order historical information, have meal with personnel's preference information and businessman's menu information；
Historical information of ordering can be included in the vegetable of user's once post-consumer, vegetable consumption number of times, vegetable scoring, vegetable
The information such as consumption time.
Preference information can include preference information of the user to the vegetable attribute such as taste, food materials, culinary art.
The menu information for providing the businessman of food and drink includes the information for the vegetable that businessman can provide.
Step 202, ordered historical information according to the personnel of having meal with, dish list and non-recommended dish list are recommended in generation；
In embodiments of the present invention, the personnel's of having meal with historical information of ordering includes：Have meal with the consumption vegetable and correspondingly of personnel
Vegetable score value；The step 202 can include following sub-step：
Sub-step S11, calculates the average value of all vegetable score values of consumption vegetable, and the recommendation as the consumption vegetable is commented
Score value；
Sub-step S12, the recommendation score value of each consumption vegetable is entered with preset first threshold value and default Second Threshold
Row compares；The preset first threshold value is more than the default Second Threshold；
Sub-step S13, if the recommendation score value of consumption vegetable is more than or equal to the first threshold, by the consumption vegetable
It is included in and recommends dish list；
Sub-step S14, if the recommendation score value of consumption vegetable is less than or equal to the Second Threshold, by the consumption vegetable
It is included in non-recommended dish list.
It is a kind of signal table for historical information of ordering in the embodiment of the present invention as shown in table 1；
| User | Vegetable and score value |
| User01 | (fish-flavoured shredded pork, 5), (pork braised in brown sauce, 4), (stirfried bean curd in hot sauce, 1) ... |
| User02 | (stewed chick with mushroom, 3), (blueberry Chinese yam, 5) ... |
| User03 | (fish-flavoured shredded pork, 4), (stewed chick with mushroom, 4) |
Table 1
In embodiments of the present invention, after user has consumed vegetable in network ordering platform, vegetable can be scored.
To each vegetable, network ordering platform receives schooling group internal user to the vegetable score value of the vegetable, then calculates
Recommendation score value of the average value of the vegetable score value of each user as the vegetable.For example, for fish-flavoured shredded pork, the He of user 01
User 03 is scored the vegetable, and the recommendation score value of fish-flavoured shredded pork can be (5+4)/2=4.5.Stewed for chicken
Mushroom, user 02 and user 03 are scored the vegetable, and the recommendation score value of stewed chick with mushroom can be (3+4)/2=
3.5。
After the recommendation score value of each vegetable is calculated, by the recommendation score value of vegetable respectively with preset first threshold value and
Default Second Threshold is compared, and preset first threshold value is more than default Second Threshold.
If the recommendation score value of vegetable is more than or equal to first threshold, using the vegetable as vegetable is recommended, it is included in and pushes away
Recommend dish list.
If the recommendation score value of vegetable is less than or equal to Second Threshold, using the vegetable as non-recommended vegetable, it is included in
Non-recommended dish list.
For example, if first threshold is 4.5, the recommendation score value of fish-flavoured shredded pork is 4.5, then fish-flavoured shredded pork is included in into recommendation dish
List.
Step 203, according to personnel's preference information of having meal with, generation group preference distribution information；
In embodiments of the present invention, personnel's preference information of having meal with includes：Personnel have meal with to presetting the individual of vegetable attribute partially
Good value；Group's preference distribution information includes：Have meal with personnel to preset vegetable attribute group's preference value；
In embodiments of the present invention, vegetable attribute can be obtained by manual sorting in advance, vegetable attribute can be divided into taste,
These three classifications of food materials, cooking methods.
Taste classification can include：Acid, sweet tea, hardship, peppery, numb, fragrant, salty ... wait vegetable attribute
Food materials classification can include：Meat, egg, milk, mushroom, Chinese yam, capsicum, onion ... wait vegetable attribute
Cooking methods classification can include：Fry, mix, braising in soy sauce, stewing, decocting, baking ... and wait vegetable attribute
Each classification can be by all possible vegetable attribute of manual sorting.
It is as shown in table 2 the signal table for personnel's preference information of being had meal with the embodiment of the present invention；
Table 2
In embodiments of the present invention, it is inclined to the individual of each vegetable attribute to collect each user in group for network ordering platform
Good value.Personal preference value can be the numerical value between 0-1, for weighing preference of the user to some vegetable attribute.
Group's preference distribution information reflects preference of the group to some vegetable attribute from the angle of group.
In embodiments of the present invention, the step 203 can include following sub-step：
Sub-step S21, using the personal preference value of the personnel to default vegetable attribute of having meal with, calculate each vegetable attribute
Certain preference value；
Network ordering platform can use each personnel that have meal with to build matrix to the personal preference value of vegetable attribute, with each
Row represents user, and a kind of vegetable attribute is represented with each row.
It is a kind of schematic diagram of vegetable attribute matrix in the embodiment of the present invention as shown in table 3.
| Acid | Sweet tea | It is salty | It is peppery | … | |
| User-01 | 0 | 0 | 0.5 | 0.4 | … |
| User-02 | 0 | 0.6 | 0.6 | 0 | … |
| … | … | … | … | … | … |
Table 3
To the data of each row, it can adopt and calculate certain preference value by some way, as group in the vegetable attribute
On preference value.Calculation can include：Calculate maximum, calculated minimum, calculate average, calculate intermediate value etc..
Sub-step S22, determine the relating attribute of vegetable attribute；
In embodiments of the present invention, vegetable attribute can be divided into taste classification, food materials classification, cooking method class with category
Not.It is all relating attribute to belong to the other vegetable attribute of same class, if for example, taste classification includes：It is acid, sweet tea, salty, peppery 4
Vegetable attribute, then sour relating attribute include：It is sweet tea, salty, peppery.
Sub-step S23, carried out using the certain preference value of the certain preference value of vegetable attribute, and corresponding relating attribute
Normalized, obtain group preference value of the personnel of having meal with to vegetable attribute.
Assuming that V_ { taste } represents the preference value of a certain taste, V ' _ { taste } represents the taste preference value after normalization,
By taking taste " peppery " as an example, then
V ' _ peppery=V_ is peppery/and (salty+V_ of V_ acid+V_ sweet teas+V_ peppery+...)
The benefit that vegetable attribute is normalized is, to belonging to same category of vegetable attribute, vegetable attribute
Preference value will not be too wide in the gap；It can be compared to belonging to same category of vegetable attribute in same number range.
In embodiments of the present invention, having meal with personnel can be by following sub-step to presetting the personal preference value of vegetable attribute
It is determined that：
Sub-step S31, count the vegetable and overall consumption number of user's history post-consumer in a period of time；
Sub-step S32, to the vegetable of each post-consumer, the overall consumption number of vegetable of the statistics comprising a certain vegetable attribute；
Sub-step S33, by the overall consumption number divided by overall consumption number of the vegetable comprising a certain vegetable attribute, obtain user
To the personal preference value of the vegetable attribute.
For example, the vegetable of certain user interior post-consumer for a period of time includes：Spicy chicken leg fort, lotus pool side fish, spicy chicken wings, husband
Wife's lung piece.Consumption number of times are respectively：1、6、1、2.Include vegetable attribute：Peppery vegetable has spicy chicken leg fort, spicy chicken wings, man and wife
Lung piece.
Overall consumption number is 10, consumer package attribute containing vegetable：The number of peppery vegetable is 4.Then the user is to vegetable attribute：
Peppery personal preference value is 4/10=0.4.
Step 204, the vegetable that non-recommended dish list is belonged in businessman's menu information is rejected；
If having the vegetable for belonging to non-recommended dish list in the vegetable that businessman provides, these vegetables are rejected.
Step 205, using the default vegetable attribute as dimension, generate candidate's vegetable set in each vegetable vegetable to
Amount；
Using a vegetable attribute as a dimension, each vegetable attribute occupies a dimension.If vegetable has
Some vegetable attribute, then vegetable is 1 in the value of the dimension of the vegetable attribute, is otherwise 0.
The signal table of the vegetable vector of vegetable during the present invention is implemented is shown with reference to table 4.
Table 4
In the vegetable vector, middle vegetable attribute：Acid, vegetable attribute：Meat, vegetable attribute：The value of stir-fry is 1, remaining dimension
Value is all 0.
Step 206, using the default vegetable attribute as dimension, using the group of the personnel to default vegetable attribute of having meal with
Preference value, generation group preference vector；
To generate vegetable vector identical dimension, group's preference value according to the personnel of having meal with to default vegetable attribute, generation
The preference vector of group.
It is a kind of signal table of group's preference vector in the embodiment of the present invention as shown in table 5.
Table 5
Specifically, can by according to 203 group preference values of the personnel to each default vegetable attribute of having meal with being calculated,
It is combined according to vegetable vector identical dimension, obtains group preference vector of the personnel of having meal with to each vegetable attribute.
Step 207, the recommendation extent index calculated using the vegetable of group's preference vector and each vegetable vector；
Specifically, recommendation degree that can be using the cosine value of the vegetable of group's preference vector and vegetable vector as vegetable is joined
Number.Cosine value is bigger, and two vectorial similarity degrees are bigger, recommends extent index bigger.
Step 208, the weighted value for the recommendation extent index for belonging to the vegetable for recommending dish list in businessman's menu information is improved；
If having the vegetable for belonging to and recommending dish list in the vegetable that businessman provides, the recommendation degree ginseng of these vegetables is improved
Several weighted values.Specifically improving weight mode can be：The recommendation extent index of vegetable is multiplied by certain multiple or increase
Certain threshold value, as final recommendation extent index.
Step 209, in businessman's menu information, vegetable is recommended according to recommending extent index to choose target.
The product provided businessman, mesh is chosen according to clooating sequence from being ranked up to small greatly according to extent index is recommended
Mark recommended products.
It can include following sub-step in the step 209 in the embodiment of the present invention：
Sub-step S41, obtain personnel amount of having meal with；
Sub-step S42, according to personnel amount of having meal with, determine the vegetable number of target vegetable species and target vegetable species；
Sub-step S43, the candidate's vegetable set for belonging to the target vegetable species is determined from commodity menu information；
Sub-step S44, from candidate's vegetable set, recommend vegetable according to recommending extent index to choose target, until
Target through selection recommends the quantity of vegetable to reach the vegetable number of target vegetable species.
In embodiments of the present invention, set meal template, each set meal template regulation can be selected according to the quantity for the personnel of having meal with
The quantity of the classification of vegetable and each classification vegetable.Each personnel amount of having meal with can have multiple set meal templates to be selected
Select.
For example, set meal template A defines set meal and included：Vegetable classification A, vegetable classification A quantity are 2；Vegetable classification B,
Vegetable classification B quantity is 2.Set meal template B, which defines set meal, to be included：Vegetable classification A, vegetable classification A quantity are 3；Vegetable
Classification B, vegetable classification B quantity are 1.
The classification of vegetable, it can be divided by respective mode.For example, " meat dish " are divided into by the species of vegetable, " element
Material ", " staple food ", " beverage ", " soup class ", " congee class ".In another example divided by vegetable price：{“A”:Less than 10 yuan；“B”:
[10,25]；“C”:[25,50]；“D”:[50,100]；“E”:More than 100 yuan }
When choosing target recommendation vegetable, first choice determines the target vegetable species and target vegetable kind that set meal template is included
The vegetable number of class；Then in the vegetable for belonging to target vegetable species, successively according to the size for recommending extent index, target is chosen
Recommend vegetable.If the target for belonging to some target vegetable species chosen recommends vegetable quantity to meet to require, no
Choose again.
Step 210, after according to recommending extent index to choose a target recommendation vegetable, the dish of vegetable is recommended using target
Product vector, renewal group preference vector；
Often choose a target and recommend vegetable it is necessary to update group's preference vector.
In embodiments of the present invention it is described using target recommend vegetable vegetable vector, update group's preference vector the step of
Following sub-step can be included：
Sub-step S51, calculate the vector differentials that target recommends the vegetable vector and group's preference vector of vegetable；
Sub-step S52, in each dimension difference for determining vector differentials, minimum dimension difference；
Sub-step S53, the value of each dimension of vector differentials is all subtracted into the minimum dimension difference, obtains new group
Preference vector.
For example, if group's preference vector is (0.3,0.4,0.2,0.4)；Target recommend vegetable vegetable vector for (0.1,
0.5,0.8,0.4)；Then vector differentials are (0.2, -0.1, -0.6,0)
In each dimension difference in vector differentials, minimum dimension difference is -0.6.By each dimension of vector differentials
Value all subtracts the dimension difference of minimum, and it is (0.8,0.5,0,0.6) to obtain new group's preference vector
Step 211, the recommendation calculated using the vegetable of group's preference vector and each vegetable vector is returned
The step of extent index.
After renewal group preference vector, what the vegetable of calculating group's preference vector and each vegetable vector calculated again pushes away
Extent index is recommended, then selects new target to recommend vegetable again according to recommendation extent index.
After network ordering platform has chosen target recommendation vegetable, target can be recommended vegetable, be presented to the promoter that has meal with
Or all personnel that have meal with, by having meal with promoter or all personnel that have meal with are adjusted to vegetable (for example, increase vegetable or reducing dish
Product).After having meal with promoter or all personnel that have meal with confirm to vegetable, network ordering platform creates order, and completion is had meal with initiation
Process.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of action group
Close, but those skilled in the art should know, the embodiment of the present invention is not limited by described sequence of movement, because according to
According to the embodiment of the present invention, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, and the involved action not necessarily present invention is implemented
Necessary to example.
Reference picture 3, a kind of structured flowchart of vegetable recommendation apparatus embodiment of the present invention is shown, can specifically included such as
Lower module：
Have meal with data obtaining module 301, for obtain the personnel of having meal with order historical information, have meal with personnel's preference information and
Businessman's menu information；
Vegetable List Generating Module 302, ordered historical information for the personnel of having meal with according to, generation recommend dish list and
Non-recommended dish list；
Group's preference distribution information generating module 303, for according to personnel's preference information of having meal with, generation group preference distribution
Information；
Target recommends vegetable determining module 304, for according to the list of recommendation dish, the list of non-recommended dish and the group
Group preference distribution information, determine that target recommends vegetable from businessman's menu information.
In embodiments of the present invention, group's preference distribution information can include：Personnel have meal with to presetting vegetable attribute
Group's preference value；The target recommends vegetable determining module 304 to include：
Vegetable rejects submodule, for the vegetable for belonging to non-recommended dish list in businessman's menu information to be rejected；
Vegetable vector generation submodule, it is each in candidate's vegetable set for using the default vegetable attribute as dimension, generating
The vegetable vector of individual vegetable；
Group preference vector generation submodule, for using the default vegetable attribute as dimension, using the personnel that have meal with
Group's preference value to presetting vegetable attribute, generation group preference vector；
Recommend extent index calculating sub module, for the vegetable vector using group's preference vector and each vegetable
The recommendation extent index of calculating；
Recommend extent index to carry power submodule, belong to pushing away for the vegetable for recommending dish list in businessman's menu information for improving
Recommend the weighted value of extent index；
Target recommends vegetable to choose submodule, in businessman's menu information, target to be chosen according to extent index is recommended
Recommend vegetable.
In embodiments of the present invention, the target recommends vegetable determining module 304 to include：
Group preference vector renewal submodule, for according to recommending extent index to choose after a target recommends vegetable,
Recommend the vegetable vector of vegetable, renewal group preference vector using target；
Return submodule, for call it is described recommendation extent index calculating sub module, use group's preference vector with
And the recommendation extent index that the vegetable vector of each vegetable calculates.
In embodiments of the present invention, the target, which recommends vegetable to choose submodule, to include：
Have meal with personnel's number obtainment unit, for obtaining personnel amount of having meal with；
Vegetable number of species determining unit, for according to personnel amount of having meal with, determining target vegetable species and target vegetable
The vegetable number of species；
Candidate's vegetable set determining unit, for determining the candidate for belonging to the target vegetable species from commodity menu information
Vegetable set；
Target recommends vegetable to choose unit, for from candidate's vegetable set, target to be chosen according to extent index is recommended
Recommend vegetable, until the target chosen recommends the quantity of vegetable to reach the vegetable number of target vegetable species.
In embodiments of the present invention, group's preference vector renewal submodule can include：
Vector differentials computing unit, the vector difference for recommending the vegetable vector and group's preference vector of vegetable for calculating target
Value；
Smallest dimension difference value determining unit, in each dimension difference for determining vector differentials, minimum dimension difference；
Group's preference vector updating block, it is poor for the value of each dimension of vector differentials all to be subtracted into the minimum dimension
Value, obtains new group's preference vector.
In embodiments of the present invention, personnel's preference information of having meal with can include：Personnel have meal with to presetting vegetable attribute
Personal preference value；Group's preference distribution information generating module 303 can include：
Certain preference value calculating sub module, for had meal with described in use personnel to preset vegetable attribute personal preference value,
Calculate the certain preference value of each vegetable attribute；
Relating attribute determination sub-module, for determining the relating attribute of vegetable attribute；
Group's preference value calculating sub module, for the certain preference value using vegetable attribute, and corresponding relating attribute
Certain preference value be normalized, obtain group preference value of the personnel of having meal with to vegetable attribute.
In embodiments of the present invention, the personnel that have meal with can be by following mould to presetting the personal preference value of vegetable attribute
Block determines：
Consumption statistic module, for counting the vegetable of user's history post-consumer and overall consumption number in a period of time；
Vegetable statistics of attributes module, for the vegetable to each post-consumer, statistics includes the vegetable of a certain vegetable attribute
Overall consumption number；
Personal preference value computing module, for by the overall consumption number of the vegetable comprising a certain vegetable attribute divided by overall consumption
Number, obtain personal preference value of the user to the vegetable attribute.
In embodiments of the present invention, the personnel's of having meal with historical information of ordering can include：Have meal with personnel consumption vegetable and
Corresponding vegetable score value；The vegetable List Generating Module 302 can include：
Recommendation score value calculating sub module, the average value of all vegetable score values for calculating consumption vegetable, is used as this
Consume the recommendation score value of vegetable；
Threshold value comparison sub-module, for by recommendation score value and the preset first threshold value of each consumption vegetable and default the
Two threshold values are compared；The preset first threshold value is more than the default Second Threshold；
Dish list is recommended to be included in submodule, if being more than or equal to first threshold for the recommendation score value for consuming vegetable
Value, then the consumption vegetable is included in and recommends dish list；
Non-recommended dish list is included in submodule, if being less than or equal to second threshold for the recommendation score value for consuming vegetable
Value, then be included in non-recommended dish list by the consumption vegetable.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
The embodiment of the present invention additionally provides a kind of device, including：
One or more processors；With
One or more machine readable medias of instruction are stored thereon with, when by one or more of computing devices
When so that described device performs the method in the embodiment of the present invention.
The embodiment of the present invention additionally provides one or more machine readable medias, is stored thereon with instruction, when by one or
During multiple computing devices so that device performs the method in the embodiment of the present invention.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar part mutually referring to.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can use complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can use one or more wherein include computer can
With in the computer-usable storage medium (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention is with reference to method according to embodiments of the present invention, terminal device (system) and computer program
The flow chart and/or block diagram of product describes.It should be understood that can be by computer program instructions implementation process figure and/or block diagram
In each flow and/or square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These can be provided
Computer program instructions are set to all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to produce a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction is produced for realizing in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
The device for the function of specifying.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing terminal equipments
In the computer-readable memory to work in a specific way so that the instruction being stored in the computer-readable memory produces bag
The manufacture of command device is included, the command device is realized in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps is performed on computer or other programmable terminal equipments to produce computer implemented processing, so that
The instruction performed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or specified in one square frame of block diagram or multiple square frames function the step of.
Although having been described for the preferred embodiment of the embodiment of the present invention, those skilled in the art once know base
This creative concept, then other change and modification can be made to these embodiments.So appended claims are intended to be construed to
Including preferred embodiment and fall into having altered and changing for range of embodiment of the invention.
Finally, it is to be noted that, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or terminal device including a series of elements are not only wrapped
Those key elements, but also the other element including being not expressly set out are included, or is also included for this process, method, article
Or the key element that terminal device is intrinsic.In the absence of more restrictions, wanted by what sentence "including a ..." limited
Element, it is not excluded that other identical element in the process including the key element, method, article or terminal device also be present.
Method and a kind of vegetable recommendation apparatus are recommended to a kind of vegetable provided by the present invention above, carried out detailed Jie
Continue, specific case used herein is set forth to the principle and embodiment of the present invention, and the explanation of above example is only
It is the method and its core concept for being used to help understand the present invention；Meanwhile for those of ordinary skill in the art, according to this hair
Bright thought, there will be changes in specific embodiments and applications, in summary, this specification content should not manage
Solve as limitation of the present invention.
Claims (18)
1. a kind of vegetable recommends method, it is characterised in that including：
The acquisition personnel of having meal with order historical information, have meal with personnel's preference information and businessman's menu information；
Ordered historical information according to the personnel of having meal with, dish list and non-recommended dish list are recommended in generation；
According to personnel's preference information of having meal with, generation group preference distribution information；
According to the list of recommendation dish, the list of non-recommended dish and group's preference distribution information, from businessman's menu information
Determine that target recommends vegetable.
2. according to the method for claim 1, it is characterised in that group's preference distribution information includes：Have meal with personnel couple
Group's preference value of default vegetable attribute；It is described to recommend dish list, the list of non-recommended dish and group's preference according to described
Distributed intelligence, determine that the step of target recommends vegetable includes from businessman's menu information：
The vegetable for belonging to non-recommended dish list in businessman's menu information is rejected；
Using the default vegetable attribute as dimension, the vegetable vector of each vegetable in candidate's vegetable set is generated；
Using the default vegetable attribute as dimension, using the group preference value of the personnel to default vegetable attribute of having meal with, generation
Group's preference vector；
The recommendation extent index calculated using the vegetable of group's preference vector and each vegetable vector；
Improve the weighted value for the recommendation extent index for belonging to the vegetable for recommending dish list in businessman's menu information；
In businessman's menu information, recommend vegetable according to recommending extent index to choose target.
3. according to the method for claim 2, it is characterised in that described according to the recommendation dish list, non-recommended dish list
And group's preference distribution information, determine that the step of target recommends vegetable also includes from businessman's menu information：
After according to recommending extent index to choose a target recommendation vegetable, recommend the vegetable vector of vegetable, renewal using target
Group's preference vector；
Return to the step of the recommendation extent index calculated using the vegetable of group's preference vector and each vegetable vector
Suddenly.
4. according to the method in claim 2 or 3, it is characterised in that it is described in businessman's menu information, according to recommendation degree
The step of parameter selection target recommends vegetable includes：
Acquisition is had meal with personnel amount；
According to personnel amount of having meal with, the vegetable number of target vegetable species and target vegetable species is determined；
The candidate's vegetable set for belonging to the target vegetable species is determined from commodity menu information；
From candidate's vegetable set, recommend vegetable according to recommending extent index to choose target, until the target chosen pushes away
The quantity for recommending vegetable reaches the vegetable number of target vegetable species.
5. according to the method for claim 3, it is characterised in that the vegetable vector for recommending vegetable using target, renewal
The step of group's preference vector, includes：
Calculate the vector differentials that target recommends the vegetable vector and group's preference vector of vegetable；
In each dimension difference for determining vector differentials, minimum dimension difference；
The value of each dimension of vector differentials is all subtracted into the minimum dimension difference, obtains new group's preference vector.
6. according to the method for claim 2, it is characterised in that personnel's preference information of having meal with includes：Have meal with personnel couple
The personal preference value of default vegetable attribute；The basis is had meal with personnel's preference information, the step of generating group's preference distribution information
Including：
Using the personnel that have meal with to presetting the personal preference value of vegetable attribute, the certain preference value of each vegetable attribute is calculated；
Determine the relating attribute of vegetable attribute；
It is normalized, is obtained using the certain preference value of the certain preference value of vegetable attribute, and corresponding relating attribute
Group's preference value to the personnel of having meal with to vegetable attribute.
7. according to the method for claim 6, it is characterised in that the personal preference of the personnel to default vegetable attribute of having meal with
Value is determined as follows：
Count the vegetable and overall consumption number of user's history post-consumer in a period of time；
To the vegetable of each post-consumer, the overall consumption number of vegetable of the statistics comprising a certain vegetable attribute；
By the overall consumption number divided by overall consumption number of the vegetable comprising a certain vegetable attribute, user is obtained to the vegetable attribute
Personal preference value.
8. according to the method for claim 1, it is characterised in that the personnel's of having meal with historical information of ordering includes：Have meal with personnel's
Consume vegetable and corresponding vegetable score value；The personnel of having meal with described in the basis order historical information, and dish list is recommended in generation
Include with the step of non-recommended dish list：
Calculate the average value of all vegetable score values of consumption vegetable, the recommendation score value as the consumption vegetable；
By the recommendation score value of each consumption vegetable compared with preset first threshold value and default Second Threshold；It is described default
First threshold is more than the default Second Threshold；
If the recommendation score value of consumption vegetable is more than or equal to the first threshold, the consumption vegetable is included in and recommends dish row
Table；
If the recommendation score value of consumption vegetable is less than or equal to the Second Threshold, the consumption vegetable is included in non-recommended dish row
Table.
A kind of 9. vegetable recommendation apparatus, it is characterised in that including：
Have meal with data obtaining module, ordered historical information, have meal with personnel's preference information and businessman's dish for obtaining the personnel of having meal with
Single information；
Vegetable List Generating Module, ordered historical information for the personnel of having meal with according to, dish list and non-recommended are recommended in generation
Dish list；
Group's preference distribution information generating module, for according to personnel's preference information of having meal with, generation group preference distribution information；
Target recommends vegetable determining module, for according to the list of recommendation dish, the list of non-recommended dish and group's preference
Distributed intelligence, determine that target recommends vegetable from businessman's menu information.
10. device according to claim 9, it is characterised in that group's preference distribution information includes：Have meal with personnel couple
Group's preference value of default vegetable attribute；The target recommends vegetable determining module to include：
Vegetable rejects submodule, for the vegetable for belonging to non-recommended dish list in businessman's menu information to be rejected；
Vegetable vector generation submodule, for using the default vegetable attribute as dimension, generating each dish in candidate's vegetable set
The vegetable vector of product；
Group preference vector generation submodule, for using the default vegetable attribute as dimension, using the personnel that have meal with to pre-
If group's preference value of vegetable attribute, group's preference vector is generated；
Recommend extent index calculating sub module, calculated for the vegetable vector using group's preference vector and each vegetable
Recommendation extent index；
Recommend extent index to carry power submodule, belong to the recommendation journey for the vegetable for recommending dish list in businessman's menu information for improving
Spend the weighted value of parameter；
Target recommends vegetable to choose submodule, in businessman's menu information, recommending according to recommending extent index to choose target
Vegetable.
11. device according to claim 10, it is characterised in that the target recommends vegetable determining module also to include：
Group's preference vector renewal submodule, for after according to recommending extent index to choose a target recommendation vegetable, using
Target recommends the vegetable vector of vegetable, renewal group preference vector；
Submodule is returned to, for calling the recommendation extent index calculating sub module, using group's preference vector and respectively
The recommendation extent index that the vegetable vector of individual vegetable calculates.
12. the device according to claim 10 or 11, it is characterised in that the target recommends vegetable to choose submodule bag
Include：
Have meal with personnel's number obtainment unit, for obtaining personnel amount of having meal with；
Vegetable number of species determining unit, for according to personnel amount of having meal with, determining target vegetable species and target vegetable species
Vegetable number；
Candidate's vegetable set determining unit, for determining the candidate's vegetable for belonging to the target vegetable species from commodity menu information
Set；
Target recommends vegetable to choose unit, for from candidate's vegetable set, recommending according to recommending extent index to choose target
Vegetable, until the target chosen recommends the quantity of vegetable to reach the vegetable number of target vegetable species.
13. device according to claim 11, it is characterised in that group's preference vector renewal submodule includes：
Vector differentials computing unit, the vector differentials for recommending the vegetable vector and group's preference vector of vegetable for calculating target；
Smallest dimension difference value determining unit, in each dimension difference for determining vector differentials, minimum dimension difference；
Group's preference vector updating block, for the value of each dimension of vector differentials all to be subtracted into the minimum dimension difference,
Obtain new group's preference vector.
14. device according to claim 10, it is characterised in that personnel's preference information of having meal with includes：Have meal with personnel
Personal preference value to presetting vegetable attribute；Group's preference distribution information generating module includes：
Certain preference value calculating sub module, for personal preference value of the personnel to default vegetable attribute of being had meal with described in use, calculate
The certain preference value of each vegetable attribute；
Relating attribute determination sub-module, for determining the relating attribute of vegetable attribute；
Group's preference value calculating sub module, for the certain preference value using vegetable attribute, and the spy of corresponding relating attribute
Determine preference value to be normalized, obtain group preference value of the personnel of having meal with to vegetable attribute.
15. device according to claim 14, it is characterised in that the personnel that have meal with are to presetting the individual of vegetable attribute partially
Good value is determined by following module：
Consumption statistic module, for counting the vegetable of user's history post-consumer and overall consumption number in a period of time；
Vegetable statistics of attributes module, for the vegetable to each post-consumer, vegetable of the statistics comprising a certain vegetable attribute always disappears
Take number；
Personal preference value computing module, for the overall consumption number of the vegetable comprising a certain vegetable attribute divided by overall consumption is secondary
Number, obtains personal preference value of the user to the vegetable attribute.
16. device according to claim 9, it is characterised in that the personnel's of having meal with historical information of ordering includes：Have meal with personnel's
Consume vegetable and corresponding vegetable score value；The vegetable List Generating Module includes：
Recommendation score value calculating sub module, the average value of all vegetable score values for calculating consumption vegetable, as the consumption
The recommendation score value of vegetable；
Threshold value comparison sub-module, for by recommendation score value and the preset first threshold value of each consumption vegetable and default second threshold
Value is compared；The preset first threshold value is more than the default Second Threshold；
Dish list is recommended to be included in submodule, if being more than or equal to the first threshold for the recommendation score value for consuming vegetable,
The consumption vegetable is included in and recommends dish list；
Non-recommended dish list is included in submodule, if being less than or equal to the Second Threshold for the recommendation score value for consuming vegetable,
The consumption vegetable is then included in non-recommended dish list.
A kind of 17. device, it is characterised in that including：
One or more processors；With
One or more machine readable medias of instruction are stored thereon with, when by one or more of computing devices, are made
Obtain one or more methods of the described device execution as described in claim 1-8.
18. one or more machine readable medias, instruction is stored thereon with, when executed by one or more processors so that
Device performs one or more methods as described in claim 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898816.4A CN107862542A (en) | 2017-09-28 | 2017-09-28 | A kind of vegetable recommends method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898816.4A CN107862542A (en) | 2017-09-28 | 2017-09-28 | A kind of vegetable recommends method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107862542A true CN107862542A (en) | 2018-03-30 |
Family
ID=61698178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710898816.4A Pending CN107862542A (en) | 2017-09-28 | 2017-09-28 | A kind of vegetable recommends method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107862542A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108806769A (en) * | 2018-05-07 | 2018-11-13 | 河南金凤电子科技有限公司 | A kind of nutrient combo recommendation method and apparatus |
| CN108876520A (en) * | 2018-05-25 | 2018-11-23 | 重庆瑞耕达网络科技有限公司 | A kind of dining table interlock method and system |
| 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 |
| CN109147910A (en) * | 2018-08-09 | 2019-01-04 | 海南纽康信息系统有限公司 | A kind of dish recommendation system and implementation method based on food materials nutritional ingredient and taste |
| 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 |
| CN109544285A (en) * | 2018-11-13 | 2019-03-29 | 口碑(上海)信息技术有限公司 | The vegetable recommended method and device for process of ordering |
| CN109583999A (en) * | 2018-11-13 | 2019-04-05 | 平安科技（深圳）有限公司 | It makes a reservation information recommendation method, device, electronic equipment and storage medium |
| CN109816473A (en) * | 2018-12-19 | 2019-05-28 | 平安科技（深圳）有限公司 | Payment and settlement processing method, apparatus and system based on cloud transmission |
| CN109903133A (en) * | 2019-02-26 | 2019-06-18 | 苏州星点点信息科技有限公司 | Processing method, device and the computer equipment of group's meal vegetable |
| CN110111170A (en) * | 2019-03-28 | 2019-08-09 | 北京三快在线科技有限公司 | Candidate businessman's matching process, device, electronic equipment and readable storage medium storing program for executing |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
| CN110400197A (en) * | 2019-07-25 | 2019-11-01 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110675284A (en) * | 2018-07-03 | 2020-01-10 | 陈超 | Production method, device and system for unmanned restaurant and server |
| CN110782308A (en) * | 2019-09-20 | 2020-02-11 | 北京三快在线科技有限公司 | Pushing method and device for recommended package, electronic equipment and readable storage medium |
| CN110874785A (en) * | 2019-09-30 | 2020-03-10 | 浙江口碑网络技术有限公司 | Method, device and equipment for determining meal package information |
| CN111210267A (en) * | 2019-12-27 | 2020-05-29 | 北京三快在线科技有限公司 | Research and development dish recommendation method and device and electronic equipment |
| CN111383136A (en) * | 2018-12-29 | 2020-07-07 | 须树科技(上海)有限公司 | Self-service ordering method and system and mobile terminal |
| CN112328845A (en) * | 2020-11-12 | 2021-02-05 | 珠海格力电器股份有限公司 | Dish pushing method and device based on cooking equipment and cooking equipment |
| CN112861008A (en) * | 2021-03-01 | 2021-05-28 | 山东大学 | Restaurant ordering recommendation method and system based on multi-user information fusion and entropy |
| CN112991016A (en) * | 2021-03-25 | 2021-06-18 | 北京市商汤科技开发有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113239289A (en) * | 2021-05-28 | 2021-08-10 | 山东大学 | Group activity recommendation method and system, electronic device and readable storage medium |
| CN113362093A (en) * | 2020-03-05 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining product target attribute and readable storage medium |
| CN113632126A (en) * | 2019-03-27 | 2021-11-09 | 日本食品制造合资会社 | Project recommendation system |
| CN116457816A (en) * | 2021-08-04 | 2023-07-18 | 松下知识产权经营株式会社 | Information providing method |
| CN116529747A (en) * | 2021-08-04 | 2023-08-01 | 松下知识产权经营株式会社 | Control method and information providing method |
| CN117541359A (en) * | 2024-01-04 | 2024-02-09 | 江西工业贸易职业技术学院(江西省粮食干部学校、江西省粮食职工中等专业学校) | Dining recommendation method and system based on preference analysis |
| US12093996B2 (en) | 2021-08-04 | 2024-09-17 | Panasonic Intellectual Property Management Co., Ltd. | Method for providing information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412936A (en) * | 2013-08-21 | 2013-11-27 | 五八同城信息技术有限公司 | Dish recommendation system based on data mining and cloud computing service |
| CN106651524A (en) * | 2016-12-27 | 2017-05-10 | 杭州火小二科技有限公司 | Method for intelligently generating recommended menu |
| CN107093124A (en) * | 2017-02-27 | 2017-08-25 | 口碑控股有限公司 | A kind of information recommendation method and device |
| CN107203950A (en) * | 2016-03-18 | 2017-09-26 | 湖南餐启科技有限公司 | A kind of vegetable recommends method and system |
-
2017
- 2017-09-28 CN CN201710898816.4A patent/CN107862542A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412936A (en) * | 2013-08-21 | 2013-11-27 | 五八同城信息技术有限公司 | Dish recommendation system based on data mining and cloud computing service |
| CN107203950A (en) * | 2016-03-18 | 2017-09-26 | 湖南餐启科技有限公司 | A kind of vegetable recommends method and system |
| CN106651524A (en) * | 2016-12-27 | 2017-05-10 | 杭州火小二科技有限公司 | Method for intelligently generating recommended menu |
| CN107093124A (en) * | 2017-02-27 | 2017-08-25 | 口碑控股有限公司 | A kind of information recommendation method and device |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108806769A (en) * | 2018-05-07 | 2018-11-13 | 河南金凤电子科技有限公司 | A kind of nutrient combo recommendation method and apparatus |
| CN108876520A (en) * | 2018-05-25 | 2018-11-23 | 重庆瑞耕达网络科技有限公司 | A kind of dining table interlock method and system |
| 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 |
| WO2019223297A1 (en) * | 2018-05-25 | 2019-11-28 | 北京三快在线科技有限公司 | Method and apparatus for ordering food, and electronic device |
| CN110675284A (en) * | 2018-07-03 | 2020-01-10 | 陈超 | Production method, device and system for unmanned restaurant and server |
| CN109147910A (en) * | 2018-08-09 | 2019-01-04 | 海南纽康信息系统有限公司 | A kind of dish recommendation system and implementation method based on food materials nutritional ingredient and taste |
| 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 |
| 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 |
| CN109583999A (en) * | 2018-11-13 | 2019-04-05 | 平安科技（深圳）有限公司 | It makes a reservation information recommendation method, device, electronic equipment and storage medium |
| CN109544285A (en) * | 2018-11-13 | 2019-03-29 | 口碑(上海)信息技术有限公司 | The vegetable recommended method and device for process of ordering |
| CN109816473A (en) * | 2018-12-19 | 2019-05-28 | 平安科技（深圳）有限公司 | Payment and settlement processing method, apparatus and system based on cloud transmission |
| CN111383136A (en) * | 2018-12-29 | 2020-07-07 | 须树科技(上海)有限公司 | Self-service ordering method and system and mobile terminal |
| CN109903133A (en) * | 2019-02-26 | 2019-06-18 | 苏州星点点信息科技有限公司 | Processing method, device and the computer equipment of group's meal vegetable |
| CN113632126A (en) * | 2019-03-27 | 2021-11-09 | 日本食品制造合资会社 | Project recommendation system |
| CN110111170A (en) * | 2019-03-28 | 2019-08-09 | 北京三快在线科技有限公司 | Candidate businessman's matching process, device, electronic equipment and readable storage medium storing program for executing |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
| CN110400197A (en) * | 2019-07-25 | 2019-11-01 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110782308A (en) * | 2019-09-20 | 2020-02-11 | 北京三快在线科技有限公司 | Pushing method and device for recommended package, electronic equipment and readable storage medium |
| CN110874785A (en) * | 2019-09-30 | 2020-03-10 | 浙江口碑网络技术有限公司 | Method, device and equipment for determining meal package information |
| CN111210267A (en) * | 2019-12-27 | 2020-05-29 | 北京三快在线科技有限公司 | Research and development dish recommendation method and device and electronic equipment |
| CN113362093A (en) * | 2020-03-05 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining product target attribute and readable storage medium |
| CN112328845A (en) * | 2020-11-12 | 2021-02-05 | 珠海格力电器股份有限公司 | Dish pushing method and device based on cooking equipment and cooking equipment |
| CN112861008B (en) * | 2021-03-01 | 2022-08-09 | 山东大学 | Restaurant ordering recommendation method and system based on multi-user information fusion and entropy |
| CN112861008A (en) * | 2021-03-01 | 2021-05-28 | 山东大学 | Restaurant ordering recommendation method and system based on multi-user information fusion and entropy |
| CN112991016A (en) * | 2021-03-25 | 2021-06-18 | 北京市商汤科技开发有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113239289A (en) * | 2021-05-28 | 2021-08-10 | 山东大学 | Group activity recommendation method and system, electronic device and readable storage medium |
| CN113239289B (en) * | 2021-05-28 | 2022-08-30 | 山东大学 | Group activity recommendation method and system, electronic device and readable storage medium |
| CN116457816A (en) * | 2021-08-04 | 2023-07-18 | 松下知识产权经营株式会社 | Information providing method |
| CN116529747A (en) * | 2021-08-04 | 2023-08-01 | 松下知识产权经营株式会社 | Control method and information providing method |
| US12033227B2 (en) | 2021-08-04 | 2024-07-09 | Panasonic Intellectual Property Management Co., Ltd. | Method for providing information |
| US12093996B2 (en) | 2021-08-04 | 2024-09-17 | Panasonic Intellectual Property Management Co., Ltd. | Method for providing information |
| CN117541359A (en) * | 2024-01-04 | 2024-02-09 | 江西工业贸易职业技术学院(江西省粮食干部学校、江西省粮食职工中等专业学校) | Dining recommendation method and system based on preference analysis |
| CN117541359B (en) * | 2024-01-04 | 2024-03-29 | 江西工业贸易职业技术学院(江西省粮食干部学校、江西省粮食职工中等专业学校) | Dining recommendation method and system based on preference analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862542A (en) | A kind of vegetable recommends method and apparatus | |
| CN108897768B (en) | Ordering method and device and electronic equipment | |
| US11133098B2 (en) | Food preparation system and method | |
| CN104200409B (en) | A kind of matching process of taste selection information with application | |
| KR101552339B1 (en) | Apparatus and method for servicing personalized food menu and foods purchase able to feedback | |
| US20230169118A1 (en) | Information presenting method, recording medium, information presenting system, and terminal device | |
| CN107092647B (en) | Method and device for providing resource combination | |
| JP6410069B1 (en) | Recipe information providing apparatus, recipe information providing method, and recipe information providing program | |
| US20160098942A1 (en) | Method for Generating Low-Waste Personalized Meal Plans within a Budget | |
| CN106548006A (en) | A kind of meals based on user's typical case's taste recommend method | |
| CN107038413A (en) | recipe recommendation method, device and refrigerator | |
| KR102189232B1 (en) | Method, system and non-transitory computer-readable recording medium for providing contents based on life style | |
| KR102589880B1 (en) | Method for food recommendation using deep-learning module | |
| CN107610752A (en) | A kind of method of intelligence generation dietary program | |
| KR20120029027A (en) | Service method and apparatus for providing diet menu | |
| JP2019133624A (en) | Recipe information provision apparatus, recipe information provision method, and recipe information provision program | |
| CN106886921A (en) | Personalized recommendation method based on user interest | |
| US20200394727A1 (en) | Food ordering system based on predefined variables | |
| Benrit et al. | The relationships among food quality, service quality, physical environment and customers’ satisfaction in thai dining restaurant in malaysia | |
| CN108416628A (en) | A kind of dining room vegetable intelligent recommendation system of the fusion more relations on attributes of food | |
| CN118299001A (en) | Cooking plan generation method and device, electronic equipment and storage medium | |
| CN118369676A (en) | System for dynamically generating recommendations for purchasing sustainable items | |
| Ratisoontorn | Recipe recommendations for toddlers using integrated nutritional and ingredient similarity measures | |
| Chen | Haidilao customer evaluation based on Meituan data and analysis of the effectiveness of Haidilao's sinking strategy——Take Hohhot as an example | |
| Azhar et al. | Improvement accuracy of oil meal packaging with method ANP |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |