CN106383895A - Information recommendation method and device and terminal equipment - Google Patents
Information recommendation method and device and terminal equipment Download PDFInfo
- Publication number
- CN106383895A CN106383895A CN201610854882.7A CN201610854882A CN106383895A CN 106383895 A CN106383895 A CN 106383895A CN 201610854882 A CN201610854882 A CN 201610854882A CN 106383895 A CN106383895 A CN 106383895A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- recommendation
- described user
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses an information recommendation method, an information recommendation device and terminal equipment. The method comprises the following steps: when a triggering condition of information recommendation is detected, acquiring the current operation of a user, and determining the current state of the user according to the current operation and a pre-generated state machine model of the user, wherein the state machine model comprises a plurality of states of the user, and each state is used for indicating the current operation behavior of the user; and generating corresponding first recommendation information according to the current state. The method can enable the user to select the information content type preferred by the user without manual operation, simplifies the operation steps of the user, accelerates the identification speed of the preference of the user by applying the state machine technology to the information recommendation process, improves the information recommendation effect when the user uses the information for the first time, and improves the user experience.
Description
Technical field
The present invention relates to technical field of information processing, more particularly, to a kind of information recommendation method, device and terminal unit.
Background technology
With the fast development of electronics technology, the user using application gets more and more.In order to more preferably meet the demand of user,
When using application, in order to attract user to be continuing with or life-time service application, application would generally enter row information to user to user
Recommend.For example, user is when using article reader application, and article reader application would generally recommend article information to user.
In correlation technique, to the method generally adopting during user's recommendation information it is:Provide a user with for article content class
Multiple labels of type, user actively selects user's label interested according to itself hobby and demand from the plurality of label,
Then, the article belonging to this label is obtained according to the label that user selects, and these articles are recommended use as recommendation information
Family.
The problem that presently, there are is, during information recommendation, needs user actively to select itself label interested,
Then the label selecting further according to user carries out the recommendation of corresponding information, increased the operating procedure of user so that information recommendation
Mode is not intelligent, and the recommendation effect of information is poor, reduces the experience of user.
Content of the invention
The purpose of the present invention is intended at least solve to a certain extent one of above-mentioned technical problem.
For this reason, the first of the present invention purpose is to propose a kind of information recommendation method.The method so that user no
The information content type of itself hobby need to be manually selected, simplify the operating procedure of user, simultaneously by transporting state machine technique
During information recommendation, accelerate the identification speed to user preferences, improve information recommendation when user uses for the first time
Effect, improves Consumer's Experience.
Second object of the present invention is to propose a kind of information recommending apparatus.
Third object of the present invention is to propose a kind of terminal unit.
Fourth object of the present invention is to propose a kind of storage medium.
5th purpose of the present invention is to propose a kind of application program.
For reaching above-mentioned purpose, the information recommendation method of first aspect present invention embodiment, including:Information recommendation is being detected
Trigger condition when, obtain user current operation;State according to described current operation and the described user previously generating
Machine model determines the current state of described user, wherein, comprises multiple shapes of described user in the state machine model of described user
State, each state is used for indicating the current operation behavior of described user;Generate it according to described current state corresponding first to push away
Recommend information.
Information recommendation method according to embodiments of the present invention, when the trigger condition of information recommendation is detected, obtains user
Current operation, and determine the current state of user according to the state machine model of current operation and the user previously generating,
Afterwards, corresponding first recommendation information is generated according to this current state.I.e. by carrying out decomposing generating to the operation behavior of user
Corresponding state machine model, when subsequently using, to determine the current state of user in real time by the current operation of user, and root
According to user current state real-time update recommendation information content so that user need not manually select itself hobby information content class
Type, simplifies the operating procedure of user, simultaneously by state machine technique is applied to information recommendation during, accelerate to user
The identification speed of hobby, improves the effect of information recommendation when user uses for the first time, improves Consumer's Experience.
According to one embodiment of present invention, methods described also includes:Obtain the user profile of described user;According to described
User profile obtains the historical operation information of described user;Historical operation information according to described user generates the use of described user
Draw a portrait in family;Drawn a portrait according to described user and generate its corresponding second recommendation information;By described first recommendation information and described second
Recommendation information is combined, and forms recommendation results, and described recommendation results are supplied to described user.
According to one embodiment of present invention, described portrait according to described user generates corresponding second recommendation information, bag
Include:According to the affiliated type of described user portrait, obtain hobby type and the user types of described user;According to described user
Hobby type and user types generate described second recommendation information.
According to one embodiment of present invention, before described recommendation results are supplied to described user, methods described is also
Including:Determine the generic of recommendation information in described recommendation results, and determine the dependency with described generic be more than or
First category equal to predetermined threshold value;Obtain the information content belonging to described first category, and belong to the described first kind by described
Other information content is as the 3rd recommendation information;Wherein, described described recommendation results are supplied to described user include:Will be described
3rd recommendation information and described recommendation results are simultaneously supplied to described user.
According to one embodiment of present invention, when described first category is multiple, described described first category will be belonged to
Information content as the 3rd recommendation information, including:According to the size of multiple first category and the dependency of described generic,
Respectively the information content belonging to the plurality of first category is ranked up, and will sequence after described in belong to multiple first category
Information content as described 3rd recommendation information.
According to one embodiment of present invention, the state machine model of described user is previously generated by following steps:Obtain
Take the operation behavior information of described user, and the operation behavior information of described user is carried out with state decomposition, generate multiple states;
Determine the incidence relation between the plurality of state;According to described incidence relation, the plurality of state is combined, generates institute
State the state machine model of user.
For reaching above-mentioned purpose, the information recommending apparatus of second aspect present invention embodiment, including:First acquisition module, uses
In when the trigger condition of information recommendation is detected, obtain the current operation of user;First determining module, for working as according to described
The state machine model of the front described user operating and previously generating determines the current state of described user, wherein, described user
State machine model in comprise multiple states of described user, each state is used for indicating the current operation behavior of described user;
First generation module, for generating its corresponding first recommendation information according to described current state.
Information recommending apparatus according to embodiments of the present invention, can detect touching of information recommendation by the first acquisition module
During clockwork spring part, obtain the current operation of user, the first determining module is according to the state of current operation and the user previously generating
Machine model determines the current state of user, and the first generation module generates corresponding first recommendation information according to current state.Lead to
Cross the operation behavior to user to be decomposed to generate corresponding state machine model, so that when subsequently using, working as by user
Front operation determines in real time the current state of user, and according to the current state real-time update recommendation information content of user so that using
Family need not manually select the information content type of itself hobby, simplifies the operating procedure of user, pass through state machine skill simultaneously
During art applies to information recommendation, accelerate the identification speed to user preferences, information when user uses for the first time that improves pushes away
The effect recommended, improves Consumer's Experience.
According to one embodiment of present invention, described device also includes:Second acquisition module, for obtaining described user's
User profile, and the historical operation information of described user is obtained according to described user profile;Second generation module, for according to institute
The historical operation information stating user generates user's portrait of described user;3rd generation module, for drawing a portrait according to described user
Generate corresponding second recommendation information;Information providing module, for by described first recommendation information and described second recommendation information
It is combined, form recommendation results, and described recommendation results are supplied to described user.
According to one embodiment of present invention, described 3rd generation module includes:Taxon, for according to described user
The affiliated type of portrait, obtains hobby type and the user types of described user;Signal generating unit, for according to described user's
Hobby type and user types generate described second recommendation information.
According to one embodiment of present invention, described device also includes:Second determining module, for recommending knot by described
Before fruit is supplied to described user, determines the generic of recommendation information in described recommendation results, and determine and described affiliated class
Other dependency is more than or equal to the first category of predetermined threshold value;3rd acquisition module, belongs to described first category for obtaining
Information content, and using the described information content belonging to described first category as the 3rd recommendation information;Wherein, described information carries
It is additionally operable to for module:Described 3rd recommendation information and described recommendation results are simultaneously supplied to described user.
According to one embodiment of present invention, when described first category is multiple, described 3rd acquisition module is specifically used
In:According to the size of multiple first category and the dependency of described generic, respectively to belonging to the plurality of first category
Information content is ranked up, and will sequence after described in belong to the information content of multiple first category as described 3rd recommendation
Breath.
According to one embodiment of present invention, described device also includes:Anticipate module, be used for previously generating described use
The state machine model at family;Wherein, described module of anticipating includes:Acquiring unit, for obtaining the operation behavior of described user
Information;State decomposition unit, for carrying out state decomposition to the operation behavior information of described user, generates multiple states;Determine
Unit, for determining the incidence relation between the plurality of state;Signal generating unit, for will be described many according to described incidence relation
Individual state is combined, and generates the state machine model of described user.
For reaching above-mentioned purpose, the terminal unit of third aspect present invention embodiment, including:Housing, processor, memorizer,
Circuit board and power circuit, wherein, described circuit board is placed in the interior volume that described housing surrounds, described processor and described
Memorizer is arranged on described circuit board;Described power circuit, for being each circuit of described terminal unit or device is powered;
Described memorizer is used for storing executable program code;Described processor passes through to read the executable journey of storage in described memorizer
Sequence code running program corresponding with described executable program code, for executing following steps:Push away in the information of detecting
During the trigger condition recommended, obtain the current operation of user, and according to described current operation and the described user that previously generates
State machine model determines the current state of described user, wherein, comprises the many of described user in the state machine model of described user
Individual state, each state is used for indicating the current operation behavior of described user;According to described current state generate its corresponding
One recommendation information.
Terminal unit according to embodiments of the present invention, when the trigger condition of information recommendation is detected, obtains working as of user
Front operation, and the current state of user, finally, root is determined according to the state machine model of current operation and the user previously generating
Generate corresponding first recommendation information according to this current state.I.e. by the operation behavior of user is carried out decomposing generate corresponding
State machine model, when subsequently using, to determine the current state of user in real time, and according to user by the current operation of user
Current state real-time update recommendation information content so that user need not manually select itself hobby information content type, letter
Changed the operating procedure of user, simultaneously by state machine technique is applied to information recommendation during, accelerate to user preferences
Identification speed, improve the effect of information recommendation when user uses for the first time, improve Consumer's Experience.
For reaching above-mentioned purpose, fourth aspect present invention embodiment proposes a kind of storage medium, wherein, described storage medium
For storing application program, described application program is used for the operationally information described in execution first aspect present invention embodiment to be pushed away
Recommend method.
For reaching above-mentioned purpose, fifth aspect present invention embodiment proposes a kind of application program, wherein, described application program
For operationally executing the information recommendation method described in first aspect present invention embodiment.
The aspect that the present invention adds and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description
The above-mentioned and/or additional aspect of the present invention and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and easy to understand, wherein:
Fig. 1 is the flow chart of information recommendation method according to an embodiment of the invention;
Fig. 2 is the flow chart of information recommendation method in accordance with another embodiment of the present invention;
Fig. 3 is the structural representation of information recommending apparatus according to an embodiment of the invention;
Fig. 4 is the structural representation of the information recommending apparatus according to one specific embodiment of the present invention;
Fig. 5 is the structural representation of the information recommending apparatus according to another specific embodiment of the present invention;
Fig. 6 is the structural representation of terminal unit according to an embodiment of the invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish
The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached
The embodiment of figure description is exemplary it is intended to be used for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings information recommendation method according to embodiments of the present invention, device and terminal unit are described.
Fig. 1 is the flow chart of information recommendation method according to an embodiment of the invention.It should be noted that the present invention is real
The information recommendation method applying example can be applicable to the information recommending apparatus of the embodiment of the present invention, and this information recommending apparatus can be configured in
Terminal unit.Wherein, this terminal unit can be mobile terminal, such as mobile phone, panel computer, palm PC, personal digital assistant
Etc. the hardware device with various operating systems;This terminal unit can also be PC.
As shown in figure 1, this information recommendation method can include:
S110, when the trigger condition of information recommendation is detected, obtains the current operation of user.
For example it is assumed that the information recommendation method of the embodiment of the present invention is applied to mobile terminal, this mobile terminal is use
Family provides has the application program of information recommendation function, then monitoring during user starts and use this application program,
Can determine that the trigger condition now detecting information recommendation, now can obtain the current operation of user.It is appreciated that this is current
Operation can be read stay time, put and praise operation, comment content or other users are commented on attitude of content etc..
S120, determines the current state of user according to the state machine model of current operation and the user previously generating, its
In, comprise multiple states of user in the state machine model of user, each state is used for the current operation behavior of instruction user.
Specifically, according to this current operation, find out this current operation institute from the state machine model of the user previously generating
Corresponding state, this state can be regarded as the current state of this user.For example, certain article is entered with current operation for user
Gone as a example a little praising, when getting user and currently the operation a little praised having been carried out to certain article, can according to this point praise operation from
Find out this point in state machine model and praise the corresponding state of operation, you can obtain the state that this user is currently located.
It is appreciated that in an embodiment of the present invention, the state machine model of above-mentioned user previously generates.As one kind
Example, the state machine model of this user can be previously generated by following steps:Obtain the operation behavior information of user, and to user
Operation behavior information carry out state decomposition, generate multiple states;Determine the incidence relation between multiple states;Closed according to association
Multiple states are combined by system, generate the state machine model of user.
Wherein, this operation behavior information may include but be not limited to click information (as number of clicks, click frequency etc.), reads
Stay time, point are praised, comment on content, user provides custom data, to the other users comment attitude of content, reading content
Time etc..
It is appreciated that the present invention mainly applies to state machine technique in recommendation information.For example it is assumed that the present invention
The information recommendation method of embodiment can be applicable in terminal unit, and this terminal unit provides the user to be read with information (as article)
Read the application program of function, user can pass through this application program reading information content.It is further appreciated that user is using this application
During program, some user operation behaviors can be produced, the present invention is exactly that utilization state machine technology is entered to these operation behaviors
Row state decomposition, forms the state machine model of this user.
For example, when the click information (as number of clicks, click frequency etc.) in operation behavior information, reading can be stopped
Long, point is praised, is commented on content, the custom data of user's offer, other users are commented on the attitude of content, the time of reading content
Deng, generate multiple states as dimension, such as original state (as user has just initially entered and uses state during this application program),
First state (as user enters state when having carried out commenting on content after application program), the second state are (as instruction user
The state of the stay time read using this application program) etc..That is, with each included in above-mentioned operation behavior information
Individual parameter to generate multiple states as different dimensions, and is entered the plurality of state according to the incidence relation between multiple states
Row combination is to form the state machine model of this user.
S130, generates its corresponding first recommendation information according to current state.
Specifically, after obtaining the state that this user is currently located, corresponding recommendation can be obtained according to this current state
Information.That is, the current operation of user can be obtained, and correspondence is found out from state machine model according to the current operation of user
Current state, finally according to this current state in real time to user recommend corresponding information.So, jump from a state in user
When going to next state, can constantly change recommendation information content according to the different conditions of user.
Information recommendation method according to embodiments of the present invention, when the trigger condition of information recommendation is detected, obtains user
Current operation, and determine the current state of user according to the state machine model of current operation and the user previously generating,
Afterwards, corresponding first recommendation information is generated according to current state.I.e. by the operation behavior of user is carried out decomposing generate right
The state machine model answered, when subsequently using, to determine the current state of user in real time by the current operation of user, and according to
The current state real-time update recommendation information content of user is so that user need not manually select the information content class of itself hobby
Type, simplifies the operating procedure of user, simultaneously by state machine technique is applied to information recommendation during, accelerate to user
The identification speed of hobby, improves the effect of information recommendation when user uses for the first time, improves Consumer's Experience.
In order to lift Consumer's Experience, improve the effect of information recommendation, improve the accuracy recommended, further, at this
In a bright embodiment, as shown in Fig. 2 on the basis of as shown in Figure 1, this information recommendation method may also include:
S210, obtains the user profile of user, and obtains the historical operation information of user according to user profile.
Wherein, in one embodiment of the invention, this historical operation information may include but be not limited to:Click information, read
Read stay time, put information of praising, comment content information, use habit information and the attitude information that other users are commented on content
Deng.
For example it is assumed that the information recommendation method of the embodiment of the present invention can be applicable in terminal unit, this terminal unit
Provide the user the application program with information (as article) read function, user can be by this application program reading information
Hold.When user is when using this application program, the user profile of this user can be obtained, this user profile can be that user's use should
The user name registered during application program, can also be that apps server is the random user name generating of this user, also may be used
To be the hardware information of terminal unit.After the user profile getting user, this user can be obtained according to this user profile
Historical operation information, e.g., this historical operation information may include click information (as number of clicks, click frequency etc.), read stop
Stay duration, point to praise, comment on content, custom data that user provides, to the other users comment attitude of content, reading content when
Between etc..
S220, the historical operation information according to user generates user's portrait of user.
For example, can be according to multiple ginsengs such as the use number of clicks in historical operation information, click frequency, reading stay time
Number, as vector, forms user's portrait it will be understood that this user draws a portrait in order to describe a vector space model of user preferences
(Vector space model, referred to as VSM).Thus, by the present invention in that user's Portrait brand technology, can improve and read in the recent period
Read the weight of interest classification, reduce the weight of more front reading articles.
S230, draws a portrait according to user and generates its corresponding second recommendation information.
Specifically, in one embodiment of the invention, the love of user can be obtained according to the affiliated type of user's portrait
Good type and user types, and the hobby type according to user and user types generate the second recommendation information.
More specifically, artificial intelligence machine learning algorithm can be passed through, such as SVM support vector machine, determine the institute of user's portrait
Belong to type, to obtain hobby type and the user types of this user.Finally, the hobby type according to user and user types
Generate the second recommendation information.Wherein, in this step, carrying out classification to user's portrait has two kinds of purposes:One is to use for specifying
The hobby identification at family, counts the fancy grade to some classification for certain user;Two be generate user classification, by user incorporate in
A certain class user, formed " user types ", so, can quick identifying user owning user kind when user is necessarily operated
Class.
It is appreciated that it is to be performed after step s 130 that the present embodiment only gives above-mentioned steps S210-S230
Example, and this example can not be as the concrete restriction of the present invention, for example, above-mentioned steps S210-S230 also can be in step S120
While being performed, executed.
S240, the first recommendation information and the second recommendation information are combined, and form recommendation results, and recommendation results are carried
Supply user.
Specifically, the first recommendation information and the second recommendation information can be combined, and the information after combination be carried out interior
Hold duplicate removal, afterwards, using the first recommendation information after duplicate removal and the second recommendation information as recommendation results, and this recommendation results is carried
Supply user.
In order to lift the experience of user, as a kind of example, the first recommendation information and the second recommendation information are being entered
During row combination, also can determine the information type of the first recommendation information and the second recommendation information respectively, and according to info class
These first recommendation informations and the second recommendation information are carried out sort merge by type.That is, unified information type will be belonged to
Recommendation information condenses together, and so user friendly can check and read.
In order to lift Consumer's Experience further, the wider information popularization of user can be given, further, the present invention's
In one embodiment, before recommendation results are supplied to user, this information recommendation method may also include:Determine in recommendation results
The generic of recommendation information, and determine that the dependency with generic is more than or equal to the first category of predetermined threshold value, and obtain
Take the information content belonging to first category, and using the information content belonging to first category as the 3rd recommendation information.Wherein, at this
In inventive embodiment, the process that implements that recommendation results are supplied to user may include following steps:By the 3rd recommendation
Breath and recommendation results are simultaneously supplied to user.
Specifically, before recommendation results are supplied to user, may further determine that each recommendation information in this recommendation results
Generic, and by analyze each classification content, extensive go out different user interested in the category content when, also have
May be to other category content with the category with dependency.Wherein, the generic of above-mentioned recommendation information may include skill
Art classification, amusement classification, novel classification, sports classification etc. it is possible to understand that it is also possible to according to actual needs by above-mentioned these
Classification is subdivided into multiple subclass, for example, this novel classification can be subdivided into describing love affairs, pass through, the subclass such as ancient times.
For example, when user has larger interest to classification A, and when classification A has larger dependency with classification B, class can be obtained
The information content of other B, and using the information content of category B as the 3rd recommendation information, together it is supplied to user with recommendation results.
Wherein, by big data correlation analysiss, generic can be analyzed with first category, to obtain generic and first
Dependency between classification.
In order to lift Consumer's Experience further, as much as possible information content interested for user is shown in before,
In embodiments of the invention, can be according to the dependency size of multiple first category and generic, respectively to multiple first category
Information content be ranked up, that is,:As a kind of example, when first category for multiple when, by the information belonging to first category
Hold the process that implements as the 3rd recommendation information may include:Big according to multiple first category and the dependency of generic
Little, respectively the information content belonging to multiple first category is ranked up, and by sequence after the letter belonging to multiple first category
Breath content is as the 3rd recommendation information.
For example, it is assumed that classification C and classification D are first category, the dependency size between classification C and generic A is
90%, the dependency size between classification D and generic A is 85%, can be according to the size of dependency, to classification C and classification D
It is ranked up, the information content that will belong to classification C is arranged in before the information content of generic D, finally, after sorting
Belong to the information content of classification C and classification D as the 3rd recommendation information, the 3rd recommendation information is together carried with recommendation results
Supply user.
To sum up, during information recommendation, draw a portrait to user's recommendation information by using user, and by pushing away to user
Recommend the information content having in the classification of larger dependency with the generic of the recommendation information in recommendation results, can decay use
The hobby at family, reach hobby reset purpose, provide the user other be possible to like content, to the wider information of user
Recommend.
Corresponding with the information recommendation method that above-mentioned several embodiments provide, a kind of embodiment of the present invention also provides one kind
Information recommending apparatus, the information recommendation being provided with above-mentioned several embodiments due to information recommending apparatus provided in an embodiment of the present invention
Method is corresponding, and the embodiment therefore recommending method in aforementioned information is also applied for the information recommendation dress of the present embodiment offer
Put, be not described in detail in the present embodiment.Fig. 3 is the structural representation of information recommending apparatus according to an embodiment of the invention
Figure.As shown in figure 3, this information recommending apparatus can include:First acquisition module 310, the first determining module 320 and the first generation
Module 330.
Specifically, the first acquisition module 310 can be used for, when the trigger condition of information recommendation is detected, obtaining working as of user
Front operation.
The state machine model that first determining module 320 can be used for according to current operation and the user previously generating determines to be used
The current state at family, wherein, comprises multiple states of user in the state machine model of user, each state is used for instruction user
Current operation behavior.
First generation module 330 can be used for generating its corresponding first recommendation information according to current state.
In order to lift Consumer's Experience, improve the effect of information recommendation, improve the accuracy recommended, further, at this
In a bright embodiment, as shown in figure 4, on the basis of as shown in Figure 3, this information recommending apparatus may also include:Second obtains
Delivery block 340, the second generation module 350, the 3rd generation module 360 and information providing module 370.
Wherein, the second acquisition module 340 is used for obtaining the user profile of user, and obtains going through of user according to user profile
History operation information.Wherein, in one embodiment of the invention, historical operation information may include but be not limited to:Click information, read
Read stay time, put information of praising, comment content information, use habit information and the attitude information that other users are commented on content
Deng.
The historical operation information that second generation module 350 can be used for according to user generates user's portrait of user.The three lives
Module 360 is become to can be used for generating its corresponding second recommendation information according to user's portrait.Information providing module 370 can be used for
One recommendation information and the second recommendation information are combined, and form recommendation results, and recommendation results are supplied to user.
Wherein, in an embodiment of the present invention, as shown in figure 4, the 3rd generation module 360 may include:Taxon 361
With signal generating unit 362.Wherein, taxon 361 can be used for the affiliated type according to user's portrait, obtains the hobby type of user
And user types.Signal generating unit 362 can be used for hobby type and user types generation the second recommendation information according to user.
In order to lift Consumer's Experience further, the wider information popularization of user can be given, further, the present invention's
In one embodiment, as shown in figure 5, this information recommending apparatus may also include:Second determining module 380 and the 3rd acquisition module
390.Wherein, the second determining module 380 can be used for, before recommendation results are supplied to user, determining recommendation in recommendation results
The generic of breath, and determine that the dependency with generic is more than or equal to the first category of predetermined threshold value.3rd acquisition mould
Block 390 can be used for obtaining the information content belonging to first category, and using the information content belonging to first category as the 3rd recommendation
Information.Wherein, in an embodiment of the present invention, information providing module 370 can be additionally used in:By the 3rd recommendation information and recommendation results
It is simultaneously supplied to user.
In order to lift Consumer's Experience further, as much as possible information content interested for user is shown in before,
In embodiments of the invention, can be according to the dependency size of multiple first category and generic, respectively to multiple first category
Information content be ranked up, that is,:As a kind of example, when first category for multiple when, the 3rd acquisition module 390 is specifically used
In:According to the size of multiple first category and the dependency of generic, respectively to the information content belonging to multiple first category
Be ranked up, and will sequence after belong to the information content of multiple first category as the 3rd recommendation information.
Information recommending apparatus according to embodiments of the present invention, can detect touching of information recommendation by the first acquisition module
During clockwork spring part, obtain the current operation of user, the first determining module is according to the state of current operation and the user previously generating
Machine model determines the current state of user, and the first generation module generates corresponding first recommendation information according to current state.Lead to
Cross the operation behavior to user to be decomposed to generate corresponding state machine model, so that when subsequently using, working as by user
Front operation determines in real time the current state of user, and according to the current state real-time update recommendation information content of user so that using
Family need not manually select the information content type of itself hobby, simplifies the operating procedure of user, pass through state machine skill simultaneously
During art applies to information recommendation, accelerate the identification speed to user preferences, information when user uses for the first time that improves pushes away
The effect recommended, improves Consumer's Experience.
In order to realize above-described embodiment, the invention allows for a kind of terminal unit.
Fig. 6 is the structural representation of terminal unit according to an embodiment of the invention.As shown in fig. 6, this terminal unit
May include:Housing 61, processor 62, memorizer 63, circuit board 64 and power circuit 65, wherein, circuit board 64 is placed in housing
61 interior volume surrounding, processor 62 and memorizer 63 are arranged on circuit board 64;Power circuit 65, for for terminal unit
Each circuit or device power;Memorizer 63 is used for storing executable program code;Processor 62 passes through to read memorizer 63
The executable program code of middle storage running program corresponding with executable program code, for executing following steps:
S110 ', when the trigger condition of information recommendation is detected, obtains the current operation of user.
S120 ', determines the current state of user according to the state machine model of current operation and the user previously generating.
S130 ', generates its corresponding first recommendation information according to current state.
Terminal unit according to embodiments of the present invention, when the trigger condition of information recommendation is detected, obtains working as of user
Front operation, and the current state of user, finally, root is determined according to the state machine model of current operation and the user previously generating
Generate corresponding first recommendation information according to current state.Generate corresponding shape by carrying out decomposing to the operation behavior of user
State machine model, when subsequently using, to determine the current state of user in real time, and according to user's by the current operation of user
Current state real-time update recommendation information content, so that user need not manually select the information content type of itself hobby, simplifies
The operating procedure of user, simultaneously by state machine technique is applied to information recommendation during, accelerate to user preferences
Identification speed, improves the effect of information recommendation when user uses for the first time, improves Consumer's Experience.
In order to realize above-described embodiment, the invention allows for a kind of storage medium, wherein, this storage medium is used for storing
Application program, this application program is used for the operationally information recommendation method described in execution any of the above-described embodiment of the present invention.
In order to realize above-described embodiment, the invention allows for a kind of application program, wherein, this application program is used in fortune
Information recommendation method described in execution any of the above-described embodiment of present invention during row.
In describing the invention it is to be understood that term " first ", " second " are only used for describing purpose, and can not
It is interpreted as indicating or imply relative importance or the implicit quantity indicating indicated technical characteristic.Thus, define " the
One ", the feature of " second " can be expressed or implicitly include at least one this feature.In describing the invention, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise expressly limited specifically.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be in office
Combine in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments described in this specification or example and different embodiment or example can be tied by art personnel
Close and combine.
In flow chart or here any process described otherwise above or method description are construed as, represent and include
The module of the code of executable instruction of one or more steps for realizing specific logical function or process, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by substantially simultaneously in the way of or in the opposite order, carry out perform function, this should be by the present invention
Embodiment person of ordinary skill in the field understood.
Represent in flow charts or here logic described otherwise above and/or step, for example, it is possible to be considered as to use
In the order list of the executable instruction realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system as computer based system, including processor or other can hold from instruction
Row system, device or equipment instruction fetch the system of execute instruction) use, or with reference to these instruction execution systems, device or set
Standby and use.For the purpose of this specification, " computer-readable medium " can any can be comprised, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress using with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following:There is the electricity of one or more wirings
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program thereon or other are suitable
Medium, because edlin, interpretation or if necessary with it can then be entered for example by carrying out optical scanning to paper or other media
His suitable method is processed to electronically obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realizing.For example, if realized with hardware, and the same in another embodiment, can use well known in the art under
Any one of row technology or their combination are realizing:There is the logic gates for data signal is realized with logic function
Discrete logic, there is the special IC of suitable combinational logic gate circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part step that above-described embodiment method carries
Suddenly the program that can be by completes come the hardware to instruct correlation, and described program can be stored in a kind of computer-readable storage medium
In matter, this program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, can be integrated in a processing module in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a module.Above-mentioned integrated mould
Block both can be to be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.Described integrated module is such as
Fruit using in the form of software function module realize and as independent production marketing or use when it is also possible to be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read only memory, disk or CD etc..Although having shown that above and retouching
Embodiments of the invention are stated it is to be understood that above-described embodiment is exemplary it is impossible to be interpreted as the limit to the present invention
System, those of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (10)
1. a kind of information recommendation method is it is characterised in that comprise the following steps:
When the trigger condition of information recommendation is detected, obtain the current operation of user;
Determine the current state of described user according to the state machine model of described current operation and the described user previously generating,
Wherein, multiple states of described user are comprised in the state machine model of described user, each state is used for indicating described user's
Current operation behavior;
Its corresponding first recommendation information is generated according to described current state.
2. information recommendation method as claimed in claim 1 is it is characterised in that methods described also includes:
Obtain the user profile of described user;
Obtain the historical operation information of described user according to described user profile;
Historical operation information according to described user generates user's portrait of described user;
Drawn a portrait according to described user and generate its corresponding second recommendation information;
Described first recommendation information and described second recommendation information are combined, form recommendation results, and recommend knot by described
Fruit is supplied to described user.
3. information recommendation method as claimed in claim 2 it is characterised in that described according to described user portrait generate corresponding
Second recommendation information, including:
According to the affiliated type of described user portrait, obtain hobby type and the user types of described user;
Hobby type according to described user and user types generate described second recommendation information.
4. information recommendation method as claimed in claim 2 is it is characterised in that be supplied to described user by described recommendation results
Before, methods described also includes:
Determine the generic of recommendation information in described recommendation results, and determine that the dependency with described generic is more than or waits
First category in predetermined threshold value;
Obtain and belong to the information content of described first category, and using the described information content belonging to described first category as the 3rd
Recommendation information;
Wherein, described described recommendation results are supplied to described user include:
Described 3rd recommendation information and described recommendation results are simultaneously supplied to described user.
5. information recommendation method as claimed in claim 4 it is characterised in that when described first category be multiple when, described will
Belong to the information content of described first category as the 3rd recommendation information, including:
According to the size of multiple first category and the dependency of described generic, respectively to belonging to the plurality of first category
Information content is ranked up, and will sequence after described in belong to the information content of multiple first category as described 3rd recommendation
Breath.
6. information recommendation method as claimed in claim 1 it is characterised in that described according to described current operation and in advance
Before the state machine model of the described user generating determines the current state of described user, methods described also includes:
Obtain the operation behavior information of described user, and the operation behavior information of described user is carried out with state decomposition, generate many
Individual state;
Determine the incidence relation between the plurality of state;
According to described incidence relation, the plurality of state is combined, generates the state machine model of described user.
7. a kind of information recommending apparatus are it is characterised in that comprise the following steps:
First acquisition module, for when the trigger condition of information recommendation is detected, obtaining the current operation of user;
First determining module, for determining institute according to the state machine model of described current operation and the described user previously generating
State the current state of user, wherein, in the state machine model of described user, comprise multiple states of described user, each state is used
In the current operation behavior indicating described user;
First generation module, for generating its corresponding first recommendation information according to described current state.
8. information recommending apparatus as claimed in claim 7 are it is characterised in that described device also includes:
Second acquisition module, for obtaining the user profile of described user, and obtains described user's according to described user profile
Historical operation information;
Second generation module, generates user's portrait of described user for the historical operation information according to described user;
3rd generation module, generates its corresponding second recommendation information for drawing a portrait according to described user;
Information providing module, for being combined described first recommendation information and described second recommendation information, forms and recommends knot
Really, and by described recommendation results it is supplied to described user.
9. information recommending apparatus as claimed in claim 8 are it is characterised in that described 3rd generation module includes:
Taxon, for the affiliated type drawn a portrait according to described user, obtains hobby type and user's kind of described user
Class;
Signal generating unit, generates described second recommendation information for the hobby type according to described user and user types.
10. a kind of terminal unit is it is characterised in that include:Housing, processor, memorizer, circuit board and power circuit, wherein,
Described circuit board is placed in the interior volume that described housing surrounds, and described processor and described memorizer are arranged on described circuit board
On;Described power circuit, for being each circuit of described terminal unit or device is powered;Described memorizer is used for storing can be held
Line program code;Described processor is run by the executable program code of storage in the described memorizer of reading and is held with described
The corresponding program of line program code, for executing following steps:
When the trigger condition of information recommendation is detected, obtain the current operation of user;
Determine the current state of described user according to the state machine model of described current operation and the described user previously generating,
Wherein, multiple states of described user are comprised in the state machine model of described user, each state is used for indicating described user's
Current operation behavior;
Its corresponding first recommendation information is generated according to described current state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610854882.7A CN106383895B (en) | 2016-09-27 | 2016-09-27 | Information recommendation method and device and terminal equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610854882.7A CN106383895B (en) | 2016-09-27 | 2016-09-27 | Information recommendation method and device and terminal equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106383895A true CN106383895A (en) | 2017-02-08 |
CN106383895B CN106383895B (en) | 2019-08-27 |
Family
ID=57935988
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610854882.7A Active CN106383895B (en) | 2016-09-27 | 2016-09-27 | Information recommendation method and device and terminal equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106383895B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330747A (en) * | 2017-05-16 | 2017-11-07 | 深圳和而泰智能家居科技有限公司 | Beauty appliance gear recommends method, beauty appliance and storage medium |
CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
CN109543132A (en) * | 2018-11-22 | 2019-03-29 | 深圳墨世科技有限公司 | Content recommendation method, device, electronic equipment and storage medium |
CN109767093A (en) * | 2018-12-27 | 2019-05-17 | 中国联合网络通信集团有限公司 | Object identifying method and device, storage medium |
CN109783741A (en) * | 2019-01-31 | 2019-05-21 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
CN110209915A (en) * | 2017-12-15 | 2019-09-06 | 云天弈(北京)信息技术有限公司 | A method of the information that information platform is pushed is shown by terminal |
CN110263258A (en) * | 2019-06-25 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Method, apparatus, electronic equipment and the computer-readable medium of commending contents |
CN111105819A (en) * | 2019-12-13 | 2020-05-05 | 北京达佳互联信息技术有限公司 | Clipping template recommendation method and device, electronic equipment and storage medium |
CN111414364A (en) * | 2020-03-20 | 2020-07-14 | 杭州数梦工场科技有限公司 | User information generation method and device and electronic equipment |
CN111435371A (en) * | 2019-01-15 | 2020-07-21 | 百度在线网络技术(北京)有限公司 | Video recommendation method and system, computer program product and readable storage medium |
CN111741336A (en) * | 2020-07-20 | 2020-10-02 | 杭州翔毅科技有限公司 | Video content recommendation method, device, equipment and storage medium |
CN112004134A (en) * | 2019-05-27 | 2020-11-27 | 腾讯科技(深圳)有限公司 | Multimedia data display method, device, equipment and storage medium |
CN116167829A (en) * | 2023-04-26 | 2023-05-26 | 湖南惟客科技集团有限公司 | Multidimensional and multi-granularity user behavior analysis method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110243529A1 (en) * | 2010-03-31 | 2011-10-06 | Sony Corporation | Electronic apparatus, content recommendation method, and program therefor |
CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术(北京)有限公司 | Personalized recommendation method and system according to user state |
CN103605656A (en) * | 2013-09-30 | 2014-02-26 | 小米科技有限责任公司 | Music recommendation method and device and mobile terminal |
CN105824912A (en) * | 2016-03-15 | 2016-08-03 | 平安科技(深圳)有限公司 | Personalized recommending method and device based on user portrait |
-
2016
- 2016-09-27 CN CN201610854882.7A patent/CN106383895B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110243529A1 (en) * | 2010-03-31 | 2011-10-06 | Sony Corporation | Electronic apparatus, content recommendation method, and program therefor |
CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术(北京)有限公司 | Personalized recommendation method and system according to user state |
CN103605656A (en) * | 2013-09-30 | 2014-02-26 | 小米科技有限责任公司 | Music recommendation method and device and mobile terminal |
CN105824912A (en) * | 2016-03-15 | 2016-08-03 | 平安科技(深圳)有限公司 | Personalized recommending method and device based on user portrait |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330747A (en) * | 2017-05-16 | 2017-11-07 | 深圳和而泰智能家居科技有限公司 | Beauty appliance gear recommends method, beauty appliance and storage medium |
CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
CN110209915A (en) * | 2017-12-15 | 2019-09-06 | 云天弈(北京)信息技术有限公司 | A method of the information that information platform is pushed is shown by terminal |
CN109543132A (en) * | 2018-11-22 | 2019-03-29 | 深圳墨世科技有限公司 | Content recommendation method, device, electronic equipment and storage medium |
CN109767093A (en) * | 2018-12-27 | 2019-05-17 | 中国联合网络通信集团有限公司 | Object identifying method and device, storage medium |
CN111435371A (en) * | 2019-01-15 | 2020-07-21 | 百度在线网络技术(北京)有限公司 | Video recommendation method and system, computer program product and readable storage medium |
CN111435371B (en) * | 2019-01-15 | 2023-08-11 | 百度在线网络技术(北京)有限公司 | Video recommendation method and system, computer program product and readable storage medium |
CN109783741A (en) * | 2019-01-31 | 2019-05-21 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
CN112004134A (en) * | 2019-05-27 | 2020-11-27 | 腾讯科技(深圳)有限公司 | Multimedia data display method, device, equipment and storage medium |
CN110263258A (en) * | 2019-06-25 | 2019-09-20 | 北京字节跳动网络技术有限公司 | Method, apparatus, electronic equipment and the computer-readable medium of commending contents |
CN111105819B (en) * | 2019-12-13 | 2021-08-13 | 北京达佳互联信息技术有限公司 | Clipping template recommendation method and device, electronic equipment and storage medium |
CN111105819A (en) * | 2019-12-13 | 2020-05-05 | 北京达佳互联信息技术有限公司 | Clipping template recommendation method and device, electronic equipment and storage medium |
CN111414364A (en) * | 2020-03-20 | 2020-07-14 | 杭州数梦工场科技有限公司 | User information generation method and device and electronic equipment |
CN111414364B (en) * | 2020-03-20 | 2023-08-25 | 杭州数梦工场科技有限公司 | User information generation method and device and electronic equipment |
CN111741336B (en) * | 2020-07-20 | 2021-05-11 | 杭州翔毅科技有限公司 | Video content recommendation method, device, equipment and storage medium |
CN111741336A (en) * | 2020-07-20 | 2020-10-02 | 杭州翔毅科技有限公司 | Video content recommendation method, device, equipment and storage medium |
CN116167829A (en) * | 2023-04-26 | 2023-05-26 | 湖南惟客科技集团有限公司 | Multidimensional and multi-granularity user behavior analysis method |
CN116167829B (en) * | 2023-04-26 | 2023-08-29 | 湖南惟客科技集团有限公司 | Multidimensional and multi-granularity user behavior analysis method |
Also Published As
Publication number | Publication date |
---|---|
CN106383895B (en) | 2019-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106383895A (en) | Information recommendation method and device and terminal equipment | |
Newell | Re-visions of rationality? | |
CN112632385A (en) | Course recommendation method and device, computer equipment and medium | |
CN103513890B (en) | A kind of exchange method based on picture, device and server | |
CN110400169A (en) | A kind of information-pushing method, device and equipment | |
CN104484362B (en) | Search result shows method and device | |
CN106874314A (en) | The method and apparatus of information recommendation | |
CN111160484B (en) | Data processing method, data processing device, computer readable storage medium and electronic equipment | |
CN108334887A (en) | A kind of user's choosing method and device | |
CN108256537A (en) | A kind of user gender prediction method and system | |
CN108959329B (en) | Text classification method, device, medium and equipment | |
CN106600331A (en) | Method and apparatus for running advertisements | |
CN104809195A (en) | Recommending method and recommending device of search result | |
CN107818491A (en) | Electronic installation, Products Show method and storage medium based on user's Internet data | |
CN108536784A (en) | Comment information sentiment analysis method, apparatus, computer storage media and server | |
CN110035302A (en) | Information recommendation and model training method and device calculate equipment, storage medium | |
CN109685579A (en) | A kind of data processing method based on user tag, smart television and storage medium | |
CN110263161A (en) | A kind of processing method of information, device and equipment | |
CN108648019A (en) | Promote method, apparatus, electronic equipment and the storage medium of advertisement analysis efficiency | |
CN108959323A (en) | Video classification methods and device | |
CN110490237A (en) | Data processing method, device, storage medium and electronic equipment | |
CN110389662A (en) | Content displaying method, device, storage medium and the computer equipment of application program | |
CN108694211B (en) | Application distribution method and device | |
CN114398560B (en) | Marketing interface setting method, device, equipment and medium based on WEB platform | |
CN111737479A (en) | Data acquisition method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |