CN105989045A - Method, device and system for recommending persuasion content - Google Patents
Method, device and system for recommending persuasion content Download PDFInfo
- Publication number
- CN105989045A CN105989045A CN201510060001.XA CN201510060001A CN105989045A CN 105989045 A CN105989045 A CN 105989045A CN 201510060001 A CN201510060001 A CN 201510060001A CN 105989045 A CN105989045 A CN 105989045A
- Authority
- CN
- China
- Prior art keywords
- user
- content
- advice
- attention
- 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.)
- Pending
Links
Abstract
The invention discloses a method for recommending persuasion content. The method comprises the following steps: acquiring interface content displayed on a display screen, and acquiring at least one of an attention state of user vision on the interface content and a utilization state of the interface content of a user; according at least one of the attention state and the utilization state and the interface content, determining content catching the attention of the user at present; according to the content catching the attention of the user at present, determining the persuasion content to be recommended; and representing the persuasion content to be recommended. According to the method for recommending the persuasion content, provided by the embodiment, the persuasion content to be recommended can be determined through at least one of the attention state of the user vision on the interface content and the utilization state of the interface content of the user, so that the accuracy of recommending the persuasion content is improved.
Description
Technical field
The present invention relates to Internet technical field, be specifically related to a kind of advise the method for commending contents, device and
System.
Background technology
Along with the Internet and the development of intelligent terminal, user is more and more carried out on computer and intelligent terminal
The browsing and exchanging of information.User would generally be recommended some advice letters by information content provider and service provider
Breath.But majority of case, these advice information do not cause attention and the interest of user, even by user
Mask from consciousness as unrelated or interference information, thus desired recommendation effect could not be reached.
Prior art has and has improved recommendation effect by personalized content recommendation.But depending on of personalization
According to being confined to according to user's configuration on interface, such as selected display content, or user is in operating process
In be actively entered behavior, such as search word, click behavior etc..When user does not has these to operate, or these
When the frequency of operation is relatively low, just cannot get the interest information of user.Openness the causing of data cannot be right
Advice content is recommended accurately.
Summary of the invention
The embodiment of the present invention provides a kind of method advising commending contents, can improve the standard of advice commending contents
Exactness.The embodiment of the present invention additionally provides corresponding Apparatus and system.
First aspect present invention provides a kind of method advising commending contents, including:
Obtain the interface content of display screen display, and obtain the attention on described interface content of user's sight line
Power state and user are at least one in the use state of described interface content;
According at least one in described state of attention and described use state, and described interface content,
Determine the content that user is currently paid close attention to;
The content currently paid close attention to according to described user, determines advice content to be recommended;
Present described advice content to be recommended.
In conjunction with first aspect, in the implementation that the first is possible, the described boundary obtaining display screen display
Face content, and obtain user's sight line state of attention on described interface content and user in described interface
Hold use state at least one time, described method also includes:
Obtain the appearance form of described interface content;
Described according at least one in described state of attention and described use state, and in described interface
Holding, when determining the content that user is currently paid close attention to, described method also includes:
For described interface content, determine the appearance form that user currently pays close attention to;
Described present described advice content to be recommended, including:
The appearance form currently paid close attention to described user, presents described advice content to be recommended.
In conjunction with the first possible implementation of first aspect, in the implementation that the second is possible, described
According at least one in described state of attention and described use state, and described interface content, determine
During the content that user is currently paid close attention to, described method also includes:
Determine described advice content to be recommended presents opportunity;
The described appearance form currently paid close attention to described user, presents described advice content to be recommended, including:
Opportunity is presented described, the appearance form currently paid close attention to described user, present described to be recommended advising
Lead content.
In conjunction with the implementation that first aspect, first aspect the first or the second are possible, may at the third
Implementation in, described method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content be advice content model in a content;
At least one in state of attention according to described user's sight line and user's use state, revises described
The content model of advice.
In conjunction with the implementation that first aspect the first or the second are possible, the 4th kind of possible implementation
In, described method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, the appearance form of described advice content be advice formal model in a form;
At least one in state of attention according to described user's sight line and user's use state, revises described
The formal model of advice.
In conjunction with the implementation that first aspect the second is possible, in the 5th kind of possible implementation, described
Method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content present in model on opportunity that opportunity is advice;
At least one in state of attention according to described user's sight line and user's use state, revises described
The model on opportunity of advice.
Second aspect present invention provides a kind of device advising commending contents, including:
Acquisition module, for obtaining the interface content of display screen display, and obtains user's sight line on described boundary
State of attention in the content of face and user are at least one in the use state of described interface content;
First determines module, for the described state of attention obtained according to described acquisition module and described use
At least one in state, and described interface content, determine the content that user is currently paid close attention to;
Second determines module, for determining what the described user that module determines currently was paid close attention to according to described first
Content, determines advice content to be recommended;
Present module, determine, for presenting described second, the advice content described to be recommended that module determines.
In conjunction with second aspect, in the implementation that the first is possible,
Described acquisition module, is additionally operable to obtain the appearance form of described interface content;
Described first determines module, is additionally operable to for described interface content, determines that what user currently paid close attention to presents
Form;
Described present module, specifically for determining what the described user that module determines currently paid close attention to described first
Appearance form, presents described advice content to be recommended.
In conjunction with the first possible implementation of second aspect, in the implementation that the second is possible,
Described first determines module, and be additionally operable to determine described advice content to be recommended presents opportunity;
Described present module, specifically for presenting opportunity described, present shape with what described user currently paid close attention to
Formula, presents described advice content to be recommended.
In conjunction with the implementation that second aspect, second aspect the first or the second are possible, may at the third
Implementation in,
Described device also includes: content correcting module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, described advice content is in the content model of advice
Item content;
Described content correcting module, the attention of the described user's sight line for obtaining according to described acquisition module
At least one in state and user's use state, revises the content model of described advice.
In conjunction with the implementation that second aspect the first or the second are possible, the 4th kind of possible implementation
In,
Described device also includes: form correcting module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, the appearance form of described advice content is the form of advice
A form in model;
Described form correcting module, the attention of the described user's sight line for obtaining according to described acquisition module
At least one in state and user's use state, revises the formal model of described advice.
In conjunction with the implementation that second aspect the second is possible, in the 5th kind of possible implementation,
Described device also includes: opportunity correcting module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, the opportunity that presents of described advice content is the opportunity advised
In model one;
Described opportunity correcting module, for using state according to state of attention and the user of described user's sight line
In at least one, revise the model on opportunity of described advice.
The embodiment of the present invention uses the interface content obtaining display screen display, and obtains user's sight line described
State of attention on interface content and user are at least one in the use state of described interface content;Root
According at least one in described state of attention and described use state, and described interface content, determine use
The content that family is currently paid close attention to;The content currently paid close attention to according to described user, in determining advice to be recommended
Hold;Present described advice content to be recommended.With in prior art by the way of the key word that user inputs
Determine that advice content to be recommended is compared, the method for the advice commending contents that the embodiment of the present invention provides, can
With by user in the state of attention of interface content and user's use state to described interface content
At least one determines advice content to be recommended, thus improves the accuracy of advice commending contents.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement
In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is an embodiment schematic diagram of the method advising commending contents in the embodiment of the present invention;
Fig. 2 is dynamic according to eye in the embodiment of the present invention and/or interface operation carries out content, form, opportunity
The system architecture schematic diagram of the recommendation of property;
Fig. 3 is to show the system architecture of the feedback modifiers model of advice content according to user in the embodiment of the present invention
It is intended to;
Fig. 4 A is an example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 4 B is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 5 A is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 5 B is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 6 A is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 6 B is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 6 C is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 6 D is another example schematic diagram of application scenarios in the embodiment of the present invention;
Fig. 7 is an embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Fig. 8 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Fig. 9 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Figure 10 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Figure 11 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Figure 12 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention;
Figure 13 is another embodiment schematic diagram of the device advising commending contents in the embodiment of the present invention.
Detailed description of the invention
The embodiment of the present invention puies forward a kind of method advising commending contents, can improve the accurate of advice commending contents
Degree.The embodiment of the present invention additionally provides corresponding Apparatus and system.It is described in detail individually below.
In order to make those skilled in the art be more fully understood that the present invention program, implement below in conjunction with the present invention
Accompanying drawing in example, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that institute
The embodiment described is only the embodiment of a present invention part rather than whole embodiments.Based on this
Embodiment in bright, the institute that those of ordinary skill in the art are obtained under not making creative work premise
There are other embodiments, all should belong to the scope of protection of the invention.
Refering to Fig. 1, an embodiment of the method for the advice commending contents that the embodiment of the present invention provides includes:
101, obtain the interface content of display screen display, and obtain user's sight line on described interface content
State of attention and user at least one in the use state of described interface content.
In the embodiment of the present invention, display screen display interface content can be word content, image content,
Audio content, video content etc..
During user's browse operation interface, can by front-facing camera, far infrared camera shot first-class come
Judge the region of its sight line current and interface intersection, and the state that moves of sight line and trend;Such as double far infrareds
Then photographic head can be followed the trail of by triangle polyester fibre by the imaging on the retina of the scenery on direction of visual lines
The propagation path of light, thus calculate the focus of sight line and interface;The focus position obtained according to continuous time
Put change and calculate speed and the direction realizing movement;The sight line length resident according to sight line focus and adjacent Jiao
Distance between point distinguish stare at regard, the mobile status such as pan, jumping characteristic pan continuously.
User's sight line state of attention on described interface content refers to that user's sight line is on interface content
Intensity, such as: stare at regard, the state such as pan, jumping characteristic pan continuously.
User can be come by range sensor, tactile sensor, depth camera, acceleration transducer etc.
Judge region, state and the mobile trend of operation;As user uses touching operation, then can be by pressing biography
Sensor obtains the coordinate of finger and touch screen contact position, and obtains finger and adopt continuous time at tactile sensor
Motion track under sample and speed.
User refers to user's action type to described interface content to the use state of described interface content,
As: click on redirect, drag, page turning etc..
102, according at least one in described state of attention and described use state, and described interface
Content, determines the content that user is currently paid close attention to.
103, the content currently paid close attention to according to described user, determines advice content to be recommended.
104, described advice content to be recommended is presented.
The embodiment of the present invention uses the interface content obtaining display screen display, and obtains user's sight line described
State of attention on interface content and user are at least one in the use state of described interface content;Root
According at least one in described state of attention and described use state, and described interface content, determine use
The content that family is currently paid close attention to;The content currently paid close attention to according to described user, in determining advice to be recommended
Hold;Present described advice content to be recommended.With in prior art by the way of the key word that user inputs
Determine that advice content to be recommended is compared, the method for the advice commending contents that the embodiment of the present invention provides, can
With by user in the state of attention of interface content and user's use state to described interface content
At least one determines advice content to be recommended, thus improves the accuracy of advice commending contents.
Alternatively, on the basis of the embodiment that above-mentioned Fig. 1 is corresponding, in the advice that the embodiment of the present invention provides
Hold in first alternative embodiment of the method recommended,
The described interface content obtaining display screen display, and obtain user's sight line on described interface content
When state of attention and user are at least one in the use state of described interface content, described method is also wrapped
Include:
Obtain the appearance form of described interface content;
Described according at least one in described state of attention and described use state, and in described interface
Holding, when determining the content that user is currently paid close attention to, described method also includes:
For described interface content, determine the appearance form that user currently pays close attention to;
Described present described advice content to be recommended, including:
The appearance form currently paid close attention to described user, presents described advice content to be recommended.
In the embodiment of the present invention, can not only realize advising the personalization of commending contents, it is also possible to realize recommending shape
The personalization of formula, for user preferences, presents advice content with different appearance forms, thus improves recommendation
Precision.
Alternatively, on the basis of embodiment corresponding for above-mentioned Fig. 1 or first alternative embodiment, the present invention
In second alternative embodiment of the method for the advice commending contents that embodiment provides, described according to described interface
At least one in content, and described state of attention and described use state, determines that user is currently closed
During the content noted, described method can also include:
Determine described advice content to be recommended presents opportunity;
The described appearance form currently paid close attention to described user, presents described advice content to be recommended, including:
Opportunity is presented described, the appearance form currently paid close attention to described user, present described to be recommended advising
Lead content.
In the embodiment of the present invention, can not only realize advising the personalization of commending contents, it is also possible to when realizing recommending
The personalization of machine, for the use state of user, presents advice content, thus improves and push away on suitable opportunity
The precision recommended.Certainly, on suitable opportunity, the appearance form paid close attention to user presents to be recommended advising
Lead content, further increase the precision of recommendation.
Alternatively, on the basis of embodiment corresponding for above-mentioned Fig. 1 or first or second alternative embodiment,
In 3rd alternative embodiment of the method for the advice commending contents that the embodiment of the present invention provides, described method is also
May include that
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content be advice content model in a content;
At least one in state of attention according to described user's sight line and user's use state, revises described
The content model of advice.
In the embodiment of the present invention, present advice content after, can according to user's reaction to this advice content,
As the states such as click is checked, non-concern determine that user is interested in this advice content, thus further
Revising this advice model, if user is interested, this user of labelling clicks on and checks, then characterize user and advise this
Lead content interested, if user does not pays close attention to this advice content, then characterize user and this advice content is not felt emerging
Interest, then add a negative sense sample in content model, revise this content model, in order to when recommending next time,
Evade falling this user uninterested advice content.
Alternatively, on the basis of above-mentioned first or second alternative embodiment, the embodiment of the present invention provides
Advice commending contents method the 4th alternative embodiment in, described method can also include:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, the appearance form of described advice content be advice formal model in a form;
At least one in state of attention according to described user's sight line and user's use state, revises described
The formal model of advice.
In the embodiment of the present invention, user's reaction to appearance form can be passed through, determine that this appearance form is
No user can be caused to note, if the residence time of user's sight line is long, such as: residence time exceedes preset value,
Then characterizing this appearance form to cause user and note, residence time not less than preset value, then characterizes this and presents shape
Formula does not causes user and notes, adds a negative sense sample, revise this formal model in formal model, in order to
When recommending next time, evade falling the uninterested recommendation form of this user.
Alternatively, on the basis of above-mentioned second alternative embodiment, in the advice that the embodiment of the present invention provides
Holding in the 5th alternative embodiment of the method recommended, described method can also include:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content present in model on opportunity that opportunity is advice;
At least one in state of attention according to described user's sight line and user's use state, revises described
The model on opportunity of advice.
In the embodiment of the present invention, user's reaction to appearance form can be passed through, determine that this presents opportunity and is
No user can be caused to note, if the residence time of user's sight line is long, such as: residence time exceedes preset value,
Then characterizing this appearance form to cause user and note, residence time not less than preset value, then characterizes this and presents shape
Formula does not causes user and notes, adds a negative sense sample in formal model, revises model on this on opportunity, in order to
When recommending next time, evade falling this and present opportunity.
Fig. 2 is dynamic according to eye in the embodiment of the present invention and/or interface operation carries out content, form, opportunity
The system architecture schematic diagram that propertyization is recommended.As in figure 2 it is shown, the advice commending contents that the embodiment of the present invention provides
Another embodiment of method include:
Step 1, during user's browse operation interface, by front-facing camera, far infrared camera
Etc. judging the region of active user's sight line and interface intersection, and the state that moves of sight line and trend;As double
Far infrared camera can be then fixed by triangle by the imaging on the retina of the scenery on direction of visual lines
The propagation path of light is followed the trail of in position, thus calculates the focus of sight line and interface;According to obtain continuous time
Focal position change calculates speed and the direction realizing movement;According to the resident sight line length of sight line focus and
Distance between adjacent focal spots distinguish stare at regard, the mobile status such as pan, jumping characteristic pan continuously.
Step 2, by range sensor, tactile sensor, depth camera, acceleration transducer etc. come
Judge region, state and the mobile trend of operation, as user uses touching operation, then can be by pressing biography
Sensor obtains the coordinate of finger and touch screen contact position, and obtains finger and adopt continuous time at tactile sensor
Motion track under sample and speed.
The content of element, character (such as: image-text video etc.) in step 3, analysis current interface;Can be by dividing
In analysis interface program, the information such as the definition of each element, type, content obtains.
In step 4, analysis current interface, the position of element, size, external appearance characteristic are (such as: each table of list
Item size, position, sequentially, color, frame etc.), can be by the pattern in assay surface program, spy
Levy, the information such as configuration obtains.
Step 5, from data base extract user browsed on similar interface in the past with operating habit and set up
Interest region partitioning model;Information in data base can be based on probabilistic manner statistics to include but not limited to
The form tissue of entry, as interface character (such as: news web page 52%, communication software 23%, electricity business 10%,
Game 8%, mail 5% etc.), region of interest field type corresponding to the interface of various character (such as news web page:
Short text message 51%, picture 36%, long Word message 1), the common operation that the interface of various character is corresponding
(on news web page: click on and redirect 37%, drag 30% in the page, page turning 25% etc.), various character
Common navigation patterns corresponding to interface is (on news web page: quickly continuously browse 44%, fast hop browses
27%, middling speed read 12%, read 8% at a slow speed, pan 5% etc.).
Step 6, consider current eye dynamic and or the factor such as operation, interface element, existing model, working as
Interest regional location and the scope of user is calculated on front interface;Such as with focus and/or the operation of current gaze
Position as the center in interest region, according to sight line overlay area or in history operation may come by moving area
Draw the line, it is also possible to specify range size by presetting parameter.
Step 7, consider current eye dynamic and or operation (sight line resident relative ranks, sight line for the first time are stopped
Stay duration, sight line access times repeatedly etc.), interface element, the factor such as existing model, through but not limited to
Decision tree, support vector machine (Support Vector Machine, SVM), the such classification of neutral net
Device judges the state of attention that user is current;Such as, stare at depending on if user's sight line is in or slowly browses among shape
State, then show that the attention of user compares concentration, if the user while the most continuous or saltatory pan interface,
The probability that then its absorbed degree is relatively low is bigger.Result is recorded in following organizational form
In the table that data base's state of attention is relevant: interface element < type, character, position, color, size,
Shape etc.>to move behavior<average sight line for the first time resident relative ranks, average sight line stay time, flat for-eye
All sight line access times repeatedly>-operation behavior<operational motion, average operation number of times etc.>-state of attention
<probability distribution>.
Step 8, consider current eye dynamic and or the factor such as operation, existing model, through but not limited to certainly
Plan tree, SVM, the such grader of neutral net judge the use state that user is current;Such as user is such as
Fruit presses great efforts, fast, contracted pupil of sliding on the touchscreen, has the biggest probability to be in anxiety or angry shape
State.With following organizational form, result is recorded in that database association eye is dynamic and operation behavior with make
With in the table of state: eye moves behavior < average sight line stay time, average sight line translational speed, average sight line
Cross over distance>-state of attention<probability distribution>-use state<health probability distribution, motion shape
Condition probability distribution, mental status probability distribution etc. >;Operation behavior < average operation frequency, average operation power
Degree etc.>-state of attention<probability distribution>-<health probability distribution, moving situation are general for use state
Rate distribution, mental status probability distribution etc. >.
Step 9, content according to interest region carry out the content of personalized recommendation or advice;Can use but not
It is limited to the similarity mode algorithm such as arest neighbors, page-ranking and calculates all of recommendation of Information Provider or advice letter
With content and the theme relevant entry in user's current interest region in breath.
Step 10, come personalized recommendation or advice according to the form in interest region and user's state of attention
Appearance form.Such as, in data base, search user according to the form in interest region to pay close attention to the probability of behavior and divide
Cloth, if this form can attract the user's attention power, then can organize by same or analogous mode and present
Propertyization is recommended or advice information;If the more difficult power of attracting the user's attention of this form, then in search current interface
The attention Attraction Degree of browsed element, or calculate the attention Attraction Degree of all elements on interface, choose
It is easier to obtain the presentation mode of user's concern to show personalized recommendation or advice information.
Step 11, come according to user's state of attention and use state personalized recommendation or advice in now
Machine;According to the record in data base, through but not limited to decision tree, SVM, such point of neutral net
Class device judges, under current state of attention and use state, whether user can pay close attention to emerging information.
Step 12, currently used personalized recommendation or advice information be recorded in data base, organizational form
Can be but be not limited to: information content classification (such as restaurant), information source (as masses comment on), information tool
Internal appearance (such as certain restaurant), information position of appearing and carrier are (such as the coordinate on main interface, on screen
The relative position of the information that position is currently paid close attention to user or individually carrier such as pop-up window), information
The form that presents is (if word size pattern color, picture are with or without the approximation of the information currently paid close attention to user
Degree etc.), information opportunity (as presented when user is in certain read state) etc. of presenting.
Step 13, mutual according to the response of user and reality, record user browses and operating habit, no
Update disconnectedly individualized content, form, the prediction judgment models on opportunity (form include but not limited to decision tree,
The graders such as SVM).
With prior art determines by the way of the key word that user inputs advice content phase to be recommended
Ratio, the method for the advice commending contents that the embodiment of the present invention provides, user's note to interface content can be passed through
Meaning power state and user determine to be recommended advising at least one in the use state of described interface content
Lead content, thus improve the accuracy of advice commending contents.
Fig. 3 is to show the system architecture of the feedback modifiers model of advice content according to user in the embodiment of the present invention
It is intended to.As it is shown on figure 3, the Modifying model embodiment that the embodiment of the present invention provides includes:
Step 31, during user's browser interface, by front-facing camera, far infrared camera shot first-class come
Judge the region of its sight line current and interface intersection, and the state that moves of sight line and trend;Such as double far infrareds
Photographic head can be chased after by triangle polyester fibre by the imaging on the retina of the scenery on direction of visual lines the most again
The propagation path of track light, thus calculate the focus of sight line and interface;The focus obtained according to continuous time
Change in location calculates speed and the direction realizing movement;The sight line length resident according to sight line focus and adjacent
Distance between focus distinguish stare at regard, the mobile status such as pan, jumping characteristic pan continuously.
Step 32, by range sensor, tactile sensor, depth camera, acceleration transducer etc. come
Judge region, state and the mobile trend of operation;As user uses touching operation, then can be by pressing biography
Sensor obtains the coordinate of finger and touch screen contact position, and obtains finger and adopt continuous time at tactile sensor
Motion track under sample and speed.
Step 33, the recommendation presented obtained from data base in current interface or the content of advice information,
Appearance form and present opportunity.
Step 34, extract user browsed on similar interface in the past with operating habit and the interest region set up is drawn
Sub-model (form includes but not limited to the graders such as decision tree, SVM, neutral net).
Step 35, consider current eye dynamic and or operation, it is judged that in current interface, whether user has note
Meaning is to advice Neil;Whether i.e. sight line has resident, and whether resident order and duration reach threshold value, in information
On whether have such as to click on and the operation behavior etc. such as browse.
Step 36, as no, then in appearance form and opportunity model classifiers, add a negative sense sample, repair
The appearance form model just recommended or advise, model on opportunity.
Step 37, in this way, then consider current eye dynamic and or operation judges whether to advice content
Interested.
Step 38, as no, then toward advice content model grader in add a negative sense sample, revise advice
Content model.
Step 39, in this way, then add a forward sample toward advice content, form and opportunity in model classifiers
This.
In the embodiment of the present invention, present advice content after, can according to user's reaction to this advice content,
Determining whether this appearance form can cause user to note, whether the opportunity interrupting user namely presents opportunity
Properly, as the states such as click is checked, non-concern determine that user is interested in this advice content, thus
Revising this advice model further, if user is interested, this user of labelling clicks on and checks, then characterize user
Interested in this advice content, if user does not pays close attention to this advice content, then characterize user to this advice content
Lose interest in, then in content model, add a negative sense sample, revise this content model, in order in next time
During recommendation, evade falling this user uninterested advice content.A negative sense sample is added in formal model,
Revise this formal model, in order to when recommending next time, evade falling the uninterested recommendation form of this user.
In formal model, add a negative sense sample, revise model on this, in order to when recommending next time, evade falling on opportunity
This presents opportunity.
Content model, formal model and model on opportunity can be that propertyization recommends advice model one by one.Can also
Time separate model, the embodiment of the present invention does not limits.
The process of setting up of the Personalization recommendation model in the embodiment of the present invention is expressed as follows:
User-interested region (center, area size present form etc.) model R=f (I, E, G, M)
Region,Interface,Eye-tracking,Gesture,Model
I: the feature of interactive elements on interface, such as element morphology (figure, word), content, position, row
Dependency etc. between cloth, packet, and distinct interaction element.
The eye of E: user moves information, such as the focal position of current gaze, the distance of focus jump, jump
Direction that frequency, sight line move, the speed etc. of movement.
The operation information of G: user, such as the position of current operation, the speed of operation, the frequency of operation, hands
The dynamic direction of potential shift, the speed etc. of movement.
Browse, on M: user similar interface in the past, the interest region being accustomed to operation behavior and set up and divide mould
Type.
Interest region divides and/or operation information dynamic with reference to eye, it should be ensured that the integrity of element content.
Form includes but not limited to the graders such as decision tree, SVM, neutral net.
User's state of attention (focus, scope, intensity etc.) model A=f (I, E, G, M) Attention,
Interface,Eye-tracking,Gesture,Model。
I: the feature of interactive elements on interface, such as element morphology (figure, word), the size of element, face
Contrast etc. between color, position and distinct interaction element, it is judged that prediction user's attention is easily by what
The appearance form of sample attracts.
The eye of E: user moves information, such as the focal position of current gaze, the distance of focus jump, jump
Direction that frequency, sight line move, the speed etc. of movement, it is judged that the prediction position of user's attention, scope and
Concentration degree.
The operation information of G: user, such as the position of current operation, the speed of operation, the frequency of operation, hands
The dynamic direction of potential shift, the speed etc. of movement, it is judged that predict position and the concentration degree of user's attention.
Browse, on M: user similar interface in the past, the attention being accustomed to operation behavior and set up and judge prediction
Model.
Form includes but not limited to the graders such as decision tree, SVM, neutral net.
User uses state (mental status, condition, task status etc.) model R=f (E, G, M)
Region,Eye-tracking,Gesture,Model。
The eye of E: user moves information, such as the focal position of current gaze, the distance of focus jump, jump
Direction that frequency, sight line move, the speed etc. of movement.
The operation information of G: user, such as the position of current operation, the speed of operation, the frequency of operation, hands
The dynamic direction of potential shift, the speed etc. of movement.
Browse, on M: user similar interface in the past, the use condition adjudgement being accustomed to and set up with operation behavior pre-
Survey model.
Form includes but not limited to the graders such as decision tree, SVM, neutral net.
That recommends/advise finally presents model D=f (C, Y, T) Display, Content, Format, Timing
Content C=f1 (P, Q) presented, according to P, Q to likely content carry out relevancy ranking screening
The object that P: user's sight line is paid close attention to.
The object of Q: user operation.
Form (pattern, the position etc.) F=f2 (M, N) presented, choose that most probable causes that user notes in
Existing position and mode.
M: the pattern of user's sight line perpetual object, contrast etc..
N: user's sight line track, possible resident area etc..
The T=f3 on opportunity (R, S, T) presented, chooses and does not affects user and normally use and read, it is possible to draw
Play user to note, and the opportunity easily paid close attention in detail by user and receive.
R: user's sight line behavior, such as reading, fast browsing etc. at a slow speed.
S: user operation behavior, such as word input, handles scroll bar etc..
T: context, such as user movement state, user's body and the mental status etc..
Advice content, the appearance form recommended and presenting can understand refering to Fig. 4 A to Fig. 6 D opportunity,
Wherein, Fig. 4 A is the content determining user's current interest, and Fig. 4 B is that the content for current interest pushes away
Recommend and advise content accordingly.Fig. 5 A is to determine the form that user currently pays close attention to, and Fig. 5 B is for currently to close with user
The form of note presents the advice content of recommendation.Fig. 6 A and Fig. 6 B is the proper moment recommending advice content, point
When browsing for noncontinuity reading and middling speed or search for.Fig. 6 C and Fig. 6 D is to recommend advice content not
Appropriate opportunity, respectively during walking states and during fatigue state.
Below as a example by qualifying typical scene, illustrate the embodiment of the present invention is recommended the embodiment of advice content.
Such as:
User searches for restaurant information on smart mobile phone.The program analysis user that the embodiment of the present invention provides is current
Sight line focus is paying close attention to western-style food more, is therefore advised as recommendation by the western-style food of unsoundness, low-heat type menu
Main contents.Walking when, browse mobile phone before user, the most do not show recommendation information.User is on ground
After sitting down on ferrum, according to current gaze position on the page, similar restaurant information is used to present style,
Recommendation information is presented at the next group rolled.
User browses science and technology news at computer.The present invention is stopped on headline, summary by the sight line of user
Situation about staying and news click information, determine that user is interested in iPhone Related product.Therefore, will push away
Recommend/advice information is set to such as relevant to motion tracking iPhone app.When user reads in detail carrying out article
When, do not show recommendation/advice.When user terminates to read, restart middle fast browsing headline
Time, the form interested by this users such as audio-visual, animations carries out related content recommendation.
User uses panel computer to play game.When user is for the game state of string oneself up and time long
After between during fatigue state, it is not eager to recommend or advice.User, when process switching rest, played according to it
The content being concerned about in journey, such as fight scenes, recommends similar game, and uses field of fighting more in recommendation
Scape.
The device 20 of the advice commending contents that the embodiment of the present invention provides can be the terminal such as mobile phone, computer,
It can also be a functional module in mobile phone, computer.
Refering to Fig. 7, an embodiment of the device 20 of the advice commending contents that the embodiment of the present invention provides includes:
Acquisition module 201, for obtaining the interface content of display screen display, and obtains user's sight line in institute
State the state of attention on interface content and user at least one in the use state of described interface content;
First determines module 202, for the described state of attention obtained according to described acquisition module 201 and institute
State at least one in use state, and described interface content, determine the content that user is currently paid close attention to;
Second determines module 203, for determining, according to described first, the current institute of described user that module 202 determines
The content paid close attention to, determines advice content to be recommended;
Present module 204, for present described second determine the advice described to be recommended that module 203 determines in
Hold.
In the embodiment of the present invention, acquisition module 201 obtains the interface content of display screen display, and obtains use
Family sight line state of attention on described interface content and user are in the use state of described interface content
At least one;First determine described state of attention that module 202 obtains according to described acquisition module 201 and
At least one in described use state, and described interface content, determine the content that user is currently paid close attention to;
In second determines according to described first, module 203 determines that the described user that module 202 determines currently is paid close attention to
Hold, determine advice content to be recommended;Present module 204 to present described second and determine the institute that module 203 determines
State advice content to be recommended.Wait to push away with prior art determines by the way of the key word that user inputs
The advice content recommended is compared, the device of the advice commending contents that the embodiment of the present invention provides, and can pass through user
At least one in the state of attention of interface content and user's use state to described interface content is come
Determine advice content to be recommended, thus improve the accuracy of advice commending contents.
Alternatively, on the basis of the embodiment that above-mentioned Fig. 7 is corresponding, refering to Fig. 8, the embodiment of the present invention provides
Advice commending contents device 20 first alternative embodiment in,
Described acquisition module 201, is additionally operable to obtain the appearance form of described interface content;
Described first determines module 202, is additionally operable to, for described interface content, determine what user currently paid close attention to
Appearance form;
Described present module 204, specifically for determining that the described user that module 202 determines is current with described first
The appearance form paid close attention to, presents described advice content to be recommended.
Alternatively, on the basis of first corresponding for above-mentioned Fig. 8 alternative embodiment, the embodiment of the present invention carries
In second alternative embodiment of the device 20 of the advice commending contents of confession,
Described first determines module 202, and be additionally operable to determine described advice content to be recommended presents opportunity;
Described present module 204, specifically for presenting opportunity described, with described user currently pay close attention in
Existing form, presents described advice content to be recommended.
Alternatively, on the basis of embodiment corresponding for above-mentioned Fig. 7, first or second alternative embodiment,
Refering to Fig. 9, in the 3rd alternative embodiment of the device 20 of the advice commending contents that the embodiment of the present invention provides,
Described device 20 also includes: content correcting module 205,
Described acquisition module 201, is additionally operable to, for the described advice content presented, obtain user's sight line
At least one in state of attention and user's use state, described advice content is in the content model of advice
A content;
Described content correcting module 205, for the described user's sight line according to the acquisition of described acquisition module 201
At least one in state of attention and user's use state, revises the content model of described advice.
Alternatively, on the basis of first of said apparatus 20 or second alternative embodiment, refering to Figure 10,
In 4th alternative embodiment of the device 20 of the advice commending contents that the embodiment of the present invention provides, described device
20 also include: form correcting module 206,
Described acquisition module 201, is additionally operable to, for the described advice content presented, obtain user's sight line
At least one in state of attention and user's use state, the appearance form of described advice content is advice
A form in formal model;
Described form correcting module 206, for the described user's sight line according to the acquisition of described acquisition module 201
At least one in state of attention and user's use state, revises the formal model of described advice.
Alternatively, on the basis of second alternative embodiment of said apparatus 20, refering to Figure 11, the present invention
In 5th alternative embodiment of the device 20 of the advice commending contents that embodiment provides, described device 20 also wraps
Include: opportunity correcting module 207,
Described acquisition module 201, is additionally operable to, for the described advice content presented, obtain user's sight line
At least one in state of attention and user's use state, the opportunity that presents of described advice content is advice
In opportunity model one;
Described opportunity correcting module 207, for described user's sight line of obtaining according to described acquisition module 201
At least one in state of attention and user's use state, revises the model on opportunity of described advice.
In multiple embodiments of the device of above-mentioned advice commending contents, it should be appreciated that realize in one
Under mode, acquisition module, first determine module, second determine module, content correcting module, form correction
Module and correcting module on opportunity can be can be realized by the program in processor execution memorizer or instruction
(in other words, i.e. by the special instruction phase interworking in processor and the memorizer that couples with described processor
Incompatible realization);Under another kind of implementation, acquisition module, first determine module, second determine module,
Content correcting module, form correcting module and correcting module on opportunity can be realized by proprietary circuit respectively,
Specific implementation sees prior art, repeats no more here;Under another implementation, acquisition module,
First determine module, second determine module, content correcting module, form correcting module and correcting module on opportunity
Field programmable gate array (FPGA, Field-Programmable Gate Array) can also be passed through
Realizing, specific implementation sees prior art, repeats no more here, and the present invention includes but not limited to aforementioned
Implementation, it should be appreciated that as long as the scheme realized according to the thought of the present invention, both fall within the present invention
The scope that embodiment is protected.
Present embodiments provide the hardware configuration of a kind of device advising commending contents, shown in Figure 12, one
The hardware configuration of the device planting advice commending contents may include that
Transceiving device, software components and hardware device three part;
Transceiving device is the hardware circuit for completing pack receiving and transmitting;
Hardware device also can claim " hardware processing module ", or simpler, it is possible to referred to as " hardware ",
Hardware device mainly includes (also to coordinate other supporting devices based on FPGA, ASIC etc special hardware circuit
Part, such as memorizer) realize the hardware circuit of some specific function, its processing speed compares general processor
Often a lot of soon, but function one is customized, is just difficult to change, therefore, it is achieved get up and dumb, logical
It is commonly used to process some fixing functions.It should be noted that hardware device is in actual applications, it is also possible to
The processor such as including MCU (microprocessor, such as single-chip microcomputer) or CPU, but these processors is main
Function has been not the process of big data, and is mainly used in carrying out some and controls, under this application scenarios,
The system arranged in pairs or groups by these devices is hardware device.
Software components (or also simple " software ") mainly include general processor (such as CPU) and
The device (such as the storage device such as internal memory, hard disk) that some of is supporting, can allow process utensil by programming
Standby process function accordingly, when realizing with software, can be according to business demand flexible configuration, but often speed
Degree wants slow for comparing hardware device.After software processes is complete, the data that will be able to have been processed by hardware device
It is transmitted by transceiving device, it is also possible to sent out to transceiving device by an interface being connected with transceiving device
Send the data processed.
In the present embodiment, other functions of hardware device and software components are discussed the most in detail
State, repeat no more here.
Below in conjunction with the accompanying drawings with regard to acquisition module, first determine module, second determine module, content correcting module,
Form correcting module can be can be performed the program in memorizer by processor or instruct the technology realized
Scheme does detailed introduction:
Figure 12 is the structural representation of the device 20 of the advice commending contents that the embodiment of the present invention provides.Described advise
Lead the device 20 of commending contents include processor 210, memorizer 250 and input/output (I/O,
Input/Output) equipment 230, such as: network interface card.Memorizer 250 can include read only memory and random access memory
Memorizer, and provide operational order and data to processor 210.A part for memorizer 250 can also include
Nonvolatile RAM (NVRAM).
In some embodiments, memorizer 250 stores following element, executable module or data
Structure, or their subset, or their superset:
In embodiments of the present invention, by calling the operational order of memorizer 250 storage, (this operational order can
Storage is in an operating system),
Obtain the interface content of display screen display, and obtain the attention on described interface content of user's sight line
Power state and user are at least one in the use state of described interface content;
According at least one in described state of attention and described use state, and described interface content,
Determine the content that user is currently paid close attention to;
The content currently paid close attention to according to described user, determines advice content to be recommended;
Present described advice content to be recommended.
Visible, with prior art in by the way of the key word that user inputs, determine advice to be recommended in
Appearance is compared, the method for the advice commending contents that the embodiment of the present invention provides, can be by user to interface content
State of attention and user at least one in the use state of described interface content is determined to be recommended
Advice content, thus improve advice commending contents accuracy.
Processor 210 controls the operation of the device 20 of advice commending contents, and processor 210 can also be referred to as CPU
(Central Processing Unit, CPU).Memorizer 250 can include read only memory and
Random access memory, and provide instruction and data to processor 210.A part for memorizer 250 is all right
Including nonvolatile RAM (NVRAM).Concrete application is advised the dress of commending contents
Putting each assembly of 20 to be coupled by bus system 220, wherein bus system 220 is except including that data are total
Outside line, it is also possible to include power bus, control bus and status signal bus in addition etc..But in order to understand
See from tomorrow, in the drawings various buses are all designated as bus system 220.
The method that the invention described above embodiment discloses can apply in processor 210, or by processor 210
Realize.Processor 210 is probably a kind of IC chip, has the disposal ability of signal.Realizing
Cheng Zhong, each step of said method can be by the integrated logic circuit of the hardware in processor 210 or soft
The instruction of part form completes.Above-mentioned processor 210 can be general processor, digital signal processor
(DSP), special IC (ASIC), ready-made programmable gate array (FPGA) or other can compile
Journey logical device, discrete gate or transistor logic, discrete hardware components.Can realize or perform
Disclosed each method, step and logic diagram in the embodiment of the present invention.General processor can be micro-process
Device or this processor can also be the processors etc. of any routine.In conjunction with the side disclosed in the embodiment of the present invention
The step of method can be embodied directly in hardware decoding processor and perform, or hard with in decoding processor
Part and software module combination execution complete.Software module may be located at random access memory, flash memory, read-only storage
Device, ripe the depositing in this area such as programmable read only memory or electrically erasable programmable memorizer, depositor
In storage media.This storage medium is positioned at memorizer 250, and processor 210 reads the information in memorizer 250,
The step of said method is completed in conjunction with its hardware.
Alternatively, processor 210 specifically for:
Obtain the appearance form of described interface content;
For described interface content, determine the appearance form that user currently pays close attention to;
The appearance form currently paid close attention to described user, presents described advice content to be recommended.
Visible, in the embodiment of the present invention, can not only realize advising the personalization of commending contents, it is also possible to realize
The personalization of recommendation form, for user preferences, presents advice content with different appearance forms, thus carries
The high precision recommended.
Alternatively, processor 210 specifically for:
Determine described advice content to be recommended presents opportunity;
Opportunity is presented described, the appearance form currently paid close attention to described user, present described to be recommended advising
Lead content.
Visible, in the embodiment of the present invention, can not only realize advising the personalization of commending contents, it is also possible to realize
The personalization on recommendation opportunity, for the use state of user, presents advice content on suitable opportunity, thus
Improve the precision recommended.Certainly, on suitable opportunity, the appearance form paid close attention to user presents to be waited to push away
The advice content recommended, further increases the precision of recommendation.
Alternatively, processor 210 is additionally operable to:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content be advice content model in a content;
At least one in state of attention according to described user's sight line and user's use state, revises described
The content model of advice.
In the embodiment of the present invention, present advice content after, can according to user's reaction to this advice content,
As the states such as click is checked, non-concern determine that user is interested in this advice content, thus further
Revising this advice model, if user is interested, this user of labelling clicks on and checks, then characterize user and advise this
Lead content interested, if user does not pays close attention to this advice content, then characterize user and this advice content is not felt emerging
Interest, then add a negative sense sample in content model, revise this content model, in order to when recommending next time,
Evade falling this user uninterested advice content.
Alternatively, processor 210 is additionally operable to:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, the appearance form of described advice content be advice formal model in a form;
At least one in state of attention according to described user's sight line and user's use state, revises described
The formal model of advice.
In the embodiment of the present invention, user's reaction to appearance form can be passed through, determine that this appearance form is
No user can be caused to note, if the residence time of user's sight line is long, such as: residence time exceedes preset value,
Then characterizing this appearance form to cause user and note, residence time not less than preset value, then characterizes this and presents shape
Formula does not causes user and notes, adds a negative sense sample, revise this formal model in formal model, in order to
When recommending next time, evade falling the uninterested recommendation form of this user.
Alternatively, processor 210 is additionally operable to:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content present in model on opportunity that opportunity is advice;
At least one in state of attention according to described user's sight line and user's use state, revises described
The model on opportunity of advice.
In the embodiment of the present invention, user's reaction to appearance form can be passed through, determine that this presents opportunity and is
No user can be caused to note, if the residence time of user's sight line is long, such as: residence time exceedes preset value,
Then characterizing this appearance form to cause user and note, residence time not less than preset value, then characterizes this and presents shape
Formula does not causes user and notes, adds a negative sense sample in formal model, revises model on this on opportunity, in order to
When recommending next time, evade falling this and present opportunity.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment
Suddenly the program that can be by completes to instruct relevant hardware (such as processor), and this program can store
In a computer-readable recording medium, storage medium may include that ROM, RAM, disk or CD
Deng.
The advice method of commending contents, device and the system that are thered is provided the embodiment of the present invention above are carried out
Being discussed in detail, principle and the embodiment of the present invention are set forth by specific case used herein, with
The explanation of upper embodiment is only intended to help to understand method and the core concept thereof of the present invention;Simultaneously for this
The those skilled in the art in field, according to the thought of the present invention, the most all can
Change part, and in sum, this specification content should not be construed as limitation of the present invention.
Claims (12)
1. the method advising commending contents, it is characterised in that including:
Obtain the interface content of display screen display, and obtain the attention on described interface content of user's sight line
Power state and user are at least one in the use state of described interface content;
According at least one in described state of attention and described use state, and described interface content,
Determine the content that user is currently paid close attention to;
The content currently paid close attention to according to described user, determines advice content to be recommended;
Present described advice content to be recommended.
Method the most according to claim 1, it is characterised in that the boundary of described acquisition display screen display
Face content, and obtain user's sight line state of attention on described interface content and user in described interface
Hold use state at least one time, described method also includes:
Obtain the appearance form of described interface content;
Described according at least one in described state of attention and described use state, and in described interface
Holding, when determining the content that user is currently paid close attention to, described method also includes:
For described interface content, determine the appearance form that user currently pays close attention to;
Described present described advice content to be recommended, including:
The appearance form currently paid close attention to described user, presents described advice content to be recommended.
Method the most according to claim 2, it is characterised in that described according to described state of attention and
At least one in described use state, and described interface content, determine the content that user is currently paid close attention to
Time, described method also includes:
Determine described advice content to be recommended presents opportunity;
The described appearance form currently paid close attention to described user, presents described advice content to be recommended, including:
Opportunity is presented described, the appearance form currently paid close attention to described user, present described to be recommended advising
Lead content.
4. according to the arbitrary described method of claim 1-3, it is characterised in that described method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content be advice content model in a content;
At least one in state of attention according to described user's sight line and user's use state, revises described
The content model of advice.
The most according to the method in claim 2 or 3, it is characterised in that described method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, the appearance form of described advice content be advice formal model in a form;
At least one in state of attention according to described user's sight line and user's use state, revises described
The formal model of advice.
Method the most according to claim 3, it is characterised in that described method also includes:
For the described advice content presented, the state of attention and the user that obtain user's sight line use state
In at least one, described advice content present in model on opportunity that opportunity is advice;
At least one in state of attention according to described user's sight line and user's use state, revises described
The model on opportunity of advice.
7. the device advising commending contents, it is characterised in that including:
Acquisition module, for obtaining the interface content of display screen display, and obtains user's sight line on described boundary
State of attention in the content of face and user are at least one in the use state of described interface content;
First determines module, for the described state of attention obtained according to described acquisition module and described use
At least one in state, and described interface content, determine the content that user is currently paid close attention to;
Second determines module, for determining what the described user that module determines currently was paid close attention to according to described first
Content, determines advice content to be recommended;
Present module, determine, for presenting described second, the advice content described to be recommended that module determines.
Device the most according to claim 7, it is characterised in that
Described acquisition module, is additionally operable to obtain the appearance form of described interface content;
Described first determines module, is additionally operable to for described interface content, determines that what user currently paid close attention to presents
Form;
Described present module, specifically for determining what the described user that module determines currently paid close attention to described first
Appearance form, presents described advice content to be recommended.
Device the most according to claim 8, it is characterised in that
Described first determines module, and be additionally operable to determine described advice content to be recommended presents opportunity;
Described present module, specifically for presenting opportunity described, present shape with what described user currently paid close attention to
Formula, presents described advice content to be recommended.
10. according to the arbitrary described device of claim 7-9, it is characterised in that described device also includes:
Content correcting module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, described advice content is in the content model of advice
Item content;
Described content correcting module, the attention of the described user's sight line for obtaining according to described acquisition module
At least one in state and user's use state, revises the content model of described advice.
11. devices according to claim 8 or claim 9, it is characterised in that described device also includes: form
Correcting module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, the appearance form of described advice content is the form of advice
A form in model;
Described form correcting module, the attention of the described user's sight line for obtaining according to described acquisition module
At least one in state and user's use state, revises the formal model of described advice.
12. devices according to claim 9, it is characterised in that described device also includes: time machine maintenance
Positive module,
Described acquisition module, is additionally operable to, for the described advice content presented, obtain the attention of user's sight line
At least one in power state and user's use state, the opportunity that presents of described advice content is the opportunity advised
In model one;
Described opportunity correcting module, for using state according to state of attention and the user of described user's sight line
In at least one, revise the model on opportunity of described advice.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510060001.XA CN105989045A (en) | 2015-02-04 | 2015-02-04 | Method, device and system for recommending persuasion content |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510060001.XA CN105989045A (en) | 2015-02-04 | 2015-02-04 | Method, device and system for recommending persuasion content |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105989045A true CN105989045A (en) | 2016-10-05 |
Family
ID=57036251
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510060001.XA Pending CN105989045A (en) | 2015-02-04 | 2015-02-04 | Method, device and system for recommending persuasion content |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105989045A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106959749A (en) * | 2017-02-20 | 2017-07-18 | 浙江工业大学 | A kind of vision attention behavior cooperating type method for visualizing and system based on eye-tracking data |
CN107844257A (en) * | 2017-11-06 | 2018-03-27 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
WO2018068514A1 (en) * | 2016-10-13 | 2018-04-19 | 深圳市中兴微电子技术有限公司 | Method, device and system for analyzing user operation behaviors, and computer storage medium |
CN108563778A (en) * | 2018-04-24 | 2018-09-21 | 北京市商汤科技开发有限公司 | A kind of concern processing method and processing device of information, storage medium, electronic equipment |
CN109933723A (en) * | 2019-03-07 | 2019-06-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN110019893A (en) * | 2018-08-28 | 2019-07-16 | 京东方科技集团股份有限公司 | A kind of paintings acquisition methods and device |
CN110598086A (en) * | 2018-05-25 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Article recommendation method and device, computer equipment and storage medium |
CN115827715A (en) * | 2023-02-08 | 2023-03-21 | 上海合见工业软件集团有限公司 | Search recommendation list generation system based on user behaviors and design hierarchical tree |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102387207A (en) * | 2011-10-21 | 2012-03-21 | 华为技术有限公司 | Push method and system based on user feedback information |
CN102496012A (en) * | 2011-12-14 | 2012-06-13 | 上海海事大学 | Device and method for discovering potential demands based on eye movement tracking and historical behavior |
CN103019550A (en) * | 2012-12-07 | 2013-04-03 | 东软集团股份有限公司 | Real-time display method and system for associated content |
CN103077217A (en) * | 2012-12-28 | 2013-05-01 | 北京百度网讯科技有限公司 | Method, device and equipment for providing result additional information matched with query sequence |
CN103678647A (en) * | 2013-12-20 | 2014-03-26 | Tcl集团股份有限公司 | Method and system for recommending information |
-
2015
- 2015-02-04 CN CN201510060001.XA patent/CN105989045A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102387207A (en) * | 2011-10-21 | 2012-03-21 | 华为技术有限公司 | Push method and system based on user feedback information |
CN102496012A (en) * | 2011-12-14 | 2012-06-13 | 上海海事大学 | Device and method for discovering potential demands based on eye movement tracking and historical behavior |
CN103019550A (en) * | 2012-12-07 | 2013-04-03 | 东软集团股份有限公司 | Real-time display method and system for associated content |
CN103077217A (en) * | 2012-12-28 | 2013-05-01 | 北京百度网讯科技有限公司 | Method, device and equipment for providing result additional information matched with query sequence |
CN103678647A (en) * | 2013-12-20 | 2014-03-26 | Tcl集团股份有限公司 | Method and system for recommending information |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018068514A1 (en) * | 2016-10-13 | 2018-04-19 | 深圳市中兴微电子技术有限公司 | Method, device and system for analyzing user operation behaviors, and computer storage medium |
CN106959749B (en) * | 2017-02-20 | 2019-11-29 | 浙江工业大学 | A kind of vision attention behavior cooperating type method for visualizing and system based on eye-tracking data |
CN106959749A (en) * | 2017-02-20 | 2017-07-18 | 浙江工业大学 | A kind of vision attention behavior cooperating type method for visualizing and system based on eye-tracking data |
CN107844257A (en) * | 2017-11-06 | 2018-03-27 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
CN107844257B (en) * | 2017-11-06 | 2020-04-21 | Oppo广东移动通信有限公司 | Information display method, device, terminal and storage medium |
CN108563778A (en) * | 2018-04-24 | 2018-09-21 | 北京市商汤科技开发有限公司 | A kind of concern processing method and processing device of information, storage medium, electronic equipment |
WO2019206038A1 (en) * | 2018-04-24 | 2019-10-31 | 北京市商汤科技开发有限公司 | Attention information processing method and apparatus, storage medium, and electronic device |
CN108563778B (en) * | 2018-04-24 | 2022-11-04 | 北京市商汤科技开发有限公司 | Method and device for processing attention information, storage medium and electronic equipment |
CN110598086A (en) * | 2018-05-25 | 2019-12-20 | 腾讯科技(深圳)有限公司 | Article recommendation method and device, computer equipment and storage medium |
CN110598086B (en) * | 2018-05-25 | 2020-11-24 | 腾讯科技(深圳)有限公司 | Article recommendation method and device, computer equipment and storage medium |
US11763145B2 (en) | 2018-05-25 | 2023-09-19 | Tencent Technology (Shenzhen) Company Limited | Article recommendation method and apparatus, computer device, and storage medium |
CN110019893A (en) * | 2018-08-28 | 2019-07-16 | 京东方科技集团股份有限公司 | A kind of paintings acquisition methods and device |
US11126822B2 (en) | 2018-08-28 | 2021-09-21 | Boe Technology Group Co., Ltd. | Method and apparatus for obtaining painting |
CN109933723A (en) * | 2019-03-07 | 2019-06-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN115827715A (en) * | 2023-02-08 | 2023-03-21 | 上海合见工业软件集团有限公司 | Search recommendation list generation system based on user behaviors and design hierarchical tree |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105989045A (en) | Method, device and system for recommending persuasion content | |
TWI701959B (en) | Method, device, terminal, and storage medium for pusing information based on instant messaging | |
WO2021232930A1 (en) | Application screen splitting method and apparatus, storage medium and electric device | |
WO2015135354A1 (en) | Search method, system, and device. | |
CN106686063A (en) | Information recommendation method and apparatus, and electronic device | |
CN106202316A (en) | Merchandise news acquisition methods based on video and device | |
US20190087884A1 (en) | Theme recommendation method and apparatus | |
TWI680400B (en) | Device and method of managing user information based on image | |
US20170160907A1 (en) | Keyword-based user interface in electronic device | |
CN108228720B (en) | Identify method, system, device, terminal and the storage medium of target text content and original image correlation | |
CN108475096A (en) | Information display method and device and terminal equipment | |
CN106844472A (en) | A kind of searching method and device, a kind of device for searching for | |
US20220155940A1 (en) | Dynamic collection-based content presentation | |
CN104778600A (en) | Incentive mechanisms for user interaction and content consumption | |
WO2019178523A1 (en) | Method and device for generating object coordination information | |
Semerádová et al. | Website quality and shopping behavior: Quantitative and qualitative evidence | |
CN113973223B (en) | Data processing method, device, computer equipment and storage medium | |
CN107291772A (en) | One kind search access method, device and electronic equipment | |
CN112667120A (en) | Display method and device of interactive icon and electronic equipment | |
CN107515869A (en) | A kind of searching method and device, a kind of device for being used to search for | |
JP7326296B2 (en) | Adaptive search using social graph information | |
JP5805134B2 (en) | Terminal device and device program | |
CN107609146A (en) | Information displaying method, device, terminal and server | |
CN107786894A (en) | A kind of recognition methods of user feedback data, mobile terminal and storage medium | |
CN109426342A (en) | Document reading method and device based on augmented reality |
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: 20161005 |
|
RJ01 | Rejection of invention patent application after publication |