CN104268154A - Recommended information providing method and device - Google Patents
Recommended information providing method and device Download PDFInfo
- Publication number
- CN104268154A CN104268154A CN201410443502.1A CN201410443502A CN104268154A CN 104268154 A CN104268154 A CN 104268154A CN 201410443502 A CN201410443502 A CN 201410443502A CN 104268154 A CN104268154 A CN 104268154A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- recommendation
- perpetual object
- environment information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a recommended information providing method and device. The method comprises the steps of acquiring first environment information corresponding to a user, wherein the first environment information is determined based on user operation; determining an attention object and/or scene mode corresponding to the first environment information according to the first environment information; determining at least one piece of recommended information corresponding to the user based on the attention object and/or scene mode.
Description
Technical field
The present invention relates to field of computer technology, particularly relating to a kind of for providing the method and apparatus of recommendation information.
Background technology
In prior art, when carrying out information recommendation to user, generally determine the demand of user according to static data messages such as the historical search data of user, to provide relevant recommendation information to user.That is, in the mode of prior art, user's request cannot be determined based on the current state etc. of user, therefore cannot the current demand of clear consumer positioning accurately, also cannot provide maximally related recommendation information for user.
Summary of the invention
The object of this invention is to provide a kind of for providing the method and apparatus of recommendation information.
According to an aspect of the present invention, providing a kind of for providing the method for recommendation information, wherein, said method comprising the steps of:
-obtain the first environment information corresponding with user, wherein, described first environment information is determined based on user operation;
-according to described first environment information, determine the perpetual object corresponding with described first environment information and/or scene mode;
-based on described perpetual object and/or scene mode, determine at least one the recommendation information corresponding with described user, to present described at least one recommendation information to described user.
According to an aspect of the present invention, additionally provide a kind of for providing the recommendation apparatus of recommendation information, wherein, described recommendation apparatus comprises:
For obtaining the device of the first environment information corresponding with user, wherein, described first environment information is determined based on user operation;
For according to described first environment information, determine the perpetual object corresponding with described first environment information and/or the device of scene mode;
For based on described perpetual object and/or scene mode, determine at least one the recommendation information corresponding with described user, to present the device of described at least one recommendation information to described user.
Compared with prior art, the present invention has the following advantages: can environmentally information to determine the focus that user is current and current residing scene thereof, and determine based on the current focus of user and/or current residing scene the demand that user is current, to provide relevant recommendation information to this user, make provided recommendation information more meet the current demand of user, improve the accuracy that current information is recommended.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 illustrates according to of the present invention a kind of for providing the method flow diagram of recommendation information;
Fig. 2 illustrates according to of the present invention a kind of for providing the structural representation of the recommendation apparatus of recommendation information.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 illustrates according to of the present invention a kind of for providing the method for recommendation information.Method according to the present invention comprises step S1, step S2 and step S3.
Wherein, method according to the present invention is realized by the recommendation apparatus be contained in computer equipment.Described computer equipment comprise a kind of can according in advance setting or the instruction stored, automatically carry out the electronic equipment of numerical evaluation and/or information processing, its hardware includes but not limited to microprocessor, special IC (ASIC), programmable gate array (FPGA), digital processing unit (DSP), embedded device etc.Described computer equipment comprises the network equipment and/or subscriber equipment.
Wherein, the described network equipment includes but not limited to the server group that single network server, multiple webserver form or the cloud be made up of a large amount of main frame or the webserver based on cloud computing (Cloud Computing), wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection.Wherein, the network equipment according to the present invention is connected with subscriber equipment, to provide recommendation information to this subscriber equipment.
Described subscriber equipment includes but not limited to that any one can to carry out the electronic product of man-machine interaction with user by modes such as keyboard, mouse, telepilot, touch pad or voice-operated devices, such as, laptop computer, panel computer, smart mobile phone, PDA, handheld device etc.
Preferably, described subscriber equipment comprises as mobile terminals such as smart mobile phones.
According to a preferred embodiment of the present invention, described recommendation apparatus is contained in and can carries out in the network equipment of data transmission with subscriber equipment.
According to another kind of preferred version of the present invention, described recommendation apparatus is contained in mobile terminal.
Wherein, described subscriber equipment and the network residing for the network equipment include but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN etc.
It should be noted that; described subscriber equipment, the network equipment and network are only citing; other subscriber equipment that is existing or that may occur from now on, the network equipment and networks, as being applicable to the present invention, within also should being included in scope, and are contained in this with way of reference.
With reference to Fig. 1, in step sl, recommendation apparatus obtains the first environment information corresponding with user.
Wherein, described first environment information comprises the information that can be used for determining described user's current demand.
Wherein, described first environment information is determined based on user operation.Preferably, described first environment information comprises the information that can embody user view.
Wherein, described first environment information includes but not limited to following at least any one information:
1) image information;
2) audio-frequency information;
3) video information;
4) other heat transfer agents, the heat transfer agent that such as environment temperature, bright and dark light, sea level elevation etc. obtain by all kinds of sensing device.
Particularly, the mode that recommendation apparatus obtains the first environment information corresponding with user include but not limited to following any one:
1) recommendation apparatus obtains described first environment information based on user operation.
Such as, user instantly selected the picture uploaded or video as first environment information.Again such as, using the photo of user's current shooting as first environment information.
2) when described recommendation apparatus is contained in the network equipment, recommendation apparatus receives the first environment information from subscriber equipment.
According to the first example of the present invention, user user_A takes pictures after image_1, and the recommendation apparatus in mobile phone obtains this picture image_1 and it can be used as the first environment information corresponding with user user_A.
Then, in step s 2, recommendation apparatus, according to described first environment information, determines the perpetual object corresponding with described first environment information and/or scene mode.
Wherein, described perpetual object is used to indicate the part information that user view is highlighted by environmental information.Such as, to ply in the centre in picture the clothes of position.Again such as, the personage etc. repeatedly repeated in multiple picture, more such as, the title etc. of the special article occurred in audio frequency
Wherein, described scene mode is used to indicate the Environment space relevant to certain user behavior pattern, to determine the demand that this user is current.Such as, scene mode includes but not limited to such as shopping plaza, dining room, library, public place of entertainment, meeting room etc. scene.
Preferably, described perpetual object or described scene mode comprise the one or more descriptor for limiting himself attribute.
Such as, for " shopping plaza " this scene mode, multinomial descriptors such as comprising such as dress ornament, case and bag, cosmetics, household electrical appliances can be adopted to limit it.Again such as, for " one-piece dress " this class perpetual object, the descriptors such as such as brand, fashion elements, price, like product can be adopted to limit it.
Particularly, recommendation apparatus operates by performing the such as process such as pattern-recognition, information excavating to obtained environmental information, to determine the perpetual object corresponding with it and/or scene mode; Or recommendation apparatus, based on the machine learning model set up, performs machine learning according to obtained first environment information, to determine the perpetual object corresponding with it and/or scene mode.
Preferably, when recommendation apparatus is contained in subscriber equipment, described first environment information is sent to the network equipment by recommendation apparatus.By the method for the network equipment by machine learning, described first environment information is analyzed, determine the perpetual object corresponding with it and/or scene mode, and feed back to described subscriber equipment.
More preferably, when determining described perpetual object and/or scene mode, recommendation apparatus determines this perpetual object and/or scene mode descriptor separately simultaneously.
Continue to be described foregoing First example, this picture image_1 as first environment information is sent to server by recommendation apparatus.Then, server carries out identifying operation by the mode of machine learning to the object comprised in this picture image_1 and picture background, determine the perpetual object " one-piece dress " corresponding with this picture image_1 and scene mode " shopping plaza ", and feed back to the mobile phone of user user_A use.
Preferably, described step S1 also comprises step S101 (not shown), and described step S2 also comprises step S201 (not shown).
In step S101, recommendation apparatus obtains the second environment information corresponding with described user.
Wherein, described second environment information comprises for auxiliary perpetual object and/or the scene mode of determining described user, and the type of it information comprised is identical with the information type that aforementioned first environment information can comprise, and repeats no more herein.
Preferably, described second environment information is gathered by subscriber equipment.
Wherein, the mode that recommendation apparatus obtains the second environment information corresponding with described user include but not limited to following any one:
1) recommendation apparatus directly performs acquisition operations, to obtain second environment information; Such as, recommendation apparatus by opening the camera collection of equipment of itself to video, and it can be used as second environment information.
2) recommendation apparatus sends the instruction performing acquisition operations to other equipment one or more, and receives the second environment information gathered from this other equipment one or more.
Such as, recommendation apparatus is by network, and the multiple monitoring cameras near zone send acquisition operations instruction, receive the monitoring image information fed back from the plurality of monitoring camera, and it can be used as second environment information.
In step s 201, recommendation apparatus, according to described first environment information and described second environment information, determines the perpetual object corresponding with described first environment information and described second environment information and/or scene mode.
Preferably, recommendation apparatus determines described perpetual object according to described first environment information, and determines described scene mode according to described first environment information and described second environment information.
It should be noted that, recommendation apparatus according to arbitrary in described first environment information and described second environment information or all can determine described perpetual object.Further, recommendation apparatus according to arbitrary in described first environment information and described second environment information or all can determine described scene mode.
According to the second example of the present invention, recommendation apparatus obtains user user_B in step sl and uses the picture image_2 that uploads of mobile phone as first environment information.Further, in step S101, recommendation apparatus gathers one section of background audio of the current residing environment of this user, as the second environment information corresponding with user user_B.Then in step s 201, this picture image_2 and this background audio are sent to server by recommendation apparatus together.Then, server carries out identifying operation by the method for machine learning to the object comprised in this picture image_2, determines corresponding perpetual object " pasta ".Further, server is identified this picture image_2 picture background and background audio by the method for machine learning, determines corresponding scene mode " dining room ".Then, recommendation apparatus reception server feedback perpetual object " pasta " and scene mode " dining room ".
Then, in step s3, recommendation apparatus, based on described perpetual object and/or scene mode, determines at least one the recommendation information corresponding with described user, to present described at least one recommendation information to described user.
Wherein, described recommendation information includes but not limited to following at least any one information:
1) text message;
2) link information;
3) pictorial information;
4) audio/video information etc.Wherein, when recommendation apparatus is contained in subscriber equipment, described perpetual object and/or described scene information are sent to the network equipment by recommendation apparatus, to receive at least one the recommendation information that the network equipment feeds back based on described perpetual object and/or described scene information, to present described at least one recommendation information to described user.
Preferably, the recommendation apparatus being contained in subscriber equipment can directly present described recommendation information, or, present described recommendation information in conjunction with other application programs.
Such as, recommendation apparatus represents the text recommendation information corresponding with this picture directly to user after receiving the picture that user uploads, or, corresponding recommendation information, according to detected environmental background music, is presented to user in the mode of pushed information by recommendation apparatus.
Again such as, recommendation apparatus is by such as short message receiver module, receive the recommendation information that is sent out as note and present to user, again such as, the communications applications of recommendation apparatus or non-instant instant by such as micro-letter, microblogging, Skype etc. and/or social application, present to user by recommendation information.Again such as, by web browser, recommendation information is presented to user etc. with the form of Search Results.
When recommendation apparatus is contained in the network equipment, recommendation apparatus receives from the perpetual object of other equipment and/or described scene information, with at least one the recommendation information based on the described perpetual object received and/or described scene information feedback, then, described at least one recommendation information is sent to the subscriber equipment corresponding with described user by described recommendation apparatus, to present described at least one recommendation information to described user.
Wherein, subscriber equipment presents to the mode of user and aforementioned recommendation apparatus after receiving recommendation information to present the mode of recommendation information same or similar, repeats no more herein.Particularly, recommendation apparatus based on described perpetual object and/or scene mode, determine the mode of at least one the recommendation information corresponding with described user include but not limited to following at least any one:
1) recommendation apparatus is based on described perpetual object and/or described scene information, inquires about in the network information of preset range, and determines at least one the recommendation information corresponding with described user based on Query Result.
Wherein, the network information of described preset range include but not limited to following at least any one:
I) by the all-network information of search engine search acquisition;
The network information of ii) predetermined one or more websites;
The network information of each iii) corresponding with the history visit information of described user website.
2) recommendation apparatus is based on described perpetual object and/or described scene information, determines the interest indication information corresponding with described perpetual object and/or scene information; Then, recommendation apparatus, based on described interest indication information, determines at least one the recommendation information corresponding with described user.
Wherein, described interest indication information includes but not limited to be used to indicate the type information needing the recommendation information relevant to described perpetual object and/or scene mode obtained.
Preferably, described interest indication information includes but not limited to the attribute of any and described perpetual object and/or scene information and/or the user relevant information for described perpetual object and/or behavior possible under described scene information.
Preferably, described interest indication information includes but not limited to following at least any one information:
I) attribute compares indication information; Such as, for " fruit participants in a bridge game machine " this perpetual object, interest indication information can comprise the indication information etc. for obtaining the rate of exchange information relevant to the price attribute of this mobile phone;
Ii) similar classification indication information; Such as, for " clothes " this perpetual object, interest indication information can comprise for obtaining the indication information etc. to the recommendation information of the same brand of this clothes, similar style, again such as, for " western-style restaurant of pre-capita consumption XXX unit " this scene information, interest indication information can comprise locates the indication information etc. of similar western-style restaurant as recommendation information for obtaining to this dining room;
Iii) content association indication information; Such as, for " clothes " this perpetual object, interest indication information comprises for obtaining the indication information as recommendation information such as other article such as shoes and hats of arranging in pairs or groups with clothes; Again such as, for " dining room " this scene information, interest indication information can comprise the indication information etc. of preferential action message as recommendation information for obtaining this dining room.
Iv) effect assessment indication information; Such as, for " xxx board washing agent " this perpetual object, interest indication information can comprise for obtaining the indication information as recommendation information with the effect assessment of this object; Again such as, for " 4s shop " this scene information, interest indication information section comprises for obtaining and the indication information of the evaluation information of this scene as recommendation information.
Preferably, recommendation apparatus is by setting up corresponding machine learning model, and after acquisition perpetual object and/or scene information, determine the interest indication information corresponding with described perpetual object and/or described scene information by this learning model by the mode of machine learning.
Continue to be described foregoing First example, recommendation apparatus is based on the perpetual object " one-piece dress " of user user_A and scene mode " shopping plaza ", determine that the attribute that the interest indication information corresponding with it comprises for obtaining other brands one-piece pricing information similar with one-piece dress brand positioning compares indication information by the mode of machine learning, and the one-piece price information of other brands obtained based on the search of this interest indication information is pushed in the mobile phone of user user_A.
3) recommendation apparatus is based on described perpetual object and/or described scene information, determines the interest indication information corresponding with described perpetual object and/or scene information; Then, recommendation apparatus, based on described interest indication information, is inquired about in the network information of preset range, and determines at least one the recommendation information corresponding with described user based on Query Result.
Such as, user user_C uses panel computer to upload one section of video, recommends dress to obtain this video in step sl and also determines the perpetual object " clothes " corresponding with this video and scene mode " family " in step s 2 as first environment information.Then recommendation apparatus is based on the perpetual object " clothes " of user user_C and scene mode " family ", determines that the interest indication information of its correspondence comprises for obtaining other users to the effect assessment indication information of the evaluation information of this part clothes and for obtaining other users content association indication information of wearing collocation information relevant to this part clothes.Then, recommendation apparatus is inquired about in a search engine based on this interest indication information, and other users search obtained are to the evaluation information of this part clothes and wear collocation information and push in the panel computer of user user_C relevant to this part clothes.
Preferably, also comprise step S4 (not shown) according to method of the present invention, described step S3 also comprises step S301 (not shown).
In step s 4 which, recommendation apparatus obtains the user network information corresponding with described user.
Wherein, described user network information includes but not limited to following at least any one information:
1) web search record; Such as, the historical search record of user in the past in predetermined amount of time.
2) network collection information; Such as, user's interior web page address, merchandise news etc. collected of predetermined amount of time in the past.
3) internet traffic.Such as, the chat record etc. of user.
In step S301, recommendation apparatus, based on described perpetual object and/or scene mode and described user network information, determines at least one the recommendation information corresponding with described user.
Continue to be described foregoing second example, in step s 4 which, recommendation apparatus obtains and the historical search record of user user_B in the past in one week " West Beijing dining room ".In step S301, recommendation apparatus is based on the perpetual object " pasta " of user user_B, scene mode " dining room " and the historical search record " West Beijing dining room " that obtains, determine that the interest indication information of its correspondence comprises the content association indication information for providing the preferential activity in this dining room, and the discount action message in this dining room obtained based on the search of this interest indication information is pushed in the mobile phone of user user_B.
According to method of the present invention, environmentally information can determine the focus that user is current and current residing scene thereof, and determine based on the current focus of user and/or current residing scene the demand that user is current, to provide relevant recommendation information to this user, make provided recommendation information more meet the current demand of user, improve the accuracy that current information is recommended.
Fig. 2 illustrates according to of the present invention a kind of for providing the structural representation of the recommendation apparatus of recommendation information.Recommendation apparatus according to the present invention comprises: for obtaining the device (hereinafter referred to as " the first acquisition device 1 ") of the first environment information corresponding with user; For according to described first environment information, determine the device (hereinafter referred to as " the first determining device 2 ") of the perpetual object corresponding with described first environment information and/or scene mode; For based on described perpetual object and/or scene mode, determine at least one the recommendation information corresponding with described user, to present the device (hereinafter referred to as " the second determining device 3 ") of described at least one recommendation information to described user.
With reference to Fig. 2, the first acquisition device 1 obtains the first environment information corresponding with user.
Wherein, described first environment information comprises the information that can be used for determining described user's current demand.
Wherein, described first environment information is determined based on user operation.Preferably, described first environment information comprises the information that can embody user view.
Wherein, described first environment information includes but not limited to following at least any one information:
1) image information;
2) audio-frequency information;
3) video information;
4) other heat transfer agents, the heat transfer agent that such as environment temperature, bright and dark light, sea level elevation etc. obtain by all kinds of sensing device.
Particularly, the mode that the first acquisition device 1 obtains the first environment information corresponding with user include but not limited to following any one:
1) the first acquisition device 1 obtains described first environment information based on user operation.
Such as, user instantly selected the picture uploaded or video as first environment information.Again such as, using the photo of user's current shooting as first environment information.
2) when described recommendation apparatus is contained in the network equipment, the first acquisition device 1 receives the first environment information from subscriber equipment.
According to the first example of the present invention, user user_A takes pictures after image_1, and the first acquisition device 1 in mobile phone obtains this picture image_1 and it can be used as the first environment information corresponding with user user_A.
Then, the first determining device 2, according to described first environment information, determines the perpetual object corresponding with described first environment information and/or scene mode.
Wherein, described perpetual object is used to indicate the part information that user view is highlighted by environmental information.Such as, to ply in the centre in picture the clothes of position.Again such as, the personage etc. repeatedly repeated in multiple picture, more such as, the title etc. of the special article occurred in audio frequency
Wherein, described scene mode is used to indicate the Environment space relevant to certain user behavior pattern, to determine the demand that this user is current.Such as, scene mode includes but not limited to such as shopping plaza, dining room, library, public place of entertainment, meeting room etc. scene.
Preferably, described perpetual object or described scene mode comprise the one or more descriptor for limiting himself attribute.
Such as, for " shopping plaza " this scene mode, multinomial descriptors such as comprising such as dress ornament, case and bag, cosmetics, household electrical appliances can be adopted to limit it.Again such as, for " one-piece dress " this class perpetual object, the descriptors such as such as brand, fashion elements, price, like product can be adopted to limit it.
Particularly, the first determining device 2 operates by performing the such as process such as pattern-recognition, information excavating to obtained environmental information, to determine the perpetual object corresponding with it and/or scene mode; Or the first determining device 2, based on the machine learning model set up, performs machine learning according to obtained first environment information, to determine the perpetual object corresponding with it and/or scene mode.
Preferably, when recommendation apparatus is contained in subscriber equipment, described first environment information is sent to the network equipment by recommendation apparatus.By the method for the network equipment by machine learning, described first environment information is analyzed, determine the perpetual object corresponding with it and/or scene mode, and feed back to described subscriber equipment.
More preferably, when determining described perpetual object and/or scene mode, the first determining device 2 determines this perpetual object and/or scene mode descriptor separately simultaneously.
Continue to be described foregoing First example, this picture image_1 as first environment information is sent to server by the first determining device 2.Then, server carries out identifying operation by the mode of machine learning to the object comprised in this picture image_1 and picture background, determine the perpetual object " one-piece dress " corresponding with this picture image_1 and scene mode " shopping plaza ", and feed back to the mobile phone of user user_A use.
Preferably, described first acquisition device 1 also comprises the device (scheming not show, hereinafter referred to as " sub-acquisition device ") for obtaining the second environment information corresponding with described user.
Sub-acquisition device obtains the second environment information corresponding with described user.
Wherein, described second environment information comprises for auxiliary perpetual object and/or the scene mode of determining described user, and the type of it information comprised is identical with the information type that aforementioned first environment information can comprise, and repeats no more herein.
Preferably, described second environment information is gathered by subscriber equipment.
Wherein, the mode that sub-acquisition device obtains the second environment information corresponding with described user include but not limited to following any one:
1) sub-acquisition device directly performs acquisition operations, to obtain second environment information; Such as, sub-acquisition device by opening the camera collection of equipment of itself to video, and it can be used as second environment information.
2) sub-acquisition device sends the instruction performing acquisition operations to other equipment one or more, and receives the second environment information gathered from this other equipment one or more.
Such as, sub-acquisition device is by network, and the multiple monitoring cameras near zone send acquisition operations instruction, receive the monitoring image information fed back from the plurality of monitoring camera, and it can be used as second environment information.
Then, the first determining device 2, according to described first environment information and described second environment information, determines the perpetual object corresponding with described first environment information and described second environment information and/or scene mode.
Preferably, the first determining device 2 determines described perpetual object according to described first environment information, and determines described scene mode according to described first environment information and described second environment information.
It should be noted that, the first determining device 2 according to arbitrary in described first environment information and described second environment information or all can determine described perpetual object.Further, recommendation apparatus according to arbitrary in described first environment information and described second environment information or all can determine described scene mode.
According to the second example of the present invention, the first acquisition device 1 obtains user user_B and uses the picture image_2 that uploads of mobile phone as first environment information.Further, sub-acquisition device gathers one section of background audio of the current residing environment of this user, as the second environment information corresponding with user user_B.Then this picture image_2 and this background audio are sent to server by the first determining device 2 together.Then, server carries out identifying operation by the method for machine learning to the object comprised in this picture image_2, determines corresponding perpetual object " pasta ".Further, server is identified this picture image_2 picture background and background audio by the method for machine learning, determines corresponding scene mode " dining room ".Then, first determining device 2 reception server feedback perpetual object " pasta " and scene mode " dining room ".
Then, the second determining device 3, based on described perpetual object and/or scene mode, determines at least one the recommendation information corresponding with described user, to present described at least one recommendation information to described user.
Wherein, described recommendation information includes but not limited to following at least any one information:
1) text message;
2) link information;
3) pictorial information;
4) audio/video information etc.
Wherein, when recommendation apparatus is contained in subscriber equipment, described perpetual object and/or described scene information are sent to the network equipment by the second determining device 3, to receive at least one the recommendation information that the network equipment feeds back based on described perpetual object and/or described scene information, to present described at least one recommendation information to described user.
Preferably, the second determining device 3 being contained in subscriber equipment can directly present described recommendation information, or the second determining device 3 presents described recommendation information in conjunction with other application programs.
Such as, after recommendation apparatus receives the picture that user uploads, second determining device 3 represents the text recommendation information corresponding with this picture directly to user, or, corresponding recommendation information, according to detected environmental background music, is presented to user in the mode of pushed information by the second determining device 3 by recommendation apparatus.
Again such as, second determining device 3 is by such as short message receiver module, receive the recommendation information that is sent out as note and present to user, again such as, the communications applications of the second determining device 3 or non-instant instant by such as micro-letter, microblogging, Skype etc. and/or social application, present to user by recommendation information.Again such as, recommendation information, by web browser, is presented to user etc. with the form of Search Results by the second determining device 3.
When recommendation apparatus is contained in the network equipment, second determining device 3 receives perpetual object from other equipment and/or described scene information, with at least one the recommendation information based on the described perpetual object received and/or described scene information feedback, then, described at least one recommendation information is sent to the subscriber equipment corresponding with described user by described second determining device 3, to present described at least one recommendation information by described subscriber equipment to described user.
Wherein, the mode that subscriber equipment second determining device 3 of presenting to after receiving recommendation information in the mode of user and aforementioned recommendation apparatus presents recommendation information is same or similar, repeats no more herein.
Particularly, the second determining device 3 based on described perpetual object and/or scene mode, determine the mode of at least one the recommendation information corresponding with described user include but not limited to following at least any one:
1) the second determining device 3 is based on described perpetual object and/or described scene information, inquires about in the network information of preset range, and determines at least one the recommendation information corresponding with described user based on Query Result.
Wherein, the network information of described preset range include but not limited to following at least any one:
I) by the all-network information of search engine search acquisition;
The network information of ii) predetermined one or more websites;
The network information of each iii) corresponding with the history visit information of described user website.
2) the second determining device 3 is based on described perpetual object and/or described scene information, determines the interest indication information corresponding with described perpetual object and/or scene information; Then, recommendation apparatus, based on described interest indication information, determines at least one the recommendation information corresponding with described user.
Wherein, described interest indication information includes but not limited to be used to indicate the type information needing the recommendation information relevant to described perpetual object and/or scene mode obtained.
Preferably, described interest indication information includes but not limited to the attribute of any and described perpetual object and/or scene information and/or the user relevant information for described perpetual object and/or behavior possible under described scene information.
Preferably, described interest indication information includes but not limited to following at least any one information:
I) attribute compares indication information; Such as, for " fruit participants in a bridge game machine " this perpetual object, interest indication information can comprise the indication information etc. for obtaining the rate of exchange information relevant to the price attribute of this mobile phone;
Ii) similar classification indication information; Such as, for " clothes " this perpetual object, interest indication information can comprise for obtaining the indication information etc. to the recommendation information of the same brand of this clothes, similar style, again such as, for " western-style restaurant of pre-capita consumption XXX unit " this scene information, interest indication information can comprise locates the indication information etc. of similar western-style restaurant as recommendation information for obtaining to this dining room;
Iii) content association indication information; Such as, for " clothes " this perpetual object, interest indication information comprises for obtaining the indication information as recommendation information such as other article such as shoes and hats of arranging in pairs or groups with clothes; Again such as, for " dining room " this scene information, interest indication information can comprise the indication information etc. of preferential action message as recommendation information for obtaining this dining room.
Iv) effect assessment indication information; Such as, for " xxx board washing agent " this perpetual object, interest indication information can comprise for obtaining the indication information as recommendation information with the effect assessment of this object; Again such as, for " 4s shop " this scene information, interest indication information can comprise for obtaining and the indication information of the evaluation information of this scene as recommendation information.
Preferably, second determining device 3 is by setting up corresponding machine learning model, and after acquisition perpetual object and/or scene information, determine the interest indication information corresponding with described perpetual object and/or described scene information by this learning model by the mode of machine learning.
Continue to be described foregoing First example, second determining device 3 is based on the perpetual object " one-piece dress " of user user_A and scene mode " shopping plaza ", determine that the attribute that the interest indication information corresponding with it comprises for obtaining other brands one-piece pricing information similar with one-piece dress brand positioning compares indication information by the mode of machine learning, and the one-piece price information of other brands obtained based on the search of this interest indication information is pushed in the mobile phone of user user_A.
3) the second determining device 3 is based on described perpetual object and/or described scene information, determines the interest indication information corresponding with described perpetual object and/or scene information; Then, the second determining device 3, based on described interest indication information, is inquired about in the network information of preset range, and determines at least one the recommendation information corresponding with described user based on Query Result.
Such as, user user_C uses panel computer to upload one section of video, and the first acquisition device 1 obtains this video as first environment information, and the first determining device 2 determines the perpetual object " clothes " corresponding with this video and scene mode " family ".Then the second determining device 3 is based on the perpetual object " clothes " of user user_C and scene mode " family ", determines that the interest indication information of its correspondence comprises for obtaining other users to the effect assessment indication information of the evaluation information of this part clothes and for obtaining other users content association indication information of wearing collocation information relevant to this part clothes.Then, recommendation apparatus is inquired about in a search engine based on this interest indication information, and other users search obtained are to the evaluation information of this part clothes and wear collocation information and push in the panel computer of user user_C relevant to this part clothes.
Preferably, the device (scheming not show, hereinafter referred to as " the 3rd acquisition device ") obtaining the user network information corresponding with described user for recommendation apparatus is also comprised according to recommendation apparatus of the present invention.
3rd acquisition device obtains the user network information corresponding with described user.
Wherein, described user network information includes but not limited to following at least any one information:
1) web search record; Such as, the historical search record of user in the past in predetermined amount of time.
2) network collection information; Such as, user's interior web page address, merchandise news etc. collected of predetermined amount of time in the past.
3) internet traffic.Such as, the chat record etc. of user.
Second determining device 3, based on described perpetual object and/or scene mode and described user network information, determines at least one the recommendation information corresponding with described user.
Continue to be described foregoing second example, the 3rd acquisition device obtains and the historical search record of user user_B in the past in one week " West Beijing dining room ".Then the second determining device 3 is based on the perpetual object " pasta " of user user_B, scene mode " dining room " and the historical search record " West Beijing dining room " that obtains, determine that the interest indication information of its correspondence comprises the content association indication information for providing the preferential activity in this dining room, and the discount action message in this dining room obtained based on the search of this interest indication information is pushed in the mobile phone of user user_B.
According to the solution of the present invention, environmentally information can determine the focus that user is current and current residing scene thereof, and determine based on the current focus of user and/or current residing scene the demand that user is current, to provide relevant recommendation information to this user, make provided recommendation information more meet the current demand of user, improve the accuracy that current information is recommended.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.First, second word such as grade is used for representing title, and does not represent any specific order.
Claims (14)
1., for providing a method for recommendation information, wherein, said method comprising the steps of:
-obtain the first environment information corresponding with user, wherein, described first environment information is determined based on user operation;
-according to described first environment information, determine the perpetual object corresponding with described first environment information and/or scene mode;
-based on described perpetual object and/or scene mode, determine at least one the recommendation information corresponding with described user, to present described at least one recommendation information to described user.
2. method according to claim 1, wherein, the step of the first environment information that described acquisition is corresponding with user is further comprising the steps of:
-obtain the second environment information corresponding with described user, wherein, described second environment information is gathered by subscriber equipment;
Wherein, described according to described first environment information, determine that the step of the perpetual object corresponding with described first environment information and/or scene mode comprises the following steps:
-according to described first environment information and described second environment information, determine the perpetual object corresponding with described first environment information and described second environment information and/or scene mode.
3. method according to claim 1 and 2, wherein, described based on described perpetual object and/or described scene information, the step of inquiring about in the network information of preset range is further comprising the steps of:
-based on described perpetual object and/or described scene information, determine the interest indication information corresponding with described perpetual object and/or scene information;
-based on described interest indication information, determine at least one the recommendation information corresponding with described user.
4. method according to claim 3, wherein, described interest indication information comprises following at least any one information:
-attribute compares indication information;
-similar classification indication information;
-content association indication information;
-effect assessment indication information.
5. method according to any one of claim 1 to 4, wherein, described based on described perpetual object and/or scene mode, determine that the step of at least one the recommendation information corresponding with described user comprises the following steps:
-based on described perpetual object and/or described scene information, inquire about in the network information of preset range;
-determine at least one the recommendation information corresponding with described user based on Query Result.
6. method according to any one of claim 1 to 5, wherein, described method is further comprising the steps of:
-obtain the user network information corresponding with described user;
Wherein, described based on described perpetual object and/or scene mode, determine that the step of at least one the recommendation information corresponding with described user comprises the following steps:
-based on described perpetual object and/or scene mode and described user network information, determine at least one the recommendation information corresponding with described user.
7. method according to any one of claim 1 to 6, wherein, described first environment information or second environment information comprise following at least any one information respectively:
-image information;
-audio-frequency information;
-video information;
-other heat transfer agents.
8. for providing a recommendation apparatus for recommendation information, wherein, described recommendation apparatus comprises:
For obtaining the device of the first environment information corresponding with user, wherein, described first environment information is determined based on user operation;
For according to described first environment information, determine the perpetual object corresponding with described first environment information and/or the device of scene mode;
For based on described perpetual object and/or scene mode, determine at least one the recommendation information corresponding with described user, to present the device of described at least one recommendation information to described user.
9. recommendation apparatus according to claim 8, wherein, the described device for obtaining the first environment information corresponding with user also comprises:
For obtaining the device of the second environment information corresponding with described user, wherein, described second environment information is gathered by subscriber equipment;
Wherein, described for according to described first environment information, determine that the device of the perpetual object corresponding with described first environment information and/or scene mode comprises:
For according to described first environment information and described second environment information, determine the perpetual object corresponding with described first environment information and described second environment information and/or the device of scene mode.
10. recommendation apparatus according to claim 8 or claim 9, wherein, described for based on described perpetual object and/or described scene information, the device inquired about in the network information of preset range also comprise with:
-for based on described perpetual object and/or described scene information, determine the device of the interest indication information corresponding with described perpetual object and/or scene information;
-for based on described interest indication information, determine the device of at least one the recommendation information corresponding with described user.
11. recommendation apparatus according to claim 10, wherein, described interest indication information comprises following at least any one information:
-attribute compares indication information;
-similar classification indication information;
-content association indication information;
-effect assessment indication information.
Recommendation apparatus according to any one of 12. according to Claim 8 to 11, wherein, described for based on described perpetual object and/or scene mode, determine that the device of at least one the recommendation information corresponding with described user comprises:
For based on described perpetual object and/or described scene information, the device inquired about in the network information of preset range;
For determining the device of at least one the recommendation information corresponding with described user based on Query Result.
Recommendation apparatus according to any one of 13. according to Claim 8 to 12, wherein, described recommendation apparatus also comprises:
For obtaining the device of the user network information corresponding with described user;
Wherein, described for based on described perpetual object and/or scene mode, determine the device of at least one the recommendation information corresponding with described user for:
-based on described perpetual object and/or scene mode and described user network information, determine at least one the recommendation information corresponding with described user.
Recommendation apparatus according to any one of 14. according to Claim 8 to 13, wherein, described first environment information or second environment information comprise following at least any one information respectively:
-image information;
-audio-frequency information;
-video information;
-other heat transfer agents.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410443502.1A CN104268154A (en) | 2014-09-02 | 2014-09-02 | Recommended information providing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410443502.1A CN104268154A (en) | 2014-09-02 | 2014-09-02 | Recommended information providing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268154A true CN104268154A (en) | 2015-01-07 |
Family
ID=52159676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410443502.1A Pending CN104268154A (en) | 2014-09-02 | 2014-09-02 | Recommended information providing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268154A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302904A (en) * | 2015-10-29 | 2016-02-03 | 努比亚技术有限公司 | Information pushing method and apparatus |
| WO2016150170A1 (en) * | 2015-03-25 | 2016-09-29 | 百度在线网络技术（北京）有限公司 | Recommendation method, device and equipment and computer storage medium |
| CN106294489A (en) * | 2015-06-08 | 2017-01-04 | 北京三星通信技术研究有限公司 | Content recommendation method, Apparatus and system |
| CN106572390A (en) * | 2016-11-09 | 2017-04-19 | 咪咕音乐有限公司 | Audio and video recommending method and equipment |
| CN106878355A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of information recommendation method and device |
| CN106874021A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | terminal visual interface automatic switching method and device |
| CN108347520A (en) * | 2017-01-23 | 2018-07-31 | 阿里巴巴集团控股有限公司 | The sending method and device of contextual model, the startup method and device of application |
| CN109104524A (en) * | 2018-06-29 | 2018-12-28 | 奇酷互联网络科技（深圳）有限公司 | Application program aligning method, device, readable storage medium storing program for executing and mobile terminal |
| CN109670106A (en) * | 2018-12-06 | 2019-04-23 | 百度在线网络技术（北京）有限公司 | Things recommended method and device based on scene |
| WO2019128552A1 (en) * | 2017-12-29 | 2019-07-04 | Oppo广东移动通信有限公司 | Information pushing method, apparatus, terminal, and storage medium |
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN111447260A (en) * | 2020-03-20 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Information pushing and information publishing method and device |
| CN111798260A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | User behavior prediction model construction method and device, storage medium and electronic equipment |
| CN113204654A (en) * | 2021-04-21 | 2021-08-03 | 北京达佳互联信息技术有限公司 | Data recommendation method and device, server and storage medium |
| CN114528482A (en) * | 2022-01-25 | 2022-05-24 | 北京三快在线科技有限公司 | Method and device for determining recommended object, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890713A (en) * | 2012-09-20 | 2013-01-23 | 浙江大学 | Music recommending method based on current geographical position and physical environment of user |
| CN103106259A (en) * | 2013-01-25 | 2013-05-15 | 西北工业大学 | Mobile webpage content recommending method based on situation |
| CN103136324A (en) * | 2011-11-22 | 2013-06-05 | 三星电子株式会社 | System and method of recommending applications based on context information |
| US20130212101A1 (en) * | 2012-02-09 | 2013-08-15 | Nec Corporation | Portlet processing apparatus, portal server, portal system, portlet processing method and recording medium |
| CN103324729A (en) * | 2013-06-27 | 2013-09-25 | 北京小米科技有限责任公司 | Method and device for recommending multimedia resources |
| EP2650803A1 (en) * | 2011-07-29 | 2013-10-16 | Rakuten, Inc. | Device for providing information, method for providing information, program for providing information, and computer-readable recording medium storing program for same |
| CN103678719A (en) * | 2013-12-31 | 2014-03-26 | 冠捷显示科技（厦门）有限公司 | Recommended system for providing feedback through environment sensing actively |
| CN103729476A (en) * | 2014-01-26 | 2014-04-16 | 王玉娇 | Method and system for correlating contents according to environmental state |
-
2014
- 2014-09-02 CN CN201410443502.1A patent/CN104268154A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2650803A1 (en) * | 2011-07-29 | 2013-10-16 | Rakuten, Inc. | Device for providing information, method for providing information, program for providing information, and computer-readable recording medium storing program for same |
| CN103136324A (en) * | 2011-11-22 | 2013-06-05 | 三星电子株式会社 | System and method of recommending applications based on context information |
| US20130212101A1 (en) * | 2012-02-09 | 2013-08-15 | Nec Corporation | Portlet processing apparatus, portal server, portal system, portlet processing method and recording medium |
| CN102890713A (en) * | 2012-09-20 | 2013-01-23 | 浙江大学 | Music recommending method based on current geographical position and physical environment of user |
| CN103106259A (en) * | 2013-01-25 | 2013-05-15 | 西北工业大学 | Mobile webpage content recommending method based on situation |
| CN103324729A (en) * | 2013-06-27 | 2013-09-25 | 北京小米科技有限责任公司 | Method and device for recommending multimedia resources |
| CN103678719A (en) * | 2013-12-31 | 2014-03-26 | 冠捷显示科技（厦门）有限公司 | Recommended system for providing feedback through environment sensing actively |
| CN103729476A (en) * | 2014-01-26 | 2014-04-16 | 王玉娇 | Method and system for correlating contents according to environmental state |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016150170A1 (en) * | 2015-03-25 | 2016-09-29 | 百度在线网络技术（北京）有限公司 | Recommendation method, device and equipment and computer storage medium |
| CN106294489A (en) * | 2015-06-08 | 2017-01-04 | 北京三星通信技术研究有限公司 | Content recommendation method, Apparatus and system |
| CN106294489B (en) * | 2015-06-08 | 2022-09-30 | 北京三星通信技术研究有限公司 | Content recommendation method, device and system |
| CN105302904A (en) * | 2015-10-29 | 2016-02-03 | 努比亚技术有限公司 | Information pushing method and apparatus |
| CN106878355A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of information recommendation method and device |
| CN106874021A (en) * | 2015-12-11 | 2017-06-20 | 腾讯科技（深圳）有限公司 | terminal visual interface automatic switching method and device |
| CN106572390A (en) * | 2016-11-09 | 2017-04-19 | 咪咕音乐有限公司 | Audio and video recommending method and equipment |
| CN106572390B (en) * | 2016-11-09 | 2020-03-13 | 咪咕音乐有限公司 | Audio and video recommendation method and equipment |
| CN108347520A (en) * | 2017-01-23 | 2018-07-31 | 阿里巴巴集团控股有限公司 | The sending method and device of contextual model, the startup method and device of application |
| CN109995799A (en) * | 2017-12-29 | 2019-07-09 | 广东欧珀移动通信有限公司 | Information-pushing method, device, terminal and storage medium |
| WO2019128552A1 (en) * | 2017-12-29 | 2019-07-04 | Oppo广东移动通信有限公司 | Information pushing method, apparatus, terminal, and storage medium |
| CN109995799B (en) * | 2017-12-29 | 2020-12-29 | Oppo广东移动通信有限公司 | Information pushing method and device, terminal and storage medium |
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN109104524A (en) * | 2018-06-29 | 2018-12-28 | 奇酷互联网络科技（深圳）有限公司 | Application program aligning method, device, readable storage medium storing program for executing and mobile terminal |
| CN109670106A (en) * | 2018-12-06 | 2019-04-23 | 百度在线网络技术（北京）有限公司 | Things recommended method and device based on scene |
| CN111798260A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | User behavior prediction model construction method and device, storage medium and electronic equipment |
| CN111447260A (en) * | 2020-03-20 | 2020-07-24 | 北京字节跳动网络技术有限公司 | Information pushing and information publishing method and device |
| CN113204654A (en) * | 2021-04-21 | 2021-08-03 | 北京达佳互联信息技术有限公司 | Data recommendation method and device, server and storage medium |
| CN113204654B (en) * | 2021-04-21 | 2024-03-29 | 北京达佳互联信息技术有限公司 | Data recommendation method, device, server and storage medium |
| CN114528482A (en) * | 2022-01-25 | 2022-05-24 | 北京三快在线科技有限公司 | Method and device for determining recommended object, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104268154A (en) | Recommended information providing method and device | |
| CN104244032B (en) | Push the method and apparatus of multi-medium data | |
| US10621954B2 (en) | Computerized system and method for automatically creating and applying a filter to alter the display of rendered media | |
| US11182068B2 (en) | Method and system for interacting with a touch screen | |
| CN106357517B (en) | Directional label generation method and device | |
| CN110046299B (en) | Computerized system and method for automatically performing an implicit message search | |
| US20160034977A1 (en) | System and method for embedded search within messaging applications | |
| CN103729777A (en) | Online shopping method, device and system based on image recognition technology | |
| CN107527274B (en) | Information recommendation platform, device, system, method and terminal | |
| US20160335498A1 (en) | Augmented reality information system | |
| US9621622B2 (en) | Information providing apparatus, information providing method, and network system | |
| TW201533588A (en) | Method and system for providing code scanning result information | |
| CN110223093B (en) | Commodity recommendation method and device | |
| CN102982472A (en) | Method and device for automatically recommending similar commodities by terminal | |
| CN103440260A (en) | Method and equipment used for providing representation information | |
| TW201533687A (en) | Method, apparatus, and system for displaying order information | |
| US20170316469A1 (en) | Native advertisement smart injection | |
| US11599571B2 (en) | Generic card feature extraction based on card rendering as an image | |
| CN105488109A (en) | Content item configuration method, device and system | |
| CN104731870A (en) | Method and device for providing recommendation information | |
| CN104615640A (en) | Method and device for providing searching keywords and carrying out searching | |
| CN102880974A (en) | System for sending commodity group purchase information to user | |
| US20180139265A1 (en) | Computerized system and method for automatically providing networked devices non-native functionality | |
| CN103123639A (en) | Article data query system and method | |
| CN104156375A (en) | Message inputting method and system based on crowdsourcing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150107 |
|
| RJ01 | Rejection of invention patent application after publication |