CN106547365A - The method and apparatus of commercial product recommending - Google Patents
The method and apparatus of commercial product recommending Download PDFInfo
- Publication number
- CN106547365A CN106547365A CN201510593446.4A CN201510593446A CN106547365A CN 106547365 A CN106547365 A CN 106547365A CN 201510593446 A CN201510593446 A CN 201510593446A CN 106547365 A CN106547365 A CN 106547365A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- preference
- label
- server
- 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 41
- 239000013065 commercial product Substances 0.000 title description 12
- 230000002349 favourable effect Effects 0.000 claims abstract description 67
- 235000013311 vegetables Nutrition 0.000 claims description 29
- 235000019688 fish Nutrition 0.000 description 10
- 235000002568 Capsicum frutescens Nutrition 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 239000000047 product Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 241001622901 Scomberomorus commerson Species 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of method to user's Recommendations, and on the server, the server can get the preference information of multiple users and favorable comment commodity, and methods described includes for application：First user is being received after the access that terminal is initiated, according to the matching degree with first user preference information, is determining at least one other user as similar preferences user；According to the preference information of first user, at least one commodity are selected as the commodity for recommending first user in the favorable comment commodity of similar preferences user, and return to the terminal.By the technical scheme of the application so that Recommendations disclosure satisfy that the preference of first user, with higher accuracy, the efficiency that first user obtains information is improve.
Description
Technical field
The application is related to technical field of data processing, more particularly to a kind of method and apparatus of commercial product recommending.
Background technology
With the development and the popularization of intelligent terminal of network technology, the information that people can be obtained from network
It is more and more, also increasingly get used to using such information for assisting oneself to complete various work and life thing
.For example, many users often in online enquiries restaurant and vegetable, are determined before eating out
Where have dinner.
In order to meet the demand of user, some application programs in terminal are with to user's Recommendations
Or the function of trade company.In prior art, on typically comprehensive line or entity trade company to the description of itself commodity,
What trade company threw in runs the factors such as other services (such as parking stall, wireless network) of advertisement, trade company, knot
Consumer record before sharing family comes the trade company or commodity that certainly directional user recommends.This way of recommendation does not have
The demand of consideration different user is different, and the commodity for recommending user are likely to not meet the happiness of the user
Good, accuracy is relatively low, have impact on the efficiency that user obtains information.
The content of the invention
In view of this, the application provides a kind of method to user's Recommendations, applies on the server,
The server can get the preference information of multiple users and favorable comment commodity, and methods described includes：
Receiving first user after the access that terminal is initiated, according to first user preference information
With degree, determine at least one other user as similar preferences user；
According to the preference information of first user, at least one is selected in the favorable comment commodity of similar preferences user
Commodity are used as the commodity for recommending first user, and return to the terminal.
A kind of method to user's Recommendations that the application is provided, on application terminal, methods described includes：
According to the instruction of first user, initiate to access to server；
The Recommendations of the reception server return simultaneously show first user；The Recommendations are by server
Preference information according to first user in the favorable comment commodity of similar preferences user selects to draw；It is described similar
Preferences user is by server according to determining with the matching degree of first user preference information.
Present invention also provides a kind of device to user's Recommendations, applies on the server, the clothes
Business device can get the preference information and favorable comment commodity of multiple users, and described device includes：
Similar preferences user unit, for receiving first user after the access that terminal is initiated, according to
With the matching degree of first user preference information, determine at least one other user as similar preferences user；
Recommendations select unit, for the preference information according to first user, in similar preferences user
At least one commodity are selected in favorable comment commodity as the commodity for recommending first user, and returns to the end
End.
A kind of device to user's Recommendations that the application is provided, on application terminal, described device includes：
Access and initiate unit, for the instruction according to first user, initiate to access to server；
Recommendations receiving unit, the Recommendations returned for the reception server simultaneously show first user；
The Recommendations are by server according to the preference information of first user in the favorable comment commodity for being similar to preferences user
Middle selection draws；The similar preferences user matches journey according to first user preference information by server
Degree determines.
From above technical scheme, embodiments herein is by having similar preference from first user
Other users favorable comment commodity in select to first user recommend commodity so that Recommendations can be expired
The preference of sufficient first user, with higher accuracy, improves the efficiency that first user obtains information.
Description of the drawings
Fig. 1 is a kind of flow chart of application Method of Commodity Recommendation on the server in the embodiment of the present application；
Fig. 2 is a kind of flow chart of the Method of Commodity Recommendation applied in terminal in the embodiment of the present application；
Fig. 3 is the interface schematic diagram of user's selection taste label in the application application example；
Fig. 4 is the interface schematic diagram that user input preference describes label in the application application example；
Fig. 5 is the interface schematic diagram that user preference information and favorable comment commodity are shown in the application application example；
Fig. 6 is a kind of hardware structure diagram of terminal or server；
Fig. 7 is a kind of logical structure of application device for recommending the commodity on the server in the embodiment of the present application
Figure；
Fig. 8 is a kind of building-block of logic of the device for recommending the commodity applied in terminal in the embodiment of the present application.
Specific embodiment
Embodiments herein proposes a kind of method of new commercial product recommending, can be based on the inclined of multiple users
Good information and favorable comment commodity, the favorable comment commodity of the other users for recommending there is similar preference with which to user,
Recommendations are enabled to meet the hobby of user, so as to the accuracy and user that improve recommendation obtain letter
The efficiency of breath, to solve problems of the prior art.
In embodiments herein, mutually may have access to by network between terminal and server, wherein, eventually
End can be mobile phone, panel computer, PC (Personal Computer, PC), notebook,
Deng equipment；Server can be a physically or logically server, or by two or more
Share the physically or logically server of different responsibilities, mutually cooperate with to realize server in the embodiment of the present application
Various functions.The embodiment of the present application to terminal, the species of server, and between terminal and server
The type of communication network, agreement etc. are not limited.
The method of commercial product recommending flow process on the server is as shown in figure 1, flow process such as Fig. 2 in terminal
It is shown.Commodity can be it is any be supplied to consumer articles or service in entity trade company or Xian Shang trade companies, such as
Clothes, shoes and hats, digital product, the vegetable in restaurant, hair caring service, manicure service etc..
In terminal, step 210, according to the instruction of first user, is initiated to access to server.
In embodiments herein, first user sends instruction to terminal, makes terminal initiate to arrive server
Access.Application scenarios to C/S (Client/Server, client/server) pattern, first user can
With the client-side program by starting terminal come to server initiation access, it is also possible to by client journey
The function of starting Recommendations in sequence to initiate to access to server；First user can also be by making terminal
The mode of the chained address that access is associated with server, initiates to access to server.The enforcement of the application
Example is not limited.
On the server, step 110, receiving first user after the access that terminal is initiated, according to
With the matching degree of first user preference information, determine at least one other user as similar preferences user.
In embodiments herein, server can get the preference information of multiple users and favorable comment commodity.
Preference information is determined by user, reflection preference in person to factors such as the type of merchandise, styles；Preference
Information can by user from primary input description its preference text；Can also be by user input by servicing
Device provides the selection gone out done in the option relevant with preference.Favorable comment commodity are the business that user once bought
Think to be worth the commodity for recommending others in product, in the information of usual favorable comment commodity, will also include the commodity institute
The trade company of category, including Xian Shang trade companies or entity trade company.
User can in terminal inputting preferences information and favorable comment commodity, uploaded onto the server by terminal, take
Preference information from multiple users and favorable comment commodity are stored in local or can pass through network access by business device
Memorizer on, for carrying out commercial product recommending to user；The preference information and favorable comment commodity of user input
Can be stored in terminal, from server when to certain user's Recommendations, from the terminal of other users
It is upper to obtain in real time.Embodiments herein is not limited.
In one embodiment, preference information includes that preference describes label, typically certain of user preferences
Plant or certain class commodity, for example, to vegetable, user can be by " Sichuan cuisine ", " cake ", " wheaten food "
The word for so representing a certain type vegetable describes label as the preference of oneself, it is also possible to by " dumpling ",
" Fish Filets in Hot Chili Oil " so represent the word of certain concrete vegetable and describe label as the preference of oneself.
In another embodiment, in addition to preference describes label, preference can also in preference information, be included
Attribute class label, for classifying to certain attribute of user preference.Attributes preferred class label because
Specific commodity are different and different, and server can arrange with selectable value one and arrive multiple attributes preferred
Class label, is selected most reflect the value of oneself preference by user in these selectable value.By taking clothing as an example,
Can be using style as an attributes preferred class label, by user in " leisure ", " America and Europe ", " multiple
Make a choice in the selectable value such as Gu ", " commuting ", " Korea Spro system ".Using attributes preferred class label energy
Embodying the hobby of user, describing that label combines with preference can be more smart for the angle of enough dependences itself
The preference of true positioning user.
Server receives first user after the access that terminal is initiated, if defeated before first user
Entered preference information to be uploaded to server and be saved, then server can obtain the from the information for preserving
The preference information of one user；Otherwise server may require first user inputting preferences information be simultaneously in terminal
Server is uploaded to by terminal.For example, represent input circle that preference describes label from terminal to first user
Face, or represent the selection interface that preference describes the inputting interface and attributes preferred class label of label；Eventually
The preference of end reception first user input describes label or preference describes label and attributes preferred classification mark
After label, upload onto the server.
According to the preference information of first user, server is by the preference information of first user and other users
Preference information is matched, and selects at least one other user as similar preferences user according to matching degree.
According to the needs of concrete application scene, server can select various matching algorithms (such as collaborative filtering)
With different selection standards, embodiments herein do not limit.
Label being described using preference as in the implementation of preference information, can according to first user phase
Same and/or similar preference describes the number of label, and at least one user's conduct is selected in other users
Similar preferences user.For example, first user preference can be described " Fish Filets in Hot Chili Oil " and the user in label
A preferences describe " Fish Filets in Hot Chili Oil " in label and are considered to match completely, by the preference description mark of first user
In label, " Fish Filets in Hot Chili Oil " are considered fuzzy matching with " fish " that user's B preferences are described in label, and have been
Full matching gives the matching score value higher than fuzzy matching；Total matching point of label is described according to all preferences
Value is ranked up to other users, using several users of score value highest as first user similar preference
User.For another example, each can be described what label was matched completely with least one preference of first user
Other users will have identical preference to describe the number of label with first user as similar preferences user
Other users more than 0 are used as similar preferences user.
Label and attributes preferred class label are being described using preference as in the implementation of preference information, can
With with least one with the other users of the attributes preferred class label of first user identical in, according to
Identical with first user and/or similar preference describes the number of label, selects at least one user's conduct
Similar preferences user.Server contrasts the attributes preferred class label of first user and other users first,
Other users only with attributes preferred class label identical with first user are only possible to become first user
Similar preferences user.Select in the other users with least one identical attributes preferred class label
The mode of similar preferences user refers to the explanation of epimere, repeats no more.
On the server, step 120, according to the preference information of first user, in similar preferences user
At least one commodity for recommending first user are selected in favorable comment commodity, and returns to the terminal.
After server determines similar preferences user, as the preference of these users generally will not be used with first
Family is identical, has frequently included the commodity different from first user preference in the favorable comment commodity of these users.
Preference information of the server according to first user, filters out in the favorable comment commodity of these users and meets first
One of user preference arrives multiple commodity, as the commodity for recommending first user, returns to terminal.
Including to preference information, preference describes the implementation of label and (such as label and preference category described with preference
Property class label as preference information implementation), can in the favorable comment commodity of similar preferences user,
At least one is selected to describe commodity that label is associated as recommending first user with the preference of first user
Commodity.For example, if the preference of first user is described have in label " Fish Filets in Hot Chili Oil ", it is similar to preference and uses
The favorable comment commodity of the user A in family include " Fish Filets in Hot Chili Oil-Boiled Fish township ", can by " Fish Filets in Hot Chili Oil-
Boiled Fish township " is used as the vegetable for recommending first user.For another example, if the preference description mark of first user
Have in label " wheaten food ", and the favorable comment commodity of the user B in similar preferences user include " Spanish mackerel dumpling
- Dong Xinglou ", as Spanish mackerel dumpling belongs to wheaten food, then can using " Spanish mackerel dumpling-Dong Xinglou " as
Recommend the vegetable of first user.
Label and attributes preferred class label are being described using preference as in the implementation of preference information, is being
The preference of user is more accurately matched, item property class label can be set for user's favorable comment commodity,
Attributes preferred classification of the item property class label for classifying to the attribute of favorable comment commodity, with user
Label is identical or corresponding.Still by taking clothing as an example, corresponding to using style as attributes preferred class label,
It is same using style as item property class label, and equally using " leisure ", " America and Europe ", " answer
Gu ", " commuting ", " Korea Spro system " etc. are used as selectable value.In the favorable comment commodity of user input oneself,
For these commodity, item property class label is set, so, favorable comment business of the server in similar preferences user
Select when recommending the commodity of first user in product, can be at least one item property class label and the
In the attributes preferred class label identical favorable comment commodity of one user, one is selected to arrive multiple and first user
Preference the associated commodity for recommending first user of label are described.That is, to belonging to commodity
The favorable comment commodity of property class label, at least one and first user only in its item property class label
Attributes preferred class label it is identical when, be only possible to selected as the commodity for recommending first user.
In terminal, step 220, the Recommendations that the reception server is returned simultaneously show first user.
Recommendations are selected according to the preference information of first user in the favorable comment commodity of similar preferences user by server
Select and draw；Similar preferences user is by server according to determining with the matching degree of first user preference information.
To portable mobile terminal, may be referred to the current location of mobile terminal to carry out to first user
Commercial product recommending.Current location information is sent to server (such as in the access initiated to server by terminal
The middle carrying current location information of itself, or send to server after receiving the instruction of server)；Service
After device gets the current location information of terminal, when the commodity recommended are selected for first user, can be by
The geographical position of the affiliated trade company of preference information, commodity according to first user and the distance of terminal current location,
At least one commodity are selected as the commodity for recommending first user in the favorable comment commodity of similar preferences user.
In such manner, it is possible to give him by the commercial product recommending near first user, user is made more efficiently to obtain what is needed
Information, has provided the user more facilities.
It can be seen that, in embodiments herein, based on the preference information of multiple users and favorable comment commodity,
According to the preference of first user, from the favorable comment commodity of the other users with first user with similar preference
Select to first user the commodity recommended so that Recommendations can meet the hobby of first user, improve
The accuracy recommended, and improve the efficiency that first user obtains information.
Additionally, the information of trade company's offer is mainly based upon in prior art carrying out commercial product recommending formula, easily
Those trade companies for lacking promotional are omitted, recommends the information of institute's foundation not comprehensive enough；And the reality of the application
Apply example and the information of user's offer is based primarily upon being recommended, even if not carrying out the good of the trade company of promotional
Commodity will not also be missed, and the coverage rate of Recommendations is more broad.
During example is applied at one of the application, the commodity recommended to user are the vegetables in restaurant, user's
In preference information, using taste as attributes preferred class label, preference is used as with vegetable or vegetable type
Description label.
In this application example, user passes through the App (application program) installed on its mobile terminal and service
Device is communicated.Server end is prefixed the selectable value of several taste, by user by the App entering
Row is selected, and the interface of user's selection taste label can be as shown in Figure 3.Preference describe label can by with
The vegetable or vegetable type that family is liked according to which is voluntarily input into, and user input preference describes the interface of label can
With as shown in Figure 4.User will think in the restaurant of its post-consumer that recommendable vegetable also enters into App
In, as favorable comment commodity.
In this example, there can be user individual work(as " the cuisines circle " of a user in APP
Can option, label that user beats to various cuisines and the cuisines oneself liked, shop etc. can be remembered
Record in " cuisines circle " option, so that user checks and safeguard " the cuisines circle " of oneself.Should in different
With scene of in scene, such as doing shopping, user personality function option can be " shopping circle " etc., this
The personalized function option of sample can reflect the hobby of user itself.
The taste of user input, preference are described mobile terminal label and favorable comment commodity are stored in locally, and
It is uploaded to server.User can check the above- mentioned information of oneself in the App, and its interface can be such as 5
It is shown.In Fig. 5, " my taste " is the taste label that the user selects, and " cuisines hobby " is this
The preference of user describes label, and " recommendation cuisines " are the favorable comment commodity of the user.
Server preserves from terminal the taste of each user for receiving, preference and describes label and favorable comment commodity.
When the user M of inputting preferences information starts the App in terminal, terminal initiates server
Access.After setting up with server and being connected, according to the instruction of server, terminal is by current location information
Upload onto the server.
Server extracts the taste label and preference of the user M for preserving and describes label, by the mouth of user M
Taste label is matched with the taste label of other users, filters out at least one taste label and user M
Taste label identical other users；In the user for filtering out, label is described into the preference of user M
Label is described with the preference of these users to be matched, from high to low these users is entered according to matching degree
Row sequence, selects matching degree highest N (N is natural number) individual user as similar preferences user.
In the favorable comment commodity (i.e. vegetable and its affiliated trade company) of similar preferences user, server according to
The preference of family M describes label, and the screening from favorable comment commodity describes label with the preference of user M and is associated
Vegetable, to the vegetable that filters out according to describing belonging to the correlation degree of label, vegetable with user's M preferences
The factors such as the distance of trade company and user M current locations, other information on services of trade company are ranked up, will row
Sequence highest K (K is natural number) individual vegetable and its affiliated trade company are used as the vegetable for recommending user M.
The vegetable for recommending user M is returned to terminal by server, will recommend vegetable and its described by terminal
Trade company is presented to user M.
Corresponding with the realization of above-mentioned flow process, embodiments herein additionally provides a kind of application on the server
The device of commercial product recommending, and a kind of device of the commercial product recommending applied in terminal.Both devices
To be realized by software, it is also possible to realized by way of hardware or software and hardware combining.It is implemented in software
As a example by, as the device on logical meaning, it is CPU (the Central Process by terminal or server
Unit, central processing unit) corresponding computer program instructions are read into what operation in internal memory was formed.From
For hardware view, in addition to the CPU shown in Fig. 6, internal memory and nonvolatile memory, commodity
The terminal that the device of recommendation is located generally also includes for carrying out other hardware such as chip of wireless signal transmitting-receiving,
The server that the device of commercial product recommending is located generally also include for realize board of network communicating function etc. its
His hardware.
Fig. 7 show a kind of device to user's Recommendations of the present embodiment offer, applies in server
On, the server can get the preference information of multiple users and favorable comment commodity, and described device includes
Similar preferences user unit and Recommendations select unit, wherein：Similar preferences user unit is in receipts
To first user after the access that terminal is initiated, according to the matching degree with first user preference information,
Determine at least one other user as similar preferences user；Recommendations select unit is for according to first
The preference information of user, selects at least one commodity as recommendation in the favorable comment commodity of similar preferences user
To the commodity of first user, and return to the terminal.
In a kind of implementation, the preference information includes that preference describes label；The similar preferences user
Unit specifically for：Receiving first user after the access that terminal is initiated, according to first user phase
Same and/or similar preference describes the number of label, and at least one user's conduct is selected in other users
Similar preferences user；The Recommendations select unit specifically for：In the favorable comment business of similar preferences user
In product, at least one is selected to describe commodity that label is associated as recommending the with the preference of first user
The commodity of one user, and return to the terminal.
In a kind of upper implementation, the preference information also includes attributes preferred class label；It is described similar
Preferences user unit specifically for：First user is being received after the access that terminal is initiated, with extremely
In few other users with the attributes preferred class label of first user identical, according to first user
Identical and/or similar preference describes the number of label, selects at least one user to use as similar preference
Family.
Further, the server can also get the item property class label of user's favorable comment commodity,
Corresponding to the attributes preferred class label of the user；The Recommendations select unit specifically for：
The attributes preferred class label identical favorable comment commodity of at least one item property class label and first user
In, select one commodity that label is associated are described with the preference of first user as recommending the to multiple
The commodity of one user, and return to the terminal.
Optionally, the commodity include vegetable；The attributes preferred class label includes taste；It is described inclined
Describing well label includes vegetable or vegetable type.
Optionally, described device also includes terminal current location unit, for obtaining its present bit from terminal
Confidence ceases；The Recommendations select unit specifically for：According to the preference information of first user, commodity
The geographical position of affiliated trade company and the distance of terminal current location, in the favorable comment commodity of similar preferences user
At least one commodity are selected as the commodity for recommending first user, and returns to the terminal.
Fig. 8 show a kind of device to user's Recommendations of the present embodiment offer, on application terminal,
Described device includes accessing initiates unit and Recommendations receiving unit, wherein：Accessing initiation unit is used for
According to the instruction of first user, initiate to access to server；Recommendations receiving unit is used to receive service
The Recommendations of device return simultaneously show first user；The Recommendations are by server according to first user
Preference information in the favorable comment commodity of similar preferences user select to draw；The similar preferences user is by taking
Business device is determined according to the matching degree with first user preference information.
Optionally, the preference information includes that preference describes label, or preference describes label and attributes preferred
Class label；Described device also includes preference information uploading unit, for receiving the inclined of first user input
Describe well label or preference describes label and attributes preferred class label, and upload onto the server.
Optionally, described device also includes current location uploading unit, for sending terminal to server
Current location information；The Recommendations are by belonging to server is according to the preference information of first user, commodity
The geographical position of trade company and the distance of terminal current location, select in the favorable comment commodity of similar preferences user
Draw.
The preferred embodiment of the application is the foregoing is only, it is not to limit the application, all at this
Within the spirit and principle of application, any modification, equivalent substitution and improvements done etc. should be included in
Within the scope of the application protection.
In a typical configuration, computing device includes one or more processors (CPU), input/output
Interface, network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory
And/or the form, such as read only memory (ROM) or flash memory (flash RAM) such as Nonvolatile memory (RAM).
Internal memory is the example of computer-readable medium.
Computer-readable medium include permanent and non-permanent, removable and non-removable media can by appoint
What method or technique is realizing information Store.Information can be computer-readable instruction, data structure, program
Module or other data.The example of the storage medium of computer include, but are not limited to phase transition internal memory (PRAM),
Static RAM (SRAM), dynamic random access memory (DRAM), it is other kinds of with
Machine access memorizer (RAM), read only memory (ROM), Electrically Erasable Read Only Memory
(EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk are stored or which
His magnetic storage apparatus or any other non-transmission medium, can be used to store the letter that can be accessed by a computing device
Breath.Define according to herein, computer-readable medium does not include temporary computer readable media (transitory
Media), such as the data signal and carrier wave of modulation.
Also, it should be noted that term " including ", "comprising" or its any other variant be intended to it is non-
Exclusiveness is included, so that a series of process, method, commodity or equipment including key elements is not only wrapped
Include those key elements, but also including other key elements being not expressly set out, or also include for this process,
The intrinsic key element of method, commodity or equipment.In the absence of more restrictions, " included by sentence
One ... " key element that limits, it is not excluded that in the process including the key element, method, commodity or set
Also there is other identical element in standby.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer journey
Sequence product.Therefore, the application can using complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.And, the application can wherein include calculating using at one or more
Machine usable program code computer-usable storage medium (including but not limited to disk memory, CD-ROM,
Optical memory etc.) on the form of computer program implemented.
Claims (18)
1. a kind of method to user's Recommendations, applies on the server, it is characterised in that the clothes
Business device can get the preference information and favorable comment commodity of multiple users, and methods described includes：
Receiving first user after the access that terminal is initiated, according to first user preference information
With degree, determine at least one other user as similar preferences user；
According to the preference information of first user, at least one is selected in the favorable comment commodity of similar preferences user
Commodity are used as the commodity for recommending first user, and return to the terminal.
2. method according to claim 1, it is characterised in that the preference information includes that preference is retouched
State label；
The basis and the matching degree of first user preference information, determine at least one other user's conduct
Similar preferences user, including：The individual of label is described according to identical with first user and/or similar preference
Number, selects at least one user in other users as similar preferences user；
The preference information according to first user, selects at least in the favorable comment commodity of similar preferences user
One commodity as the commodity for recommending first user, including：In the favorable comment commodity of similar preferences user,
At least one is selected to describe commodity that label is associated as recommending first user with the preference of first user
Commodity.
3. method according to claim 2, it is characterised in that the preference information also includes preference
Attribute class label；
The basis and the matching degree of first user preference information, determine at least one other user's conduct
Similar preferences user, including：Have at least one with the attributes preferred class label of first user identical
Other users in, the number of label is described according to identical with first user and/or similar preference, select
At least one user is selected as similar preferences user.
4. method according to claim 3, it is characterised in that the server can also get
The item property class label of user's favorable comment commodity, corresponding to the attributes preferred class label of the user；
The preference information according to first user, selects at least in the favorable comment commodity of similar preferences user
One commodity as the commodity for recommending first user, including：In at least one item property class label
In the attributes preferred class label identical favorable comment commodity of first user, select one to multiple with first
The preference of user describes the associated commodity of label as the commodity for recommending first user.
5. the method according to claim 3 or 4, it is characterised in that the commodity include vegetable；
The attributes preferred class label includes taste；The preference describes label includes vegetable or vegetable type.
6. the method according to Claims 1-4 any one, it is characterised in that methods described is also
Including：Its current location information is obtained from terminal；
The preference information according to first user, selects at least in the favorable comment commodity of similar preferences user
One commodity as the commodity for recommending first user, including：According to the preference information of first user, business
The geographical position of the affiliated trade company of product and the distance of terminal current location, in the favorable comment commodity of similar preferences user
At least one commodity of middle selection are used as the commodity for recommending first user.
7. a kind of method to user's Recommendations, on application terminal, it is characterised in that methods described bag
Include：
According to the instruction of first user, initiate to access to server；
The Recommendations of the reception server return simultaneously show first user；The Recommendations are by server
Preference information according to first user in the favorable comment commodity of similar preferences user selects to draw；It is described similar
Preferences user is by server according to determining with the matching degree of first user preference information.
8. method according to claim 7, it is characterised in that the preference information includes that preference is retouched
Label is stated, or preference describes label and attributes preferred class label；
Methods described also includes：The preference of reception first user input describes label or preference describes label
With attributes preferred class label, and upload onto the server.
9. method according to claim 7, it is characterised in that methods described also includes：To service
Device sends the current location information of terminal；
Preference information of the Recommendations by server according to first user, the geography of the affiliated trade company of commodity
Position and the distance of terminal current location, in the favorable comment commodity of similar preferences user select to draw.
10. a kind of device to user's Recommendations, applies on the server, it is characterised in that described
Server can get the preference information of multiple users and favorable comment commodity, and described device includes：
Similar preferences user unit, for receiving first user after the access that terminal is initiated, according to
With the matching degree of first user preference information, determine at least one other user as similar preferences user；
Recommendations select unit, for the preference information according to first user, in similar preferences user
At least one commodity are selected in favorable comment commodity as the commodity for recommending first user, and returns to the end
End.
11. devices according to claim 10, it is characterised in that the preference information includes preference
Description label；
The similar preferences user unit specifically for：Receiving the access that first user is initiated by terminal
Afterwards, the number of label is described according to identical with first user and/or similar preference, in other users
At least one user is selected as similar preferences user；
The Recommendations select unit specifically for：In the favorable comment commodity of similar preferences user, select
At least one describes commodity that label is associated as the business for recommending first user with the preference of first user
Product, and return to the terminal.
12. devices according to claim 11, it is characterised in that the preference information also includes inclined
Good attribute class label；
The similar preferences user unit specifically for：Receiving the access that first user is initiated by terminal
Afterwards, in at least one other users with the attributes preferred class label of first user identical, root
The number of label is described according to identical with first user and/or similar preference, selects at least one user to make
To be similar to preferences user.
13. devices according to claim 12, it is characterised in that the server can also be obtained
To the item property class label of user's favorable comment commodity, corresponding to the attributes preferred class label of the user；
The Recommendations select unit specifically for：In at least one item property class label and first
In the attributes preferred class label identical favorable comment commodity of user, one is selected to multiple and first user
Preference describes the associated commodity of label as the commodity for recommending first user, and returns to the terminal.
14. devices according to claim 12 or 13, it is characterised in that the commodity include dish
Product；The attributes preferred class label includes taste；The preference describes label includes vegetable or vegetable class
Type.
15. devices according to claim 10 to 13 any one, it is characterised in that the dress
Putting also includes：Terminal current location unit, for obtaining its current location information from terminal；
The Recommendations select unit specifically for：According to belonging to the preference information of first user, commodity
The geographical position of trade company and the distance of terminal current location, select in the favorable comment commodity of similar preferences user
At least one commodity are used as the commodity for recommending first user, and return to the terminal.
16. a kind of devices to user's Recommendations, on application terminal, it is characterised in that described device
Including：
Access and initiate unit, for the instruction according to first user, initiate to access to server；
Recommendations receiving unit, the Recommendations returned for the reception server simultaneously show first user；
The Recommendations are by server according to the preference information of first user in the favorable comment commodity for being similar to preferences user
Middle selection draws；The similar preferences user matches journey according to first user preference information by server
Degree determines.
17. devices according to claim 16, it is characterised in that the preference information includes preference
Label is described, or preference describes label and attributes preferred class label；
Described device also includes：Preference information uploading unit, the preference for receiving first user input are retouched
State label or preference describes label and attributes preferred class label, and upload onto the server.
18. devices according to claim 16, it is characterised in that described device also includes：Currently
Position uploading unit, for the current location information of terminal is sent to server；
Preference information of the Recommendations by server according to first user, the geography of the affiliated trade company of commodity
Position and the distance of terminal current location, in the favorable comment commodity of similar preferences user select to draw.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510593446.4A CN106547365A (en) | 2015-09-17 | 2015-09-17 | The method and apparatus of commercial product recommending |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510593446.4A CN106547365A (en) | 2015-09-17 | 2015-09-17 | The method and apparatus of commercial product recommending |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106547365A true CN106547365A (en) | 2017-03-29 |
Family
ID=58362715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510593446.4A Pending CN106547365A (en) | 2015-09-17 | 2015-09-17 | The method and apparatus of commercial product recommending |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106547365A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256513A (en) * | 2017-06-19 | 2017-10-17 | 数据堂（北京）科技股份有限公司 | Method and device is recommended in a kind of collocation of object |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN107910044A (en) * | 2017-10-09 | 2018-04-13 | 北京京东尚科信息技术有限公司 | object push method and system |
| CN109345175A (en) * | 2018-10-10 | 2019-02-15 | 江苏满运软件科技有限公司 | Source of goods method for pushing, system, equipment and storage medium based on driver's matching degree |
| CN110782325A (en) * | 2019-10-31 | 2020-02-11 | 深圳市云积分科技有限公司 | Member information recommendation method and device |
| CN111159555A (en) * | 2019-12-30 | 2020-05-15 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN111582905A (en) * | 2020-03-26 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Target object acquisition method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408960A (en) * | 2007-10-12 | 2009-04-15 | 阿里巴巴集团控股有限公司 | Method and apparatus for recommendation of personalized information |
| CN101853463A (en) * | 2009-03-30 | 2010-10-06 | 北京邮电大学 | Collaborative filtering recommending method and system based on client characteristics |
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| CN103345699A (en) * | 2013-07-10 | 2013-10-09 | 湖南大学 | Personalized food recommendation method based on commodity forest system |
| CN104731866A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Individual gourmet recommending method based on position |
-
2015
- 2015-09-17 CN CN201510593446.4A patent/CN106547365A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408960A (en) * | 2007-10-12 | 2009-04-15 | 阿里巴巴集团控股有限公司 | Method and apparatus for recommendation of personalized information |
| CN101853463A (en) * | 2009-03-30 | 2010-10-06 | 北京邮电大学 | Collaborative filtering recommending method and system based on client characteristics |
| CN102411754A (en) * | 2011-11-29 | 2012-04-11 | 南京大学 | Personalized recommendation method based on commodity property entropy |
| CN103345699A (en) * | 2013-07-10 | 2013-10-09 | 湖南大学 | Personalized food recommendation method based on commodity forest system |
| CN104731866A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Individual gourmet recommending method based on position |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256513A (en) * | 2017-06-19 | 2017-10-17 | 数据堂（北京）科技股份有限公司 | Method and device is recommended in a kind of collocation of object |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN107910044A (en) * | 2017-10-09 | 2018-04-13 | 北京京东尚科信息技术有限公司 | object push method and system |
| CN109345175A (en) * | 2018-10-10 | 2019-02-15 | 江苏满运软件科技有限公司 | Source of goods method for pushing, system, equipment and storage medium based on driver's matching degree |
| CN109345175B (en) * | 2018-10-10 | 2021-08-03 | 江苏满运软件科技有限公司 | Goods source pushing method, system, equipment and storage medium based on driver matching degree |
| CN110782325A (en) * | 2019-10-31 | 2020-02-11 | 深圳市云积分科技有限公司 | Member information recommendation method and device |
| CN111159555A (en) * | 2019-12-30 | 2020-05-15 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
| CN111582905A (en) * | 2020-03-26 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Target object acquisition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106547365A (en) | The method and apparatus of commercial product recommending | |
| CN103514204B (en) | Information recommendation method and device | |
| WO2019056661A1 (en) | Search term pushing method and device, and terminal | |
| US10929913B2 (en) | Systems, methods, and computer program products for intelligently processing and manipulating a subject image according to consumer data | |
| CN107424043A (en) | A kind of Products Show method and device, electronic equipment | |
| Quelch et al. | All business is local: Why place matters more than ever in a global, virtual world | |
| CN107111591A (en) | Session and the state of certification are transmitted between devices | |
| KR102227552B1 (en) | System for providing context awareness algorithm based restaurant sorting personalized service using review category | |
| US20150199752A1 (en) | Electronic commerce using social media | |
| CN103425658A (en) | Commodity information storing and searching method, mobile terminal and server | |
| US20130091130A1 (en) | Systems and methods that utilize preference shields as data filters | |
| US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
| US20200226651A1 (en) | Methods and systems for product discovery in user generated content | |
| CN111259281B (en) | Method and device for determining merchant label and storage medium | |
| CN107092609A (en) | A kind of information-pushing method and device | |
| CN107220854A (en) | A kind of method and device for sending electronic ticket | |
| Nguyen et al. | Using micro-reviews to select an efficient set of reviews | |
| CN111967924A (en) | Commodity recommendation method, commodity recommendation device, computer device, and medium | |
| US20230030560A1 (en) | Methods and systems for tagged image generation | |
| KR101350079B1 (en) | Device for providing information, method for providing information, and computer-readable recording medium storing program for providing information | |
| CN106779926A (en) | Correlation rule generation method, device and terminal | |
| CN115795136A (en) | Data processing method, device and equipment | |
| CN108076439A (en) | For the method and apparatus based on wireless access point PUSH message | |
| CN116228342B (en) | Commodity recommendation method and device and computer readable storage medium | |
| JPWO2020129527A1 (en) | Receipt processing device, control method, and program |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1235129 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170329 |
|
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: WD Ref document number: 1235129 Country of ref document: HK |