CN110189195A - A kind of method and device of commercial product recommending - Google Patents
A kind of method and device of commercial product recommending Download PDFInfo
- Publication number
- CN110189195A CN110189195A CN201910401580.8A CN201910401580A CN110189195A CN 110189195 A CN110189195 A CN 110189195A CN 201910401580 A CN201910401580 A CN 201910401580A CN 110189195 A CN110189195 A CN 110189195A
- Authority
- CN
- China
- Prior art keywords
- raw material
- identified
- user
- recommendations
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 239000013065 commercial product Substances 0.000 title claims abstract description 21
- 239000002994 raw material Substances 0.000 claims abstract description 194
- 238000012549 training Methods 0.000 claims abstract description 24
- 239000000463 material Substances 0.000 claims description 58
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 235000013305 food Nutrition 0.000 description 23
- 235000013311 vegetables Nutrition 0.000 description 19
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000006872 improvement Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 239000000047 product Substances 0.000 description 7
- 238000010411 cooking Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 235000019640 taste Nutrition 0.000 description 3
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of method and apparatus of commercial product recommending, the first identification model that the picture to be identified that user can be sent in the method passes through training in advance, to determine the object for including in the picture to be identified, and according to the corresponding relationship of each object and each raw material that pre-save, the corresponding raw material of the object is inquired, and then the raw material inquired is recommended into user as Recommendations.That is, bringing great advantage to the user without raw material needed for user actively online inquiry object to effectively raise the efficiency that user purchases raw material.
Description
Technical field
This application involves computer field more particularly to a kind of method and devices of commercial product recommending.
Background technique
Currently, user can be used installed in the terminal devices such as tablet computer, mobile phone shopping application (Application,
App shopping online) is carried out whenever and wherever possible, is brought great convenience to the daily life of user.
Before vegetable of the user needed for culinary art, food materials needed for needing first to purchase the vegetable.In general, user is not
In the case where understanding the vegetable, needing actively to surf the Internet inquires each food materials needed for the vegetable, then chooses one by one in shopping App
It selects each food materials inquired and places an order.It can be seen, in the prior art, it needs when user purchases each food materials by master
It moves and the operation such as inquires, selects, process is relatively complicated, that is, the efficiency that user purchases each food materials is lower, to bring not to user
Just.
It is then a urgent problem to be solved so how effectively to improve the efficiency that user purchases each food materials.
Summary of the invention
The embodiment of the present application provides a kind of method and device of commercial product recommending, purchases food to solve user in the prior art
When material the problem of inefficiency.
The application adopts the following technical solutions:
This application provides a kind of methods of commercial product recommending, comprising:
Obtain the picture to be identified that user sends；
By the first identification model of training in advance, the picture to be identified is identified, it is described to be identified with determination
The object for including in picture；
According to the corresponding relationship of each object and each raw material that pre-save, the corresponding raw material of the object is inquired；
Using the raw material inquired as Recommendations, and the Recommendations are recommended into the user.
Optionally, if not inquiring the corresponding raw material of the object, the method also includes:
By the second identification model of training in advance, the picture to be identified is identified, to identify the object
Corresponding raw material；
The raw material that will identify that recommends the user as Recommendations, and by the Recommendations.
Optionally, if local some or all of do not recorded in the Recommendations the corresponding merchandise news of commodity,
The method also includes:
According to the attribute of the object, determining other objects to match with the attribute, and will other described mesh
The corresponding raw material of object is marked as Recommendations, recommends the user.
Optionally, if the local corresponding merchandise news of part commodity not recorded in the Recommendations, the side
Method further include:
Determine the corresponding alternative materials of the object；
The raw material for replacing the part commodity, and the raw material that the part commodity will be replaced are chosen from the alternative materials
As Recommendations, the user is recommended.
Optionally, the method also includes:
Monitor the operation that the user executes the Recommendations；
Replacement operation is performed to the part commodity in the Recommendations if monitoring the user, according to the user
Other commodity for replacing the part commodity, adjust the corresponding relationship between the object and raw material.
Optionally, the Recommendations are recommended into the user, specifically included:
By Recommendations addition in the shopping cart of the user.
Optionally, the method also includes:
By the second identification model of training in advance, the picture to be identified is identified, it is described wait know to identify
The corresponding raw material of object for including in other picture；
By the first identification model of training in advance, the picture to be identified is identified, it is described to be identified with determination
The object for including in picture, specifically includes:
By the first identification model of training in advance and the raw material identified by second identification model to described
Picture to be identified is identified, with the object for including in the determination picture to be identified.
This application provides a kind of devices of commercial product recommending, comprising:
Module is obtained, for obtaining the picture to be identified of user's transmission；
Determining module identifies the picture to be identified, for the first identification model by training in advance with true
The object for including in the fixed picture to be identified；
Enquiry module inquires the object for the corresponding relationship according to each object and each raw material that pre-save
Corresponding raw material；
The Recommendations for using the raw material inquired as Recommendations, and are recommended the use by recommending module
Family.
This application provides a kind of computer readable storage medium, the storage medium is stored with computer program, described
The method of above-mentioned commercial product recommending is realized when computer program is executed by processor.
This application provides a kind of electronic equipment, including memory, processor and storage on a memory and can handled
The computer program run on device, the processor execute the method for realizing above-mentioned commercial product recommending when described program.
The application use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that
As can be seen that the first identification that the picture to be identified that user can be sent passes through training in advance in from the above
Model, to determine the object for including in the picture to be identified, and according to pair of each object and each raw material that pre-save
It should be related to, inquire the corresponding raw material of the object, and then the raw material inquired is recommended into user as Recommendations.That is,
Without raw material needed for user actively online inquiry object, so that the efficiency that user purchases raw material is effectively raised, to use
Family brings great convenience.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of the method for commercial product recommending in the embodiment of the present application；
Fig. 2 is the schematic diagram that Recommendations are recommended user by the network platform provided by the embodiments of the present application；
Fig. 3 is a kind of schematic device of commercial product recommending provided by the present application；
Fig. 4 is the electronic equipment schematic diagram provided by the present application corresponding to Fig. 1.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with the application specific embodiment and
Technical scheme is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the application one
Section Example, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall in the protection scope of this application.
Below in conjunction with attached drawing, the technical scheme provided by various embodiments of the present application will be described in detail.
Fig. 1 is a kind of flow diagram of the method for commercial product recommending in the embodiment of the present application, specifically includes the following steps:
S101: the picture to be identified that user sends is obtained.
It in the embodiment of the present application, can be by the picture of the object when user needs to purchase object corresponding raw material
Be uploaded to the network platform, the picture of the object that user that the network platform can will acquire sends as picture to be identified,
To be identified to the object in the picture to be identified during subsequent.
Wherein, object mentioned herein can refer to vegetable, cake and other items, and the corresponding raw material of object refers to group
At the food materials of vegetable, cake and other items.The network platform, can be by the object after identifying the object in picture to be identified
Corresponding raw material recommends user as Recommendations, to eliminate the corresponding raw material of user oneself active inquiry object
Complicated processes, bring great convenience to user.
In the embodiment of the present application, user can be by the picture of the object voluntarily shot by installing in mobile terminal
App be sent to the network platform, the picture for the object voluntarily searched for can also be sent to the network platform by the App,
Also or the link of the picture of the object can be sent to the network platform, the network platform can according to the link, get to
Identify picture.
Mobile terminal mentioned herein can refer to the electronic equipments such as the mobile phone of user, tablet computer, and the network platform is used
It can be server or computer etc. in obtaining equipment used in the picture to be identified that user sends.And for ease of description,
The method of commercial product recommending provided by the present application will be described in detail only using the network platform as executing subject below.
S102: by the first identification model of training in advance, identifying the picture to be identified, with determine it is described to
The object for including in identification picture.
It, can be by preset first identification model, to this after the network platform receives the picture to be identified of user's transmission
Picture to be identified is identified, to determine its object for being included from the picture to be identified.Wherein, mentioned herein
One identification model, which can be, pre- first passes through what the training of a large amount of training sample obtained.The staff of the network platform can collect greatly
The picture of each object of amount, and object corresponding to these pictures is marked out respectively.Then, the staff of the network platform
The picture of these marks can be input in first identification model as training sample and be trained.After completing training,
The network platform can be identified by first identification model, the picture to be identified sent to user.First identification model institute
The recognizer used is not defined specific recognizer herein for conventional algorithms such as neural networks.
S103: according to the corresponding relationship of each object and each raw material that pre-save, the corresponding original of the object is inquired
Material.
In the embodiment of the present application, the network platform pre-saves the corresponding relationship of each object Yu each raw material, is based on this,
The network platform, can be according to pair of each object and each raw material that pre-save after determining the object in picture to be identified
It should be related to, inquire the corresponding raw material of the object, and then during subsequent, the corresponding original of the object that will be inquired
Material recommends user as Recommendations.
S104: using the raw material inquired as Recommendations, and the Recommendations are recommended into the user.
The network platform can recommend user using the raw material inquired as Recommendations.As shown in Figure 2.
Fig. 2 is the schematic diagram that Recommendations are recommended user by the network platform provided by the embodiments of the present application.
User can shoot object by the mobile phone (mobile terminal) that oneself is held, with obtained object
Picture.The picture can be sent to the network platform by user, and the network platform can lead to using the picture as picture to be identified
The first identification model is crossed to identify the picture to be identified.The network platform determined from the picture to be identified it includes mesh
After marking object, the corresponding raw material of the object can be inquired, and then the raw material inquired is recommended into user as Recommendations.
Wherein, Recommendations can be added the shopping cart of the App in the customer mobile terminal by the network platform, and user can be in shopping cart
In check and decide whether to purchase these raw materials.
As can be seen that user is when purchasing the corresponding raw material of object, without by way of search in from the above
The picture of the object can be sent to the network platform, be passed through by the network platform by the corresponding raw material of the active inquiry object
First identification model identifies the object for including in picture, and then the corresponding raw material of the object inquired is recommended use
Family brings great side to user to eliminate the complicated processes of the corresponding raw material of user oneself active inquiry object
Just.
It should be noted that the corresponding relationship of each object and each raw material that save in the network platform is usually all to pass through people
The mode of work counted, is recorded, and in practical applications, since object is more various, so, some objects and former
The corresponding relationship of material may and be not recorded in the network platform.
Therefore, if the network platform does not inquire the object according to each object of record and the corresponding relationship of each raw material
(object identified from picture to be identified) corresponding raw material, then show not record in the network platform object with
The corresponding relationship of raw material.The picture to be identified can be input in the second identification model by the network platform, second to be known by this
Other model identifies the corresponding raw material of the object from the picture to be identified.
Wherein, the staff of the network platform can mark the picture for a large amount of each object being collected into advance
Note, that is, mark out raw material involved in each object, and using the picture of each object after mark as training sample to this
Two identification models are trained.And by the second identification model after training, it can know from the picture to be identified that user sends
Raw material corresponding to the object that Chu do not include in the picture to be identified, and the raw material that will identify that is recommended as Recommendations
User.
For the corresponding each raw material of each object of network platform local record, there may be part material not flat in network
It is sold on platform.For example, it is assumed that having recorded the corresponding raw material of object A in the network platform are as follows: raw material 1, raw material 2, raw material 3.Wherein,
It is not sold in 2 network platform of raw material.That is, having recorded the corresponding each raw material of object in the network platform, it is not intended to
The network platform be bound to sell these raw materials.
So the network platform using the corresponding each raw material of the object determined as each Recommendations recommend user it
Before, need first to inquire whether the corresponding merchandise news of each Recommendations is recorded in locally (if record there are commodity in the network platform
Merchandise news, then illustrate that the commodity are sold in the network platform).If so, each Recommendations can be recommended into user, if
The merchandise news of part commodity in each Recommendations is not inquired, then illustrates that this part commodity is not sold in the network platform.
And in order to guarantee the experience of user, the network platform can determine that other commodity of this part commodity can be substituted,
And by other commercial product recommendings to user.Specifically, after determining that this part commodity is sold not in the network platform, the network platform
It can determine the corresponding alternative materials of object (object identified from picture to be identified), and from alternative materials
Middle choose replaces the raw material of this part commodity as Recommendations, recommends user.
In the embodiment of the present application, in the network platform other than recording the corresponding relationship for having each object and each raw material, also
Record has the corresponding relationship of each object Yu each alternative materials.Wherein, for each object, the corresponding raw material of the object is
Refer to the conventional raw material for making the object, and the corresponding alternative materials of the object can replace the conventional raw material of the object.
For example, it is assumed that the corresponding conventional food materials (raw material) of a vegetable A (object) are as follows: food materials a, food materials b, food materials c, food materials d, and this
Four kinds of food materials can be replaced respectively by food materials e, food materials f, food materials g, food materials h, so, food materials e, food materials f, food materials g, food materials h
For the corresponding substitution food materials (i.e. alternative materials) of vegetable B.
It, can be according to record if not selling the part material in the corresponding raw material of object in the network platform based on this
The object and alternative materials corresponding relationship, choose replace this part material alternative materials recommended as Recommendations
User.
In addition, if the network platform some or all of does not record in the Recommendations determined the corresponding quotient of commodity locally
Product information then illustrates that the corresponding part material of the object or whole raw materials are not sold in the network platform, then the network platform
Other objects to match with the attribute can be determined according to the attribute of the object, and then by other objects pair
The raw material answered recommends user as Recommendations.
Wherein, the attribute of object mentioned herein refers to the information that can show that the object feature, for example, vegetable
The information such as the affiliated style of cooking, taste can effectively show the actual characteristic of vegetable, so, these information can be referred to as vegetable
Attribute.
So if part material or whole raw materials in the corresponding raw material of object are not sold in the network platform,
The network platform can select raw material corresponding with object similar in the object as recommendation quotient according to the attribute of the object
Product recommend user.For example, it is assumed that part material or whole raw materials that the network platform inquires vegetable A be not in the network platform
Upper sale, then the network platform can according to attributes such as the affiliated style of cooking of vegetable A, tastes, determine with the affiliated style of cooking of vegetable A,
The identical vegetable B of taste, and then user is recommended using the corresponding raw material of vegetable B as Recommendations.
It should be noted that attribute of the network platform according to object, determines other targets to match with the attribute
After object, it can inquire whether the corresponding raw material of other objects is sold in the network platform.If inquiring other targets
The corresponding raw material of object has sale in the network platform, then can push away using the corresponding raw material of other objects as Recommendations
It recommends to user.And if the part material inquired in the corresponding raw material of other objects is not sold in the network platform, can
Further to determine the corresponding alternative materials of other objects, and therefrom choose the raw material conduct for replacing this part material
Recommendations recommend user.
In the embodiment of the present application, after Recommendations are recommended user by the network platform, user can be monitored, these is pushed away
Operation performed by commodity is recommended, replacement operation is performed to the part commodity in Recommendations if monitoring the user, it can root
Other commodity that this part commodity is replaced according to the user, are adjusted the corresponding relationship between the object and raw material.
It is mentioned herein to monitor the user replacement operation is performed to the part commodity in Recommendations, can there are many
Situation.For example, if user removes the part commodity that the network platform is added in the Recommendations of shopping cart from shopping cart,
And other commodity are added into shopping cart again, then the network platform monitors the user and executes to the part commodity in Recommendations
Replacement operation.For another example if user is replaced the part commodity in Recommendations, and replaced commodity are carried out
Lower single operation, then the lower single operation that the network platform can be executed according to the user, monitor the user will be in Recommendations
Part commodity are replaced.Other the case where, just do not have been illustrated in detail herein.
After monitoring the user and performing replacement operation to the part commodity in Recommendations, it can be replaced according to the user
Other commodity of this part commodity are changed, the corresponding relationship between object and raw material is adjusted, that is, to network platform local record
Corresponding relationship between object and raw material is modified.For example, it is assumed that having recorded the corresponding raw material of object A in the network platform
Are as follows: raw material 1, raw material 2, raw material 3, raw material 4.After this four raw materials are recommended user as Recommendations by the network platform, prison
It controls user and the raw material 3 has been substituted for raw material 5, then the network platform can be corresponding with raw material by the object A of precedence record
Relationship adjustment are as follows: object A corresponds to raw material 1, raw material 2, raw material 4, raw material 5.
Certainly, the commodity that the network platform can also be replaced according to user, to the object of precedence record and alternative materials it
Between corresponding relationship be adjusted.Specifically, after the commodity for determining user's replacement, can from the object of local record with
In corresponding relationship between alternative materials, whether the inquiry replaced commodity of user (commodity are raw material) is recorded in the object
In corresponding alternative materials.If so, otherwise can will be used without the corresponding relationship adjusted between the object and alternative materials
The replaced commodity in family are added in the corresponding alternative materials of the object.
For example, it is assumed that the corresponding alternative materials of object are as follows: raw material 1, raw material 2, raw material 3, the replaced commodity of user are as follows:
Raw material 4, the network platform can determine that raw material a4 does not appear in this by inquiring the corresponding relationship of the object and alternative materials
In the corresponding alternative materials of object, therefore, the corresponding alternative materials of object can be adjusted are as follows: raw material 1, raw material 2, raw material
3, raw material 4.
When different user is replaced operation for the Recommendations of same object, to the selected replacement of same commodity
Commodity afterwards are possibly different from.For example, it is assumed that the network platform is by the corresponding raw material 1 of object, raw material 2, raw material 3 as recommendation
When commodity recommend user A and user B respectively, raw material 1 is replaced with raw material 4 (i.e. replaced commodity) by user's selection, and is used
Raw material 1 is replaced with raw material 5 by family B selection.
So if the network platform is directed to the selected replaced quotient of Recommendations of same object according to each user
Product constantly adjust the corresponding relationship of the object and raw material, then not only will increase the adjustment frequency of the corresponding relationship, while can
The object that can gradually cause the corresponding relationship to be recorded is not matched that with raw material, that is, according to gradually correspondence adjusted
The raw material recorded in relationship, it may not be possible to produce corresponding object.
Therefore, the network platform can count the Recommendations that different user is directed to same object within the set time
Replacement when being replaced is as a result, in turn according to the replacement of each user as a result, determining how pair of adjustment object and raw material
It should be related to.
For example, it is assumed that the network platform determines that 73% user is directed to by one month (in setting time) of statistics past
The replacement result that the corresponding raw material 1 of object is replaced are as follows: raw material 1 has been substituted for raw material 3 (i.e. replaced commodity),
Raw material 1 has been substituted for raw material 4 by 13% user, and raw material 1 has been substituted for raw material 5 by 14% user.Therefore, the network platform can
With the replacing as a result, by the corresponding relationship of the object of local record and raw material for raw material 1 according to most users
Raw material 1 is adjusted to raw material 3.
It should be noted that the raw material that the network platform can also be identified by the second identification model, to the first identification mould
Whether the object that type identifies is verified, correct to be verified the object that the first identification model identifies.
Specifically, the network platform can identify picture to be identified by the second identification model of training in advance, with
Determine raw material corresponding to the object for including in the picture to be identified.Then, the network platform first can be identified by this
Model and the raw material identified by the second identification model identify the picture to be identified, to determine that this is to be identified
The object for including in picture.
That is, the raw material that the network platform can be identified according to the second identification model, and local record each object with
The corresponding relationship of raw material inquires object corresponding to the raw material identified, and then the object and the first identification model is known
Not Chu object be compared.
Wherein, if the two is identical, then the object for illustrating that the first identification model identifies is errorless, if the two is not
Together, then information can be sent to the staff of the network platform, to prompt the staff to including in the picture to be identified
Object carries out manual identified, and the first identification model of adjustment or the second identification model.Certainly, the feelings different in the two
Under condition, the network platform can also be according to the obtained recognition result of any one identification model in the two identification models, really
The object for including in the picture to be identified is made, and then recommends use using the corresponding raw material of the object as Recommendations
Family.
In addition, after the network platform inquires raw material corresponding to the object identified by the first identification model, it can also
To identify the picture to be identified by the second identification model, the raw material identified, and by the raw material inquired with identify
Raw material be compared, and then according to comparison result, carry out the Recommendations that true directional user is recommended.
Wherein, when the raw material that inquires is not exactly the same with the raw material that identifies, the network platform can will be inquired
Raw material and the raw material identified take union, and then recommend user using raw material included in union as Recommendations.For example,
Assuming that corresponding to for object A, the corresponding raw material of object A that the network platform inquires are as follows: raw material 1, raw material 2, raw material 3,
The raw material identified by the second identification model are as follows: raw material 1, raw material 3, raw material 4.The network platform can by the raw material inquired and
The raw material identified takes union, and then raw material 1, raw material 2, raw material 3, raw material 4 are recommended user as Recommendations.
It certainly, can also basis after the network platform determines that the raw material inquired and the raw material identified are not exactly the same
The raw material identified, corresponding relationship (or pair between object and alternative materials of object and raw material to local record
Should be related to) it is adjusted.Continue to use the example above, it, can after the raw material determining the raw material of inquiry and identifying is not exactly the same
The corresponding raw material of object to be adjusted are as follows: raw material 1, raw material 2, raw material 3, raw material 4.
It, can also be according to object (or the recommendation quotient identified after Recommendations are recommended user by the network platform
Product), determine other commodity mutually arranged in pairs or groups with the object (or the Recommendations), and then these other commodity are pushed away together
It recommends to user.For example, it is assumed that being determined while the corresponding raw material of vegetable A is recommended user as Recommendations by the network platform
Vegetable A and commodity a, commodity b phase are arranged in pairs or groups out, and (collocation of so-called phase refers to body when user eats vegetable A, commodity a and commodity b simultaneously
Test preferably), and then commodity a, commodity b can be recommended into user together with the Recommendations determined together.
The above are the methods for the commercial product recommending that one or more embodiments of the application provide, and are based on same thinking, this
Application additionally provides the device of corresponding commercial product recommending, as shown in Figure 3.
Fig. 3 is a kind of schematic device of commercial product recommending provided by the present application, is specifically included:
Module 301 is obtained, for obtaining the picture to be identified of user's transmission；
Determining module 302, for being identified to the picture to be identified by the first trained in advance identification model,
With the object for including in the determination picture to be identified；
Enquiry module 303 inquires the target for the corresponding relationship according to each object and each raw material that pre-save
The corresponding raw material of object；
Recommending module 304 for using the raw material inquired as Recommendations, and the Recommendations is recommended described
User.
Optionally, described device further include:
Identification module 305, for being identified to the picture to be identified by the second trained in advance identification model,
To identify the corresponding raw material of the object；
The recommending module 304 is specifically used for, the raw material that the identification module 305 is identified as Recommendations, and
The Recommendations are recommended into the user.
Optionally, if local some or all of do not recorded in the Recommendations the corresponding merchandise news of commodity, institute
Recommending module 304 is stated to be specifically used for, according to the attribute of the object, determining other objects to match with the attribute,
And the corresponding raw material of other objects is recommended into the user as Recommendations.
Optionally, if the local corresponding merchandise news of part commodity not recorded in the Recommendations, the recommendation
Module 304 is specifically used for, and determines the corresponding alternative materials of the object；It is chosen from the alternative materials and replaces the part
The raw material of commodity, and the raw material of the part commodity will be replaced as Recommendations, recommend the user.
Optionally, described device further include:
Monitoring module 306, the operation that the Recommendations are executed for monitoring the user；If monitoring the user
Replacement operation is performed to the part commodity in the Recommendations, other quotient of the part commodity are replaced according to the user
Product adjust the corresponding relationship between the object and raw material.
Optionally, the recommending module 304 is specifically used for, and the Recommendations are added the shopping cart in the user
In.
Optionally, the identification module 305 is specifically used for, by the second identification model of training in advance, to described wait know
Other picture is identified, to identify the corresponding raw material of object for including in the picture to be identified；
The determining module 302 is specifically used for, and knows by the first identification model of training in advance and by described second
The raw material that other model identifies identifies the picture to be identified, with the target for including in the determination picture to be identified
Object.
The embodiment of the present application also provides a kind of computer readable storage medium, which is stored with computer journey
Sequence, computer program can be used for executing the method for the commercial product recommending that above-mentioned Fig. 1 is provided.
The embodiment of the present application also provides the schematic configuration diagrams of electronic equipment shown in Fig. 4.As described in Figure 4, in hardware layer
Face, the electronic equipment include processor, internal bus, network interface, memory and nonvolatile memory, are also possible to wrap certainly
Include hardware required for other business.Processor is right into memory from corresponding computer program is read in nonvolatile memory
After run, the method to realize commercial product recommending described in above-mentioned Fig. 1.Certainly, other than software realization mode, this specification is simultaneously
It is not excluded for other implementations, such as logical device or the mode of software and hardware combining etc., that is to say, that following process flow
Executing subject be not limited to each logic unit, be also possible to hardware or logical device.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware
DescriptionLanguage)、Confluence、CUPL(Cornell University Programming
Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、
PALASM, RHDL (Ruby Hardware Description Language) etc., most generally use VHDL at present
(Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog.
Those skilled in the art, which also will be apparent to the skilled artisan that, only needs that slightly programming in logic is simultaneously with above-mentioned several hardware description languages by method flow
It is programmed into integrated circuit, so that it may be readily available the hardware circuit for realizing the logical method process.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group
Part, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (10)
1. a kind of method of commercial product recommending characterized by comprising
Obtain the picture to be identified that user sends；
By the first identification model of training in advance, the picture to be identified is identified, with the determination picture to be identified
In include object；
According to the corresponding relationship of each object and each raw material that pre-save, the corresponding raw material of the object is inquired；
Using the raw material inquired as Recommendations, and the Recommendations are recommended into the user.
2. the method as described in claim 1, which is characterized in that described if not inquiring the corresponding raw material of the object
Method further include:
By the second identification model of training in advance, the picture to be identified is identified, to identify that the object is corresponding
Raw material；
The raw material that will identify that recommends the user as Recommendations, and by the Recommendations.
3. method according to claim 1 or 2, which is characterized in that if the local part not recorded in the Recommendations
Or the corresponding merchandise news of entire service, then the method also includes:
According to the attribute of the object, determining other objects to match with the attribute, and will other described objects
Corresponding raw material recommends the user as Recommendations.
4. method according to claim 1 or 2, which is characterized in that if the local part not recorded in the Recommendations
The corresponding merchandise news of commodity, then the method also includes:
Determine the corresponding alternative materials of the object；
From the alternative materials choose replace the part commodity raw material, and will replace the part commodity raw material as
Recommendations recommend the user.
5. the method as described in claim 1, which is characterized in that the method also includes:
Monitor the operation that the user executes the Recommendations；
Replacement operation is performed to the part commodity in the Recommendations if monitoring the user, is replaced according to the user
Other commodity of the part commodity, adjust the corresponding relationship between the object and raw material.
6. the method as described in claim 1, which is characterized in that the Recommendations are recommended the user, are specifically included:
By Recommendations addition in the shopping cart of the user.
7. the method as described in claim 1, which is characterized in that the method also includes:
By the second identification model of training in advance, the picture to be identified is identified, to identify the figure to be identified
The corresponding raw material of the object for including in piece；
By the first identification model of training in advance, the picture to be identified is identified, with the determination picture to be identified
In include object, specifically include:
By the first identification model of training in advance and the raw material identified by second identification model to described wait know
Other picture is identified, with the object for including in the determination picture to be identified.
8. a kind of device of commercial product recommending characterized by comprising
Module is obtained, for obtaining the picture to be identified of user's transmission；
Determining module identifies the picture to be identified, for the first identification model by training in advance to determine
State the object for including in picture to be identified；
It is corresponding to inquire the object for the corresponding relationship according to each object and each raw material that pre-save for enquiry module
Raw material；
The Recommendations for using the raw material inquired as Recommendations, and are recommended the user by recommending module.
9. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with computer program, the calculating
The described in any item methods of the claims 1~7 are realized when machine program is executed by processor.
10. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the described in any item sides of the claims 1~7 when executing described program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910401580.8A CN110189195A (en) | 2019-05-14 | 2019-05-14 | A kind of method and device of commercial product recommending |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910401580.8A CN110189195A (en) | 2019-05-14 | 2019-05-14 | A kind of method and device of commercial product recommending |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110189195A true CN110189195A (en) | 2019-08-30 |
Family
ID=67716329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910401580.8A Pending CN110189195A (en) | 2019-05-14 | 2019-05-14 | A kind of method and device of commercial product recommending |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110189195A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110599307A (en) * | 2019-09-17 | 2019-12-20 | 北京三快在线科技有限公司 | Commodity recommendation method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447708A (en) * | 2014-08-28 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information offering method and information offering device |
| CN105631722A (en) * | 2015-07-23 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Service information push method, service information push system and terminal |
| CN107301592A (en) * | 2017-07-19 | 2017-10-27 | 北京京东尚科信息技术有限公司 | The method and device excavated for commodity substitute |
| CN107861972A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | The method and apparatus of the full result of display of commodity after a kind of user's typing merchandise news |
| CN107862562A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | A kind of method and device that selection progress commercial product recommending is liked according to the picture of user |
| CN108596718A (en) * | 2018-04-17 | 2018-09-28 | 合肥美的智能科技有限公司 | Menu pushing method and system and computer equipment |
| CN109242017A (en) * | 2018-08-30 | 2019-01-18 | 杨镇蔚 | Intelligent identification Method, device and the equipment of object information |
-
2019
- 2019-05-14 CN CN201910401580.8A patent/CN110189195A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447708A (en) * | 2014-08-28 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information offering method and information offering device |
| CN105631722A (en) * | 2015-07-23 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Service information push method, service information push system and terminal |
| CN107301592A (en) * | 2017-07-19 | 2017-10-27 | 北京京东尚科信息技术有限公司 | The method and device excavated for commodity substitute |
| CN107861972A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | The method and apparatus of the full result of display of commodity after a kind of user's typing merchandise news |
| CN107862562A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | A kind of method and device that selection progress commercial product recommending is liked according to the picture of user |
| CN108596718A (en) * | 2018-04-17 | 2018-09-28 | 合肥美的智能科技有限公司 | Menu pushing method and system and computer equipment |
| CN109242017A (en) * | 2018-08-30 | 2019-01-18 | 杨镇蔚 | Intelligent identification Method, device and the equipment of object information |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110599307A (en) * | 2019-09-17 | 2019-12-20 | 北京三快在线科技有限公司 | Commodity recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033156B (en) | Method and device for determining business activity effect | |
| CN109472296A (en) | A kind of model training method and device promoting decision tree based on gradient | |
| CN107368510B (en) | A kind of shop search ordering method and device | |
| CN108345539A (en) | A kind of method and apparatus for carrying out AB tests | |
| CN109389412A (en) | A kind of method and device of training pattern | |
| US20230274340A1 (en) | Automating the creation of listings using augmented reality computer technology | |
| CN109271587A (en) | A kind of page generation method and device | |
| CN108874831A (en) | A kind of information recommendation method and device | |
| CN110163666A (en) | A kind of method and device of commercial product recommending | |
| CN110378400A (en) | A kind of model training method and device for image recognition | |
| CN110148013A (en) | A kind of user tag distribution forecasting method, apparatus and system | |
| CN110532295A (en) | A kind of method and device of computer-implemented information processing, information inquiry | |
| CN109345285A (en) | A kind of movable put-on method, device and equipment | |
| CN107093094A (en) | The dissemination method and device of a kind of evaluation information | |
| CN111177562B (en) | Recommendation ordering processing method and device for target object and server | |
| CN110060085A (en) | It is a kind of to parse method, system and the equipment being distributed under advertising objective crowd line | |
| CN109598285A (en) | A kind of processing method of model, device and equipment | |
| CN109003090A (en) | risk control method and device | |
| CN110517095A (en) | A kind of method and device for launching advertisement | |
| CN107577660A (en) | Category information recognition methods, device and server | |
| CN107451204A (en) | A kind of data query method, apparatus and equipment | |
| CN110189195A (en) | A kind of method and device of commercial product recommending | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
| CN108537616A (en) | A kind of method and device of Information Sharing | |
| CN110414572A (en) | A kind of method and device of image recognition |
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 |