CN109214955A - The generation method and device of food product set meal - Google Patents
The generation method and device of food product set meal Download PDFInfo
- Publication number
- CN109214955A CN109214955A CN201810938844.9A CN201810938844A CN109214955A CN 109214955 A CN109214955 A CN 109214955A CN 201810938844 A CN201810938844 A CN 201810938844A CN 109214955 A CN109214955 A CN 109214955A
- Authority
- CN
- China
- Prior art keywords
- food product
- information
- ordering
- history
- set meal
- 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
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—Systems or methods specially adapted for 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)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the generation methods and device of a kind of food product set meal, are related to electronic information field, the record this method comprises: acquisition history corresponding with sample of users is ordered;It is ordered each timing information of ordering for having put food product for including in record according to the history, generation is ordered sample data;The sample data of ordering is trained by machine learning model, with each sequential correlation relationship put between food product of determination;Food product package information is generated according to each sequential correlation relationship put between food product.Due to the preference that the timing information of ordering during ordering can further reflect user for food product, the present invention combines each timing information of ordering for having selected food product to be trained and generate set meal, and the set meal generated can be made more to be bonded user demand.
Description
Technical field
The present invention relates to electronic information fields, and in particular to a kind of generation method and device of food product set meal.
Background technique
In order to promote the efficiency of ordering of customer, many businessmans are proposed a plurality of set meals, so that user selects.Due to set meal
In contain staple food, non-staple foodstuff, soup drink etc. all kinds of food products therefore can satisfy user's demand in all directions, thus avoid user by
One selects the problem of taking time and effort caused by each food product, receives the high praise of a large number of users.In the prior art, businessman pushes away
The set meal sent is generated by manual type mostly: by food and drink staff according to food product arrange in pairs or groups habit and it is previous sell experience,
Several money set meals of labor mix.
But inventor is in the implementation of the present invention, it is found that it is as follows aforesaid way in the prior art at least exists
Problem: the mode of labor mix's set meal causes set meal formation efficiency low, also, is limited to the experience of food and drink staff, leads
The set meal artificially arranged in pairs or groups is caused to tend not to the demand for catering to users well.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
State the generation method and device of a kind of food product set meal of problem.
According to an aspect of the invention, there is provided a kind of generation method of food product set meal, comprising: acquisition and sample of users
Corresponding history is ordered record;
It is ordered each timing information of ordering for having put food product for including in record according to the history, generation is ordered sample number
According to;
The sample data of ordering is trained by machine learning model, with determination it is each put between food product when
Sequence incidence relation;
Food product package information is generated according to each sequential correlation relationship put between food product.
Optionally, described to be ordered each timing information of ordering for having put food product for including in record according to the history, it is raw
At order sample data the step of specifically include:
Order record for every history respectively, obtain this history and order include in record each put food product it is right
Order time and/or the serial number of ordering answered;
Ordered according to this history include in record it is each put to order corresponding to food product the time and/or order
Serial number determines that this history is ordered each timing information of ordering for having put food product for including in record;
According to this history order record in include each timing information of ordering for having put food product, generate one group with
This history, which is ordered, records corresponding sample data of ordering.
Optionally, the step that food product package information is generated according to each sequential correlation relationship put between food product
Suddenly it specifically includes:
According to each sequential correlation relationship put between food product, analyze each preference-score for having put food product and/
Or food product combined information;
According to each preference-score for having put food product and/or food product combined information, food product package information is generated.
Optionally, the machine learning model is the machine learning model based on time series, and described based on time sequence
The machine learning model of column includes: time recurrent neural networks model.
Optionally, the step that food product package information is generated according to each sequential correlation relationship put between food product
Suddenly it specifically includes:
Food product package information is generated in conjunction with preset set meal collocation rule;Wherein, the set meal collocation rule includes following
At least one of: number of meals division rule, dining Type division rule, meat and vegetables collocation rule and entree garnishes collocation
Rule.
Optionally, the step that food product package information is generated according to each sequential correlation relationship put between food product
After rapid, further comprise:
The food product package information is pushed to user terminal, for the user terminal to the food product package information into
Row display.
Optionally, the step that food product package information is generated according to each sequential correlation relationship put between food product
After rapid, further comprise: including according in each determining food product package information generated of timing information of ordering for having put food product
Multiple food products show sequence information;
It is then described that the food product package information is pushed to user terminal, so that the user terminal is to the food product set meal
The step of information is shown specifically includes: the food product package information and multiple food products wherein included are showed sequence
Information is pushed to user terminal, so that the user terminal shows sequence information to the food product set according to the multiple food product
The multiple food products for including in meal information sort and show.
Optionally, described according to each timing put between food product when the food product package information is multiple
After incidence relation generates the step of food product package information, further comprise: being generated for each food product package information corresponding
Push official documents and correspondence information;
It is then described that the food product package information is pushed to user terminal, so that the user terminal is to the food product set meal
The step of information is shown specifically includes: the food product package information and its corresponding push official documents and correspondence information are pushed to user
Terminal, so that the push official documents and correspondence information is associated with display with the food product package information by the user terminal.
Optionally, before the method executes, further comprise: the sample of users being divided into a variety of user class in advance
Type then further includes user type information in order sample data and the food product package information;
Then the described the step of food product package information is pushed to user terminal specifically includes: selection is whole with the user
The food product package information that the user type at end matches is pushed.
According to another aspect of the present invention, a kind of generating means of food product set meal are provided, comprising:
Module is obtained, is ordered record suitable for obtaining corresponding with sample of users history;
Sample data generation module, suitable for ordered according to the history include in record each put when ordering of food product
Sequence information generates sample data of ordering;
Training module, it is each with determination suitable for being trained by machine learning model to the sample data of ordering
Sequential correlation relationship between point food product;
Set meal generation module, suitable for generating food product set meal letter according to each sequential correlation relationship selected between food product
Breath.
Optionally, the sample data generation module is particularly adapted to:
Order record for every history respectively, obtain this history and order include in record each put food product it is right
Order time and/or the serial number of ordering answered;
Ordered according to this history include in record it is each put to order corresponding to food product the time and/or order
Serial number determines that this history is ordered each timing information of ordering for having put food product for including in record;
According to this history order record in include each timing information of ordering for having put food product, generate one group with
This history, which is ordered, records corresponding sample data of ordering.
Optionally, the set meal generation module is particularly adapted to:
According to each sequential correlation relationship put between food product, analyze each preference-score for having put food product and/
Or food product combined information;
According to each preference-score for having put food product and/or food product combined information, food product package information is generated.
Optionally, the machine learning model is the machine learning model based on time series, and described based on time sequence
The machine learning model of column includes: time recurrent neural networks model.
Optionally, the set meal generation module is particularly adapted to:
Food product package information is generated in conjunction with preset set meal collocation rule;Wherein, the set meal collocation rule includes following
At least one of: number of meals division rule, dining Type division rule, meat and vegetables collocation rule and entree garnishes collocation
Rule.
Optionally, described device further comprises:
Pushing module, suitable for the food product package information is pushed to user terminal, so that the user terminal is to described
Food product package information is shown.
Optionally, the pushing module is further adapted for: being determined and is generated according to each timing information of ordering for having put food product
Food product package information in include multiple food products show sequence information;By the food product package information and wherein included
The sequence information that shows of multiple food products is pushed to user terminal, so that the user terminal shows sequence according to the multiple food product
Column information sorts and shows to the multiple food products for including in the food product package information.
Optionally, when the food product package information is multiple, the pushing module is further adapted for: being directed to each food product
Package information generates corresponding push official documents and correspondence information;The food product package information and its corresponding push official documents and correspondence information are pushed to
User terminal, so that the push official documents and correspondence information is associated with display with the food product package information by the user terminal.
Optionally, the pushing module is further adapted for: the sample of users is divided into a variety of user types in advance, and
User type information is further included in order sample data and the food product package information;Selection is whole with the user
The food product package information that the user type at end matches is pushed.
According to the present invention in another aspect, providing a kind of electronic equipment, comprising: processor, memory, communication interface and
Communication bus, the processor, the memory and the communication interface complete mutual communication by the communication bus;
For the memory for storing an at least executable instruction, it is as above that the executable instruction executes the processor
The corresponding operation of the generation method for the food product set meal stated.
According to the present invention in another aspect, provide a kind of computer storage medium, be stored in the storage medium to
A few executable instruction, the executable instruction make processor execute the corresponding behaviour of generation method such as above-mentioned food product set meal
Make.
The generation method and device of the food product set meal provided according to the present invention can obtain go through corresponding with sample of users
History is ordered record, and is ordered each timing information of ordering for having put food product for including in record according to history, and generation is ordered sample
Data;Sample data of ordering is trained by machine learning model, so that it is determined that each timing put between food product is closed
Connection relationship, and food product package information is generated according to each sequential correlation relationship put between food product.Since history is ordered record
It is able to reflect order habit and the taste preference of most users, therefore, can be made more by the order excavation of record of history
Add reasonable set meal.Also, since the timing information of ordering during ordering can further reflect user for the inclined of food product
Good, therefore, the present invention combines each timing information of ordering for having selected food product to be trained and generate set meal, can make the set generated
Meal is more bonded user demand.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of flow chart of the generation method of food product set meal of the offer of the embodiment of the present invention one;
Fig. 2 shows a kind of flow charts of the generation method of food product set meal provided by Embodiment 2 of the present invention;
Fig. 3 shows a kind of structure chart of the generating means of food product set meal of the offer of the embodiment of the present invention three;
Fig. 4 shows the structural schematic diagram of a kind of electronic equipment of the offer of the embodiment of the present invention five.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Embodiment one
Fig. 1 shows a kind of flow chart of the generation method of food product set meal of the offer of the embodiment of the present invention one.Such as Fig. 1 institute
Show, this method comprises:
Step S110: it obtains corresponding with sample of users history and orders record.
Wherein, for the precision and universality of lift scheme training, user's conduct of largely ordering can be collected in advance
Sample of users, also, in order to cater to the demand of Different crowds, the user type of sample of users can cover multiple types, with anti-
Reflect the hobby of ordering of all types of user.Specifically, history record of ordering typically refers to: point caused by during once ordering
Meal record.For example, it is assumed that user A has carried out behavior of once ordering at noon June 1, then this time orders behavior corresponding to one
History is ordered record.
Step S120: each timing information of ordering for having put food product for including in recording of being ordered according to history, generation are ordered
Sample data.
Specifically, it is usually ordered with a history and is recorded as minimum unit and is analyzed.It orders record for a history,
This history is obtained to order each title for having put food product or other identifier information for including in record, it is each uniquely to distinguish
Then a food product obtains this history and orders include in record each and put to order corresponding to food product and the time and/or order
All kinds of information for being able to reflect timing of ordering such as serial number, and accordingly generate one group and order with this history and record corresponding order
Sample data.It can be seen that each timing information of ordering for having put food product is as important category in every group of sample data of ordering
Property information is recorded.Certainly, in sample data of ordering, other dimensions in addition to timing information of ordering can also be recorded
Attribute information, preferably to reflect each the characteristics of having put food product, the present invention does not do the concrete form for sample data of ordering
It limits.
Step S130: being trained sample data of ordering by machine learning model, with determination it is each put food product it
Between sequential correlation relationship.
Wherein, which can use all kinds of model realizations for having machine learning function, and the present invention is to machine
The specific choice and training method of device learning model are without limitation.Specifically, the machine learning based on time series can be passed through
Model, such as time recurrent neural networks model are realized, preferably to excavate each sequential correlation put between food product
Relationship.
Step S140: food product package information is generated according to each sequential correlation relationship put between food product.
Wherein, each sequential correlation relationship put between food product is primarily referred to as each put between food product in time dimension
Difference with contact, such as sequencing, time interval information for ordering etc..For example, passing through each elder generation put between food product
Sequentially be able to reflect the preference information of user afterwards: the food product selected at first is usually that different degree is higher, the higher meal of preference-score
Product;And the food product of rearmost point is then often that user is intended to tentative food product that is indefinite, arbitrarily clicking.It can be seen that by each
A sequencing put between food product can speculate the preferred diet of each user.For another example, it has been put between food product by each
Time interval be able to reflect user food product collocation habits information: if at least two have put the time interval of ordering between food product
Less than preset interval threshold value, then illustrate that user tends both to click this and at least two put food product, i.e. 1 point
The degree of association between food product is larger, preferably may arrange in pairs or groups as set meal;Conversely, if at least two have put ordering between food product
Time interval is greater than preset interval threshold value, then illustrates that at least two degree of association put between food product is smaller, may be not suitable for
It arranges in pairs or groups as set meal.
Those skilled in the art can also be excavated each sequential correlation put between food product by various other ways and be closed
System, to generate food product package information, the present invention to specific implementation detail without limitation.
It can be seen that the generation method of the food product set meal provided according to the present invention, can obtain corresponding with sample of users
History order record, and ordered each timing information of ordering for having put food product for including in record according to history, generation is ordered
Sample data;Sample data of ordering is trained by machine learning model, so that it is determined that it is each put between food product when
Sequence incidence relation, and food product package information is generated according to each sequential correlation relationship put between food product.Since history is ordered
Record is able to reflect order habit and the taste preference of most users, therefore, can be formulated by the order excavation of record of history
More reasonable set meal out.Also, since the timing information of ordering during ordering can further reflect user for food product
Preference, therefore, the present invention combine each timing information of ordering for having selected food product be trained and generate set meal, can make to generate
Set meal be more bonded user demand.
Fig. 2 shows a kind of flow charts of the generation method of food product set meal provided by Embodiment 2 of the present invention.Such as Fig. 2 institute
Show, this method comprises:
Step S200: mixing the sample with family is divided into a variety of user types in advance.
It specifically, in the present embodiment, can be in conjunction with age, gender, native place, preferred diet, the user etc. of sample of users
The various informations such as grade divide user type.Wherein, preferred diet can be divided according to personal taste, comprising: spicy, light,
Sweet food etc.;It can also be according to shops's Type division, comprising: fast food, western-style food, Chinese meal etc..User gradation can be according to user account
The factors such as registion time, frequency of ordering, and/or history consumption price section divide: for example, the frequency that will order is higher and goes through
The higher user in history consumption price section is divided into advanced level user;The frequency that will order is lower and history consumption price section is lower
User be divided into less advanced users.In short, the present invention to the division mode of user type without limitation, as long as happiness can will be ordered
Good similar user is divided into same type.
Step S210: it obtains corresponding with sample of users history and orders record.
Wherein, it for the precision and universality of lift scheme training, needs to collect user's conduct of largely ordering in advance
Sample of users, also, in order to cater to the demand of Different crowds, the user type of sample of users need to cover multiple types, with reflection
The hobby of ordering of all types of user.
Specifically, history record of ordering typically refers to: record of ordering caused by during once ordering.Wherein,
The primary process of ordering includes: the process that a user individually has dinner or several users have dinner jointly.When the process of ordering is a use
When the process that family is individually had dinner, a corresponding history, which is ordered, needs the user identity information comprising the user (such as can in record
To be user account information or user type information etc.), period information of ordering, put it is each put food product food product mark letter
It ceases and timing information of ordering.When the process of ordering is the process that several users have dinner jointly, a corresponding history is ordered note
The user identity information comprising the user, period information of ordering, each food product identification information for having put food product put are removed in record
And except timing information of ordering, the number information that has dinner can also be further included.Also, process is total to by several users when ordering
When with completing, the user identifier for having put the user that orders corresponding to food product can also be recorded further directed to each food product of having put
Information, to analyze the personal preference of each user.The information content for including in record in short, history is ordered is more comprehensive, more advantageous
In subsequent analysis.
Step S220: each timing information of ordering for having put food product for including in recording of being ordered according to history, generation are ordered
Sample data.
Specifically, order record for every history respectively, obtain this history order record in include each point
It orders corresponding to food product time and/or serial number of ordering;Ordered according to this history include in record each put food product institute
It is corresponding to order the time and/or serial number of ordering determines that this history is ordered each timing of ordering for having put food product for including in record
Information;According to this history order record in include each timing information of ordering for having put food product, generate one group gone through with this
History, which is ordered, records corresponding sample data of ordering.
For example, it is assumed that a history is ordered comprising following information in record: user " small red " is on June 6th, 2018 in north
Consume following food product in capital dining room: stewed fish with brown sauce (order time 12:08), hand beat eggplant (order time 12:09), pork steamed with ground rice flour (point
Eat time 12:15), Kung Pao chicken (order time 12:23), green salad (order time 12:30).Wherein, the point of stewed fish with brown sauce
Meal serial number 1, hand beat serial number 2 of ordering, the serial number 3 of ordering of pork steamed with ground rice flour, the order serial number 4, vegetable of Kung Pao chicken of eggplant
The serial number 5 of ordering of dish salad.Wherein, order corresponding to food product time and/or serial number of ordering determination are being put according to each
This history order record in include it is each put food product order timing information when, will directly can put corresponding to food product
Order and the time or order serial number or combination is determined as having put the timing information of ordering of food product.In addition, upper
It states in example, when scene of ordering is that more people order, it is also necessary to further record and each put the user that orders corresponding to food product.
For example, it is assumed that order in scene in two people, stewed fish with brown sauce, hand beat eggplant and Kung Pao chicken be user " small red " institute point, pork steamed with ground rice flour with
Green salad is user " little Huang " institute point, then in sample data of ordering, except needing to record each timing of ordering for having put food product
Except information, it is also necessary to record each user information of ordering for having put food product, thus reflect the hobby of different user.
Step S230: being trained sample data of ordering by machine learning model, with determination it is each put food product it
Between sequential correlation relationship.
In the present embodiment, machine learning model is the machine learning model based on time series, and specifically include: the time passs
Return neural network model.For example, LSTM (Long Short-Term Memory) is a kind of shot and long term memory network, it is suitable for locating
Be spaced and postpone relatively long critical event in reason and predicted time sequence, the present embodiment can be using LSTM model at
Reason, so as to according to each timing information of ordering for having put food product for including in sample data of ordering, excavate it is each put food product it
Between sequential correlation relationship.
Specifically, sample data of ordering is trained by LSTM model, each put between food product can be excavated
Sequential correlation relationship.For example, being able to reflect user for the preference of each food product according to each serial number of ordering for having put food product
Degree: serial number of ordering is more forward, illustrates that preference-score is higher;Order serial number more rearward, illustrates that preference-score is lower.Inventor exists
Find during realizing the present invention: user often clicks the food product that it is intended to favor clearly and very at first and therefore passes through
Serial number of ordering is able to reflect user preference.For another example, according to the interval between each time of ordering for having put food product, it is able to reflect meal
Product combined information: the interval between the time of ordering is less than intercombination preferably between the food product of preset interval threshold value, when ordering
Between between interval not less than preset interval threshold value food product between be then not suitable for being combined with each other.Inventor is of the invention in realization
It finds in the process: it is often preferably between the lesser food product of time interval of ordering to arrange in pairs or groups as set meal, therefore, by ordering
Time interval is able to reflect food product combined information.Wherein, preset interval threshold value can flexible setting, be preferably arranged to the not false think of of user
The interval threshold to link up to rope when ordering, for example, most users link up without thinking order when, between each food product between
Every being usually no more than 3 seconds, if exceeding 3 seconds, illustrate that user is thinking next set food product combination.Correspondingly, it in upper example, braises in soy sauce
Fish (order time 12:08) and hand, which beat eggplant (order time 12:09), can be used as one group of food product combined information.Specific training
When, on the one hand, the preference of each food product is determined according to each serial number of ordering for having put food product;It on the other hand, basis
Each time interval of ordering for having put food product determines food product combined information.In addition, also to come in conjunction with user number, type final true
The accuracy of preference and food product combined information is determined, only when same food product combined information is ordered field by multiple people repeatedly
When clicking in scape, can finally confirm whether this group of food product combined information be suitable.In short, can be excavated by training process
Each sequential correlation relationship put between food product out.The sequential correlation relationship refers to: it is all kinds of can be according to timing information of ordering
The food product incidence relation excavated.
Step S240: food product package information is generated according to each sequential correlation relationship put between food product.
Specifically, according to each sequential correlation relationship put between food product, each preference-score for having put food product is analyzed
And/or food product combined information;According to each preference-score for having put food product and/or food product combined information, food product set meal letter is generated
Breath.When it is implemented, the higher food product of preference-score can be determined as to the leading food product in set meal, to attract customer;And root
The combination food product mutually arranged in pairs or groups in set meal with leading food product is determined according to food product combined information.Concrete analysis process can pass through step
Training process in S230 is realized, it may be assumed that in the training process, has been put ordering for food product according to each and serial number and/or is ordered the time
Interval determines each preference-score for having put food product and/or food product combined information.Alternatively, can also be in the training in step S230
Secondary analysis is carried out further according to training result after process.
It, can also be into addition, when generating food product package information according to each sequential correlation relationship for having put between food product
One step combines preset set meal collocation rule to generate food product package information.Wherein, set meal collocation rule include it is following at least
One: (1) number of meals division rule: specifically may include a variety of set meal types such as two people meal, five people meal, ten people meal.Specific system
Periodically, it is divided in combination with the average volume of the flow of passengers of shops and the crowd of having dinner.(2) it dining Type division rule: can specifically wrap
Include family dinner party type, have a dinner party type, commercial affairs of work are received a visitor type etc..Wherein, family dinner party type is laid particular emphasis on quality-high and inexpensive, and
Commercial affairs type of receiving a visitor then lays particular emphasis on high-end and atmospheric improve grade.(3) meat and vegetables collocation rule: may include specifically between meat dish and vegetable dish
Commonly used collocation rule.For example, the vegetable dishes such as more greasy normal and light tasty and refreshing cold dish of meat dish such as mutton, trotter are arranged in pairs or groups.
(4) entree garnishes collocation rule: specifically may include the collocation rule etc. between entree and beverage, soup product.
Step S250: being pushed to user terminal for food product package information, so that user terminal carries out food product package information
Display.
Specifically, above-mentioned generated each food product can be shown by the default set meal column in preset food and drink APP
Package information.In addition, inventor has found in the implementation of the present invention: the displaying sequence of each food product in set meal is directly closed
It is that whether can select the set meal to user.If the food product that can more favor user comes position forward in set meal, have
Conducive to promoting user to select this set meal.Correspondingly, in the present embodiment, according to each sequential correlation put between food product
After relationship generates food product package information, the food product set generated is further determined according to each timing information of ordering for having put food product
The multiple food products for including in meal information show sequence information.This shows sequence information for reflecting showing sequentially for each food product
And/or show position.Correspondingly, food product package information is pushed to user terminal, so that user terminal is to food product package information
When being shown, the sequence information that shows of food product package information and multiple food products wherein included is pushed to user terminal,
So that user terminal sorts and shows to the multiple food products for including in food product package information according to the sequence information that shows of multiple food products
Show.It can be seen that in the present embodiment, it is possible to determining include in food product package information more according to the timing information of ordering of food product
A food product shows sequence information, to carry out rational sorting to multiple food products in set meal.When it is implemented, both can be by taking
Business device will show sequence information and be supplied to user terminal, so that user terminal shows sequence information to each set meal food product according to this
It is ranked up;Alternatively, can also be ranked up in advance to each set meal food product by server, and each set after sequence will be sequenced
Meal food product is directly pushed to user terminal, so that user terminal is directly rendered and shown to the sorted food product of server.
In addition, since businessman often releases a plurality of set meals simultaneously to attract the user of different groups, for the ease of
The user of each group quickly and efficiently filters out the set meal of optimum itself, in the present embodiment, when food product package information is
When multiple, after generating food product package information according to each sequential correlation relationship put between food product, further directed to each
A food product package information generates corresponding push official documents and correspondence information.The push official documents and correspondence information is used to illustrate the recommendation reason of this money set meal
By for example, can be the push official documents and correspondence information of following form: " fat reducing crowd specially enjoys ", " chief cooker recommend new product ", " your most normal point
A set meal ", " the highest set meal of head store sales volume ".Correspondingly, food product package information is being pushed to user terminal, for
When family terminal shows food product package information, specifically food product package information and its corresponding push official documents and correspondence information are pushed to
User terminal is associated with display with food product package information so that user terminal will push official documents and correspondence information, in order to which user makes properly
Selection.Wherein, the particular content of the push official documents and correspondence information can be determined according to the training result in step S230.
In addition, in order to be suitble to the personalized set meal of the user for different types of user push, in the present embodiment
Order sample data and food product package information in further include user type information, it is various types of in order to determine
The set meal type that user is had a preference for.Correspondingly, in this step, when food product package information being pushed to user terminal, selection with
The food product package information that the user type of user terminal matches is pushed.Specifically, due to including in sample data of ordering
Therefore user type information can determine the food product that various types of users are favored by training process respectively, and then make really
Corresponding user type information is further included in each money food product package information made.Correspondingly, for active user's terminal,
The user type of the user terminal is determined according to the user identity information of the user terminal, then, to its push and its user class
The food product package information that type matches, thus, it is possible to push different personalized set meals for different types of user, to cater to
The demand of all types of user.It certainly, in the present embodiment, can also be into other than carrying out personalized push according to user type
One step realizes the customized push effect for active user according to unique identifications such as user accounts, for example, can be with
It is ordered according to the history of the user account and is recorded as its and pushes the set meal for being suitable for the user customizedly.
In summary, the generation method of the food product set meal provided according to the present invention can obtain corresponding with sample of users
History order record, and ordered each timing information of ordering for having put food product for including in record according to history, generation is ordered
Sample data;Sample data of ordering is trained by machine learning model, so that it is determined that it is each put between food product when
Sequence incidence relation, and food product package information is generated according to each sequential correlation relationship put between food product.Since history is ordered
Record is able to reflect order habit and the taste preference of most users, therefore, can be formulated by the order excavation of record of history
More reasonable set meal out.Also, since the timing information of ordering during ordering can further reflect user for food product
Preference, therefore, the present invention combine each timing information of ordering for having selected food product be trained and generate set meal, can make to generate
Set meal be more bonded user demand.Also, the present invention can push different set meals for different types of user, additionally it is possible to
For the push official documents and correspondence information that each money set meal is arranged in pairs or groups different, and rational sorting is carried out to multiple food products in set meal, to improve
Push success rate.
In addition, in the above-described embodiments, can also be recommended further combined with the profit margin of food product.Specifically, exist
When generating food product package information according to each sequential correlation relationship for having put between food product, further combined with each food product of having put
Earnings information generates food product package information.For example, for each having put food product, determine this put the food materials information of food product and/or
Process information determines that this has put the cost information of food product according to food materials information and/or process information.Wherein, food materials information includes
Staple food material and/or non-staple foodstuff material, the cost information of food product can be calculated by food materials information.Process information refers specifically to the production of food product
Process, comprising: drain the oil, stir-fry, boiling in water for a while, then dress with soy, vinegar, etc. the various operations such as pot, steamed, the production side of food product is able to reflect by food product process information
Method, the complexity of production method also objectively determine the cost of the food product.Process is simpler, and food product cost is cheaper,
The more complicated food product cost of process is higher.It can be seen that the buying of food materials message reflection corresponding food materials of food product itself at
This, process information reflects the cost of labor of the corresponding cook of food product.When it is implemented, a food product cost can be trained in advance
Learning model, so that the food materials information and/or process information according to the food product determine the cost information of food product, to pass through machine
The mode of study promotes the accuracy of cost calculation.Then, it calculates the cost information for having put food product and has put determining for food product with this
Difference between valence information determines that this has put the earnings information of food product according to difference, final food product is determined according to earnings information
Package information.Difference is bigger, illustrates that profit space is bigger, more worth recommendation.Wherein, which can pass through
Price range of the similar food product in other shops is determined.
Embodiment three
Fig. 3 shows a kind of structural schematic diagram of the generating means of food product set meal of the offer of the embodiment of the present invention three, the dress
It sets and includes:
Module 31 is obtained, is ordered record suitable for obtaining corresponding with sample of users history;
Sample data generation module 32, suitable for ordered according to the history include in record each put ordering for food product
Timing information generates sample data of ordering;
Training module 33, it is each with determination suitable for being trained by machine learning model to the sample data of ordering
The sequential correlation relationship between food product is put;
Set meal generation module 34, suitable for generating food product set meal according to each sequential correlation relationship selected between food product
Information.
Optionally, the sample data generation module 32 is particularly adapted to:
Order record for every history respectively, obtain this history and order include in record each put food product it is right
Order time and/or the serial number of ordering answered;
Ordered according to this history include in record it is each put to order corresponding to food product the time and/or order
Serial number determines that this history is ordered each timing information of ordering for having put food product for including in record;
According to this history order record in include each timing information of ordering for having put food product, generate one group with
This history, which is ordered, records corresponding sample data of ordering.
Optionally, the set meal generation module 34 is particularly adapted to:
According to each sequential correlation relationship put between food product, analyze each preference-score for having put food product and/
Or food product combined information;
According to each preference-score for having put food product and/or food product combined information, food product package information is generated.
Optionally, the machine learning model is the machine learning model based on time series, and described based on time sequence
The machine learning model of column includes: time recurrent neural networks model.
Optionally, the set meal generation module 34 is particularly adapted to:
Food product package information is generated in conjunction with preset set meal collocation rule;Wherein, the set meal collocation rule includes following
At least one of: number of meals division rule, dining Type division rule, meat and vegetables collocation rule and entree garnishes collocation
Rule.
Optionally, described device further comprises:
Pushing module 35, suitable for the food product package information is pushed to user terminal, so that the user terminal is to institute
Food product package information is stated to be shown.
Optionally, the pushing module 35 is further adapted for: determining life according to each timing information of ordering for having put food product
At food product package information in include multiple food products show sequence information;By the food product package information and wherein include
The sequence informations that shows of multiple food products be pushed to user terminal, for the user terminal showing according to the multiple food product
Sequence information sorts and shows to the multiple food products for including in the food product package information.
Optionally, when the food product package information is multiple, the pushing module 35 is further adapted for: being directed to each meal
Product package information generates corresponding push official documents and correspondence information;The food product package information and its corresponding push official documents and correspondence information are pushed
To user terminal, so that the push official documents and correspondence information is associated with display with the food product package information by the user terminal.
Optionally, the pushing module 35 is further adapted for: the sample of users is divided into a variety of user types in advance,
And user type information is further included in order sample data and the food product package information;Selection and the user
The food product package information that the user type of terminal matches is pushed.
It can refer to the description of corresponding portion in embodiment of the method about the specific structure and working principle of above-mentioned modules,
Details are not described herein again.
Example IV
The embodiment of the present application four provides a kind of nonvolatile computer storage media, the computer storage medium storage
There is an at least executable instruction, which can be performed the life of the food product set meal in above-mentioned any means embodiment
At method.Executable instruction specifically can be used for so that processor executes corresponding each operation in above method embodiment.
Embodiment five
Fig. 4 shows the structural schematic diagram of according to embodiments of the present invention five a kind of electronic equipment, present invention specific implementation
Example does not limit the specific implementation of electronic equipment.
As shown in figure 4, the electronic equipment may include: processor (processor) 402, communication interface
(Communications Interface) 406, memory (memory) 404 and communication bus 408.
Wherein:
Processor 402, communication interface 406 and memory 404 complete mutual communication by communication bus 408.
Communication interface 406, for being communicated with the network element of other equipment such as client or other servers etc..
Processor 402, for executing program 410, in the generation method embodiment that can specifically execute above-mentioned food product set meal
Correlation step.
Specifically, program 410 may include program code, which includes computer operation instruction.
Processor 402 may be central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that electronic equipment includes can be same type of processor, such as one or more CPU;It can also
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 404, for storing program 410.Memory 404 may include high speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 510 specifically can be used for so that processor 502 executes corresponding each operation in above method embodiment.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize the prize drawing according to an embodiment of the present invention based on voice input information
The some or all functions of some or all components in system.The present invention is also implemented as being retouched here for executing
The some or all device or device programs (for example, computer program and computer program product) for the method stated.
It is such to realize that program of the invention can store on a computer-readable medium, or can have one or more signal
Form.Such signal can be downloaded from an internet website to obtain, be perhaps provided on the carrier signal or with it is any its
He provides form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (10)
1. a kind of generation method of food product set meal, comprising:
Corresponding with sample of users history is obtained to order record;
It is ordered each timing information of ordering for having put food product for including in record according to the history, generation is ordered sample data;
The sample data of ordering is trained by machine learning model, is closed with each timing put between food product of determination
Connection relationship;
Food product package information is generated according to each sequential correlation relationship put between food product.
2. according to the method described in claim 1, wherein, each having ordered of including in record of being ordered according to the history
The timing information of ordering of product generates the step of ordering sample data and specifically includes:
Order record for every history respectively, obtain this history order record in include each put corresponding to food product
It orders time and/or serial number of ordering;
Ordered according to this history include in record each put order corresponding to food product time and/or serial number of ordering
Determine that this history is ordered each timing information of ordering for having put food product for including in record;
According to this history order record in include each timing information of ordering for having put food product, generate one group with this
History, which is ordered, records corresponding sample data of ordering.
3. method according to claim 1 or 2, wherein described according to each sequential correlation put between food product
The step of relationship generation food product package information, specifically includes:
According to each sequential correlation relationship put between food product, each preference-score and/or meal for having selected food product is analyzed
Product combined information;
According to each preference-score for having put food product and/or food product combined information, food product package information is generated.
4. method according to claim 1 to 3, wherein the machine learning model is the machine based on time series
Learning model, and the machine learning model based on time series includes: time recurrent neural networks model.
5. method according to claim 1 to 4, wherein described to be closed according to each timing put between food product
The step of connection relationship generation food product package information, specifically includes:
Food product package information is generated in conjunction with preset set meal collocation rule;Wherein, the set meal collocation rule includes in following
At least one: number of meals division rule, dining Type division rule, meat and vegetables collocation rule and entree garnishes collocation rule.
6. -5 any method according to claim 1, wherein described to be closed according to each timing put between food product
After connection relationship generates the step of food product package information, further comprise:
The food product package information is pushed to user terminal, so that the user terminal shows the food product package information
Show.
7. described according to each sequential correlation relationship put between food product according to the method described in claim 6, wherein
After the step of generating food product package information, further comprise: being determined and generated according to each timing information of ordering for having put food product
Food product package information in include multiple food products show sequence information;
It is then described that the food product package information is pushed to user terminal, so that the user terminal is to the food product package information
The step of being shown specifically includes: the food product package information and multiple food products wherein included are showed sequence information
It is pushed to user terminal, so that the user terminal believes the food product set meal according to the sequence information that shows of the multiple food product
The multiple food products for including in breath sort and show.
8. a kind of generating means of food product set meal, comprising:
Module is obtained, is ordered record suitable for obtaining corresponding with sample of users history;
Sample data generation module, suitable for according to the history order record in include it is each put food product order timing letter
Breath generates sample data of ordering;
Training module has been ordered suitable for being trained by machine learning model to the sample data of ordering with determination is each
Sequential correlation relationship between product;
Set meal generation module, suitable for generating food product package information according to each sequential correlation relationship put between food product.
9. a kind of electronic equipment, comprising: processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus;
The memory executes the processor as right is wanted for storing an at least executable instruction, the executable instruction
Ask the corresponding operation of the generation method of food product set meal described in any one of 1-7.
10. a kind of computer storage medium, an at least executable instruction, the executable instruction are stored in the storage medium
Processor is set to execute the corresponding operation of generation method such as food product set meal of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810938844.9A CN109214955B (en) | 2018-08-17 | 2018-08-17 | Method and device for generating meal package |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810938844.9A CN109214955B (en) | 2018-08-17 | 2018-08-17 | Method and device for generating meal package |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109214955A true CN109214955A (en) | 2019-01-15 |
CN109214955B CN109214955B (en) | 2020-07-17 |
Family
ID=64988953
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810938844.9A Active CN109214955B (en) | 2018-08-17 | 2018-08-17 | Method and device for generating meal package |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109214955B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110555750A (en) * | 2019-07-29 | 2019-12-10 | 北京三快在线科技有限公司 | method and device for predicting number of people at dinner, 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 |
CN111210397A (en) * | 2020-01-10 | 2020-05-29 | 口碑(上海)信息技术有限公司 | Image processing method, image display method and device and electronic equipment |
WO2020192635A1 (en) * | 2019-03-22 | 2020-10-01 | 口碑(上海)信息技术有限公司 | Order placing method and device for set meal product |
CN112418974A (en) * | 2020-10-27 | 2021-02-26 | 北京思特奇信息技术股份有限公司 | Method and system for building block type telecommunication product and electronic equipment |
CN113362201A (en) * | 2021-06-07 | 2021-09-07 | 青岛海尔空调器有限总公司 | Ordering method and device based on air conditioner and intelligent air conditioner |
Citations (4)
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 |
CN105005907A (en) * | 2015-03-05 | 2015-10-28 | 张良均 | Dynamic intelligent food recommending method for catering service |
US20170262874A1 (en) * | 2016-03-10 | 2017-09-14 | Mastercard International Incorporated | Methods and system for identifying consumer preferences |
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 |
-
2018
- 2018-08-17 CN CN201810938844.9A patent/CN109214955B/en active Active
Patent Citations (4)
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 |
CN105005907A (en) * | 2015-03-05 | 2015-10-28 | 张良均 | Dynamic intelligent food recommending method for catering service |
US20170262874A1 (en) * | 2016-03-10 | 2017-09-14 | Mastercard International Incorporated | Methods and system for identifying consumer preferences |
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 |
Non-Patent Citations (1)
Title |
---|
王屯屯: "基于LSTM的在线商城商品推荐研究", 《现代计算机》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020192635A1 (en) * | 2019-03-22 | 2020-10-01 | 口碑(上海)信息技术有限公司 | Order placing method and device for set meal product |
CN110555750A (en) * | 2019-07-29 | 2019-12-10 | 北京三快在线科技有限公司 | method and device for predicting number of people at dinner, electronic equipment and readable storage medium |
CN110555750B (en) * | 2019-07-29 | 2022-06-07 | 北京三快在线科技有限公司 | Method and device for predicting number of people at dinner, 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 |
CN111210397A (en) * | 2020-01-10 | 2020-05-29 | 口碑(上海)信息技术有限公司 | Image processing method, image display method and device and electronic equipment |
CN111210397B (en) * | 2020-01-10 | 2021-09-10 | 口碑(上海)信息技术有限公司 | Image processing method, image display method and device and electronic equipment |
CN112418974A (en) * | 2020-10-27 | 2021-02-26 | 北京思特奇信息技术股份有限公司 | Method and system for building block type telecommunication product and electronic equipment |
CN113362201A (en) * | 2021-06-07 | 2021-09-07 | 青岛海尔空调器有限总公司 | Ordering method and device based on air conditioner and intelligent air conditioner |
CN113362201B (en) * | 2021-06-07 | 2022-09-06 | 青岛海尔空调器有限总公司 | Ordering method and device based on air conditioner and intelligent air conditioner |
Also Published As
Publication number | Publication date |
---|---|
CN109214955B (en) | 2020-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109214955A (en) | The generation method and device of food product set meal | |
US9633456B2 (en) | System and method for providing flavor advisement and enhancement | |
Freyne et al. | Recipe recommendation: accuracy and reasoning | |
US20140089321A1 (en) | Method and system to recommend recipes | |
Michel et al. | Perceptual attributes of poultry and other meat products: a repertory grid application | |
CN109191242A (en) | Food product method for pushing and device | |
KR20170073589A (en) | System and computer method for visually guiding a user to a current interest | |
CN109214956A (en) | Food product method for pushing and device | |
CN110458650A (en) | Method of Commodity Recommendation, device, electronic equipment and storage medium | |
CN108648059A (en) | Order recommends method and device | |
CN107230131A (en) | A kind of vegetable recommends method, apparatus and system | |
EP3678087A1 (en) | Computer system for proposing wine for consumption with food and method and program to be executed in said computer system | |
CN104200409A (en) | Method for matching taste selection information with application objects | |
US20200159750A1 (en) | System for measuring food weight | |
CN109447749A (en) | Merchandise news input method and device | |
JP2020510273A (en) | Cooking system | |
JP2019045980A (en) | Information processing apparatus, information processing method, and program | |
CN117350825A (en) | Shopping guide method and system based on large language model | |
CN110852299A (en) | Method and device for determining eating habits of customers | |
Lee et al. | Analysis of consumers’ preferences and price sensitivity to native chickens | |
CN113139120A (en) | Electronic equipment and recipe recommendation method and apparatus | |
JP6843597B2 (en) | Information processing equipment, food selection method and program | |
Cunningham et al. | An analysis of cooking queries: implications for supporting leisure cooking | |
CN112102922B (en) | Information recommendation method and device | |
JPH09218875A (en) | Interactive cooking retrieval device |
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 |