CN109241417A - User's awakening method and device calculate equipment and storage medium - Google Patents
User's awakening method and device calculate equipment and storage medium Download PDFInfo
- Publication number
- CN109241417A CN109241417A CN201810960826.0A CN201810960826A CN109241417A CN 109241417 A CN109241417 A CN 109241417A CN 201810960826 A CN201810960826 A CN 201810960826A CN 109241417 A CN109241417 A CN 109241417A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- interest
- label
- content
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to user's awakening method and device, calculating equipment and storage medium.User's awakening method includes: the user to be waken up for application, analyzes behavior of the user in the application to obtain the interest tags of the user;And the wake-up content for being pushed to the user to be waken up is determined according to the interest tags of the user.It additionally provides user's Rouser, calculate equipment and storage medium.Each embodiment through the invention can obtain the interest tags of user to be waken up according to the mass data of user's history behavior, and the wake-up content for meeting its point of interest according to the push of the interest tags of user to be waken up improves wake-up success rate to user.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of user's awakening method and device, calculate equipment and
Storage medium.
Background technique
Own services are supplied to user's use by many service providers by way of client application at present.User exists
After client application is installed on the terminal devices such as computer, mobile phone, it can be mentioned by the interface that client application provides using manufacturer
The various service products abundant supplied.But for a user, after using some period of time in service, continuation may be lost
The interest used, does not just use client application gradually.These users for not using client application for a long time are commonly referred to as
For silent user.
If user's silencing always, is bound to cause the loss of user, this is that service provider is reluctant to see, therefore,
It is necessary for carrying out wake operation to silent user.
It but is to be used all silencings by unified manner to the wake-up mode of silent user in the prior art
Family is waken up, for example, client application pushes the same preferential activity to all silent users, in this way to silencing
The wake-up effect of user is very poor.
Summary of the invention
One or more of in order to solve the above problem, the embodiment of the invention provides a kind of user's awakening methods and dress
It sets, calculate equipment and storage medium.
According to the disclosure in a first aspect, providing a kind of user's awakening method comprising:
For the user to be waken up of application, behavior of the user in the application is analyzed to obtain the user's
Interest tags;And
The wake-up content for being pushed to the user to be waken up is determined according to the interest tags of the user.
According to an exemplary embodiment, behavior of the analysis user in the application is to obtain the user's
Interest tags include:
Obtain behavior number of the user in the predetermined amount of time before enlivening behavior for the last time in the application
According to;
It is that every behavioral data distributes behavior object tag and behavior kind according to the type of the type of object of action and behavior
Class label, wherein the object of action label and the behavior type label are from scheduled object of action tag set and row
It is chosen for type tag set;
Behavior for object of action label having the same and behavior type label, count the behavior Frequency and
Time of origin;
For each object of action label distributed, behavior type label, the row of the behavioral data according to belonging to it
For Frequency and time of origin in one or more calculate its interest score;And
Select the highest object of action label of interest score or selection emerging from the object of action label distributed
Interest tags of the interesting higher multiple object of action labels of score as the user.
According to an exemplary embodiment, it is described according to the interest tags of the user determine for be pushed to the user with
The wake-up content waken up includes:
The attribute tags of each content in properties collection are obtained to be compared with the interest tags of the user;
Determine that attribute tags match with the interest tags from the properties collection according to scheduled matching rule
Content;And
Select one or more as the wake-up content from the content to match.
It is described to select one or more as the wake-up content from the content to match according to an exemplary embodiment
Including at least one of following:
Select the highest content of history wake-up rate or selection history wake-up rate higher from the content to match
Multiple contents are as the wake-up content;
Select the highest content of welcome rate or the welcome rate of selection higher multiple from the content to match
Content is as the wake-up content;
The highest content of weighted sum or choosing of history wake-up rate and welcome rate are selected from the content to match
The higher multiple contents of weighted sum of history wake-up rate and welcome rate are selected as the wake-up content.
According to an exemplary embodiment, each object of action label for being distributed, the row according to belonging to it
Its interest score is calculated for the behavior type label of data, the Frequency of behavior and time of origin, comprising:
For each object of action label, respectively according to behavior type label, the Frequency and time of origin meter of behavior
Calculate three initial interest scores for obtaining behavior object tag;
Described three initial interest scores multiplied by respective weighted value and are summed, using resulting result as the behavior pair
As the weighted sum interest score of label;And
Using highest weighted sum interest score in the obtained weighted sum interest score of the object of action label as this
The interest score of object of action label.
According to an exemplary embodiment, each object of action label for being distributed, the row according to belonging to it
Its interest score is calculated for the behavior type label of data, the Frequency of behavior and time of origin, comprising:
In the case where the behavior type label is the first behavior type label, the object of action label highest is assigned
Interest score.
According to an exemplary embodiment, user's awakening method further include:
There is the object of action label greater than predetermined number that there is highest interest to obtain in the object of action label of the user
In the case where point:
According to the time of origin of behavior by assigning the object of action mark for being greater than predetermined number again newly to old sequence
The first interest score of label from high to low;Or
According to the Frequency sequence from high to low of behavior, the object of action mark for being greater than predetermined number is assigned again
The second interest score of label from high to low;Or
For each object of action label in the object of action label greater than predetermined number, calculates the first interest and obtain
Divide and the weighted sum of the second interest score is as its final interest score.
According to the second aspect of the disclosure, a kind of user's Rouser is provided comprising:
Interest tags determining module, is configured for: for the user to be waken up of application, analyzing the user in institute
It states using upper behavior to obtain the interest tags of the user;And
Content determination module is waken up, is configured for: being determined according to the interest tags of the user for being pushed to
The wake-up content that user is stated to be waken up.
According to an exemplary embodiment, the interest tags determining module further comprises:
Behavioral data obtains module, is configured for: it is pre- before enlivening behavior for the last time to obtain the user
Behavioral data in section of fixing time in the application;
Label distribution module, is configured for: being every behavior number according to the type of the type of object of action and behavior
According to distribution behavior object tag and behavior type label, wherein the object of action label and the behavior type label be from
What scheduled object of action tag set and behavior type tag set were chosen;
Statistical module is configured for: the behavior for object of action label having the same and behavior type label,
Count the Frequency and time of origin of the behavior;
Interest score computing module, is configured for: for each object of action label distributed, according to belonging to it
In the behavior type label of behavioral data, the one or more in the Frequency and time of origin of behavior calculates its interest and obtains
Point;And
Interest tags determining module, is configured for: selecting interest score most from the object of action label distributed
A high object of action label selects interest of the higher multiple object of action labels of interest score as the user
Label.
According to an exemplary embodiment, the wake-up content determination module further comprises:
Attribute tags obtain module, be configured for: obtain properties collection in each content attribute tags with institute
The interest tags for stating user are compared;
Matching module is configured for: attribute mark is determined from the properties collection according to scheduled matching rule
The content that label match with the interest tags;And
Selecting module is configured for: selecting one or more as the wake-up content from the content to match.
According to the third aspect of the disclosure, a kind of calculating equipment, including memory and processor are provided, in the memory
It is stored with computer-readable instruction, the computer-readable instruction by the processor when being executed, so that the processor is held
Any of row embodiment of the method as described above.
According to the fourth aspect of the disclosure, a kind of storage medium is provided, is stored thereon with computer program, the computer
Program realizes any of embodiment of the method as described above when being executed by one or more processors.
The technical scheme provided by this disclosed embodiment can include the following benefits:
By the disclosure each embodiment as described above and as described below, the point of interest of user to be waken up can be directed to
(interest tags) determine the wake-up content for being pushed to user to be waken up, and are the interest for user due to waking up content
What point was determined, there is more accurate specific aim, therefore waking up success rate can be higher.In addition, in some embodiments, for behavior
The Frequency and time of origin of the combination statistics behavior of the object of action label and behavior type label of data, and according to behavior
Type label, Frequency and time of origin calculate the interest score of object of action label, use to be determined according to interest score
The interest tags at family can more accurately determine out the interest tags of user.In addition, in some embodiments, by attribute tags
The content to match with the interest tags of user is arranged according to the weighted sum of history wake-up rate, welcome rate or both of which
Sequence, so that the content that selected and sorted highest or higher one or more match can be further improved as content is waken up
Wake-up rate.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of user's awakening method shown according to an exemplary embodiment.
Fig. 2 is the exemplary specific reality of one kind according to step S110 in user's awakening method shown in Fig. 1 corresponding embodiment
The schematic flow diagram of existing mode.
Fig. 3 is the exemplary specific reality of one kind of step S240 in user's awakening method shown in corresponding embodiment according to fig. 2
The schematic flow diagram of existing mode.
Fig. 4 is that the another kind of step S240 in user's awakening method shown in corresponding embodiment according to fig. 2 is exemplary specific
The schematic flow diagram of implementation.
Fig. 5 is the exemplary specific reality of one kind according to step S120 in user's awakening method shown in Fig. 1 corresponding embodiment
The schematic flow diagram of existing mode.
Fig. 6 is the signal composition block diagram of user's Rouser 601 shown according to an exemplary embodiment.
Fig. 7 is the signal group according to interest tags determining module 610 in user's Rouser shown in Fig. 6 corresponding embodiment
At block diagram.
Fig. 8 is according to the signal group for waking up content determination module 620 in user's Rouser shown in Fig. 6 corresponding embodiment
At block diagram.
Fig. 9 is the signal composition block diagram shown according to an exemplary embodiment for calculating equipment 901.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
Exemplary embodiment of the present invention is further elaborated.In the following description when referring to the accompanying drawings, unless otherwise indicated, it is different
Same numbers in attached drawing indicate the same or similar element.The not generation of embodiment described in following exemplary embodiment
The table all embodiments consistent with the application.On the contrary, they are only and as detailed in the attached claim, this Shen
The example of the consistent device and method of some aspects please.It should be appreciated that specific embodiment described herein is used only for
It explains the present invention, is not intended to limit the present invention.
Fig. 1 is the flow diagram of user's awakening method shown according to an exemplary embodiment.As shown in Figure 1, this shows
Example user's awakening method comprising steps of
S110 analyzes user in the upper behavior of application to obtain the interest mark of user for the user to be waken up of application
Label.
So-called " user to be waken up of application ", which refers to, is applying the upper user for not enlivening behavior in predetermined period.
In order to determine user to be waken up, example user awakening method may include step: counting user is not enlivening row using upper
For time, user application the upper time for not enlivening behavior be more than predetermined period in the case where, which is considered as
User to be waken up." enlivening behavior " can refer to the behavior or the behavior for generating behavioral data that user is logged on this is applied
Deng.The predetermined period is properly termed as " customer churn period ", and expression is time that user does not enliven behavior, such as can be with
It is 80 days by customer churn period definition, meets and be lost user subject to the user in customer churn period, need to wake up, therefore
Referred to as " user to be waken up ".
Different from uniformly pushing methods same or with some project activities to needing to be waken up user in the prior art,
The example user awakening method is directed to the characteristic of each user, such as the interest tags of user, is customized wake-up to user, with
Improve wake-up rate.Therefore, in step s 110, the interest tags of user are being obtained using upper behavior by analysis user,
S120 is entered step later.
S120 determines the wake-up content for being pushed to the user to be waken up according to the interest tags of user.
Wake-up content for waking up user may have it is multiple, by determining with its point of interest according to the interest tags of user
It is the customized wake-up content that the content being consistent, which is used as, can more accurately cater to the demand of the user, greatly improve
Wake-up rate.
The tool of " analysis user is in the upper behavior of application to obtain the interest tags of user " described in step S110
Body is realized, gives an example in Fig. 2.As shown in Fig. 2, the step S110 of Fig. 1 may include step:
S210 obtains user and is applying upper behavioral data in the predetermined amount of time before enlivening behavior for the last time.
Generally, the historical behavior data that user is directed to the application are stored in the database of application.In order to analyze
The interest tags of user obtain predetermined amount of time of the user before enlivening behavior for the last time from database in this example
Apply upper behavioral data in inherence.Last time, which enlivens behavior, can be, for example, last time logs in the application, last time
This using upper generation behavioral data etc..Predetermined amount of time can be any duration, as long as the user behavior number in the duration
According to data volume enough determining its interest tags, such as the predetermined amount of time is 6 months.
S220, according to the type of the type of object of action and behavior, be every behavioral data distribute behavior object tag and
Behavior type label, wherein the object of action label and the behavior type label are from scheduled object of action tally set
It closes and the selection of behavior type tag set.
One behavior generally may include two attributes, i.e. object of action and behavior type (being what a kind of behavior),
Determine that the point of interest of user refers to that determining user is interested in which or which object of action.For the ease of the behavior number to user
It can be the object and behavior type preset label set of behavioral data generally according to being excavated and being recycled.For example, row
It may include insurance, financing, life, health etc. for object tag set, indicate the object of action of user for insurance, financing, life
Commodity, activity or advertisement of the classifications such as work, health etc..For example, behavior type tag set may include purchase, participate in, click,
Browsing etc. indicates that user performs such behavior for object of action.It can be its distribution point for each behavioral data
Not Xuan Zi scheduled object of action tag set and behavior type tag set object of action label and behavior type label.Example
Such as, it is documented in the behavioral data that some time user has purchased accident insurance for one, behavior object tag can be distributed it
" insurance " and behavior type label " purchase ";The behavior number of household electrical appliance commodity has been browsed for being documented in some time user
According to behavior object tag " life " and behavior type label " browsing " can be distributed it.
S230, the behavior for object of action label having the same and behavior type label, counts the generation of the behavior
Frequency and time of origin.
It, can be according to the group of object of action label and behavior type label after being assigned with label for every behavioral data
It closes, counts the Frequency and time of origin with the behavior of such tag combination.Wherein, Frequency can refer in institute
The number that the behavior occurs in total in the behavioral data of acquisition can also refer in unit time (such as one day, a week, one
Month) in occur number.Wherein, the newest time of origin of the behavior of same tag combination is defined as the tag combination behavior
Time of origin.By counting, the table of available form for example as follows:
Table 1: behavioral data statistical form
S240, for each object of action label distributed, the behavior kind category of the behavioral data according to belonging to it
It signs, the one or more in the Frequency and time of origin of behavior calculates its interest score.
The interest score of each object of action label and corresponding behavior type label, the Frequency of behavior and generation
Time is related.In one example, the interest score of each class behavior is purchase, and > participation > clicks > browsing, the Frequency of behavior
Higher interest score is higher, and time of origin is closer, and interest score is higher.It can be according to behavior type label, the Frequency of behavior
The interest score of object of action label is calculated with one or more of time of origin.On how to calculate interest score its
His specific example, refers to the explanation with reference to Fig. 3-4.
S250 selects the highest object of action label of interest score or choosing from the object of action label distributed
Select interest tags of the higher multiple object of action labels of interest score as the user.
Interest score is higher to show that user is interested in behavior object tag, then can determine it as the emerging of user
Interesting label.It can be that each user determines one or more interest tags according to interest score.
Fig. 3 is the exemplary specific reality of one kind of step S240 in user's awakening method shown in corresponding embodiment according to fig. 2
The schematic flow diagram of existing mode.As shown in figure 3, step S240 may include step:
S310, for each object of action label, respectively according to behavior type label, the Frequency of behavior and generation when
Between three initial interest scores of behavior object tag are calculated.
The full marks of interest score can be set to 100 points, when for different behavior type labels, Frequency and occurring
Between assign object of action label different interest score.As set forth above, it is possible to predetermined, the interest score of each class behavior be purchase >
> browsing is participated in > clicks, the Frequency of behavior is higher, and interest score is higher, and time of origin is closer, and interest score is higher.
According to example shown in table 1, obtained by the available initial interest as shown in Table 2 below of the processing of step S310
Point.
S320 multiplied by respective weighted value and sums three initial interest scores, using resulting result as the behavior
The weighted sum interest score of object tag.
Weighted value corresponding to three behavior type label, the Frequency of behavior and time of origin dimensions can be according to conjunction
The statistical result of supposition and/or wake-up rate is managed to determine.For example, in the example shown in table 2, behavior type label is corresponding
The weighted value of initial interest score is set as 60%, sets the weighted value of the corresponding initial interest score of Frequency to
20%, 20% will be set by the weighted value of the corresponding initial interest score of time of origin.
Table 2: initial interest score and weighted sum interest score calculated result
S330 makees weighted sum interest score highest in the obtained weighted sum interest score of the object of action label
For the interest score of behavior object tag.
The number of each available weighted sum interest score of object of action label (including the interest score for 0) is equal to
Its number combined with composed by behavior type label.As shown in the example of table 2, each object of action label obtains four
Weighted sum interest score chooses a highest interest score final as its, as shown in Table 3 below:
Table 3: final interest score result
As can be seen from Table 3, the interest score of four object of action labels is arranged according to sequence from high to low are as follows: financing
> insurance > life > health.In one example, interest tags of the interest score highest " financing " as user be can choose,
Also the interest tags of higher the first two of interest score " financing " and " insurance " as user be can choose.
Fig. 4 is that the another kind of step S240 in user's awakening method shown in corresponding embodiment according to fig. 2 is exemplary specific
The schematic flow diagram of implementation.As shown in figure 4, step S240 may include step:
It is happiest to assign object of action label in the case where behavior type label is the first behavior type label by S410
Interesting score.
As long as that is, occurring the case where object of action label and the first behavior type tag combination in behavioral data, to this
Object of action label assigns highest interest score (such as full marks 100 divide), but regardless of its Frequency and time of origin how.
First behavior type label, which can be in behavior type tag set, can accurately reflect user interest point
One or more behavior type labels.For example, can estimate user if user has purchased certain product and agree to such product
Surely there is larger interest.Therefore, behavior type label " purchase " can be regard as the first behavior type, as long as user has purchased certain
Object of action just assigns highest interest score to its object of action label.For example, user, which has purchased, " to be protected in the example of table 1
Danger " and " financing " two class product then can assign highest interest score 100 to object of action label " insurance " and " financing "
Point.
In one example, if finding that there is only one object of action label highest interest to obtain according to the above method
Point, then behavior object tag can be determined as to the interest tags of user.In another example, if sent out according to the above method
The object of action label for being now only less than predetermined number (predetermined number for example can be the number between 2-10) has highest interest
Score can will then be determined as the interest tags of user some or all of in these object of action labels.In another example,
If being greater than the object of action mark of predetermined number (predetermined number for example can be the number between 2-10) according to above method discovery
Label have highest interest score, then are further processed in the step s 420.
S420 has greater than the object of action label of predetermined number in the object of action label of the user with happiest
In the case where interesting score (for example, in the example shown in table 1, according to S410, two object of action labels " insurance " and " financing "
All have highest interest score 100 to divide, it is assumed that predetermined number herein is 1, then needs to be further processed), it executes as follows
(1)-(3) any one of item:
(1) according to the time of origin of behavior by assigning the behavior pair for being greater than predetermined number again newly to old sequence
As the first interest score of label from high to low.
It is exemplified by Table 1, object of action label " insurance " and " financing " and the combination of the first behavior type label " purchase "
Behavioral data is the first row and the second row data in table 1, wherein the corresponding time of origin of object of action label " insurance " is
" on March 2nd, 2018 ", the corresponding time of origin of object of action label " financing " are " on April 14th, 2018 ".According to respective hair
The morning and evening of raw time assigns the first interest score to object of action label " insurance " and " financing " again, for example, by object of action
First interest score S of label " insurance "I180 points are set as, by the first interest score S of object of action label " financing "F1If
It is set to 90 points.
It in one example, can be using the first interest score as the final interest score of object of action label.Due to inciting somebody to action
First behavior type label is set to correspond to the initial interest score of highest, hence, it can be determined that with other behavior type labels
The obtained final interest score of the object of action label being combined is less than all first interest scores.It therefore, can be true
Surely having those of the first interest score object of action label is that final interest score is higher in all object of action labels of user
Those of.In one example, final interest can be selected to obtain from having in those of the first interest score object of action label
Divide the interest tags of highest or higher one or more object of action labels as user.
(2) sequence according to the Frequency of behavior from high to low assigns the behavior pair for being greater than predetermined number again
As the second interest score of label from high to low.
It is exemplified by Table 1, object of action label " insurance " and " financing " and the combination of the first behavior type label " purchase "
Behavioral data is the first row and the second row data in table 1, wherein the corresponding Frequency of object of action label " insurance " is
" 2 ", the corresponding Frequency of object of action label " financing " are " 1 ".According to the size of respective Frequency to object of action
Label " insurance " and " financing " assign the second interest score again, for example, the second interest of object of action label " insurance " is obtained
Divide SI290 points are set as, by the second interest score S of object of action label " financing "F2It is set as 80 points.
It in one example, can be using the second interest score as the final interest score of object of action label.Due to inciting somebody to action
First behavior type label is set to correspond to the initial interest score of highest, hence, it can be determined that with other behavior type labels
The obtained final interest score of the object of action label being combined is less than all second interest scores.It therefore, can be true
Surely having those of the second interest score object of action label is that final interest score is higher in all object of action labels of user
Those of.In one example, final interest can be selected to obtain from having in those of the second interest score object of action label
Divide the interest tags of highest or higher one or more object of action labels as user.
(3) for each object of action label in the object of action label greater than predetermined number, it is emerging to calculate first
Interesting score and the weighted sum of the second interest score are as its final interest score.
It is alternatively possible to calculate the weighted sum of the first interest score and the second interest score as final interest score.The
The respective weighted value of one interest score and the second interest score can be according to the wake-up rate of reasonable expectation and/or statistics come really
It is fixed, for example, if thinking that the time of origin the new more can reflect the point of interest of user and the size of Frequency is important not as good as the former,
The weighted value of first interest score can be then set greater than to the weighted value of the second interest score.For example, can be emerging by first
The weighted value of interesting score and the second interest score is respectively set to 70% and 30%.By taking the example of table 1 as an example, then object of action mark
Sign the final interest score of " insurance " are as follows: SI=SI1* 70%+SI2* 30%=83, the final interest of object of action label " financing "
Score are as follows: SF=SF1* 70%+SF2* 30%=87.As can be seen that the final interest score of object of action label " financing " is greater than
The final interest score of object of action label " insurance ".
By the embodiment of Fig. 2-4, the point of interest of user can be more accurately determined, so that more accurately matching wakes up
Content.
Fig. 5 is the exemplary specific reality of one kind according to step S120 in user's awakening method shown in Fig. 1 corresponding embodiment
The schematic flow diagram of existing mode.As shown in figure 5, step S120 may include step:
S510 obtains the attribute tags of each content in properties collection to be compared with the interest tags of the user.
So-called " content ", which refers to, can be pushed to user to wake up user (that is, user is made above to regenerate work in application
Jump behavior) project, for example, commodity advertisement and/or purchase link, preferential activity, activity, etc. with lottery.In properties collection
Including one or more contents, each content has the attribute tags of the attribute or keyword that identify the content, and attribute tags can
To include the label of the targeted object of mark content, such as " insurance ", " financing ", " life ", " health ", or " fund ", " meaning
Outer danger ", " household electrical appliances " etc. also may include indicating the label of other attributes of content, such as " with lottery ", " preferential ", " return existing ", etc.
Deng.The properties collection data that the attribute tags including each content can be obtained from database, then by attribute tags and user
Interest tags compare.
S520 determines attribute tags and the interest tags phase according to scheduled matching rule from the properties collection
Matched content.
Comparing attribute tags is to see whether the two matches with the purpose of interest tags, if the two meets scheduled matching rule
Then, then it is judged as matching, is otherwise judged as mismatch.Scheduled matching rule may include one in following (1)-(3) or
It is multiple:
(1) if attribute tags are identical with interest tags, it is judged as matching.
For example, if in the interest tags of user including " insurance ", and in the attribute tags of content also include " insurance ", then
It is judged as the two matching.
(2) if attribute tags and interest tags belong to the same or similar classification, it is judged as matching.
For example, if in the interest tags of user including " insurance ", and in the attribute tags of content include " accident insurance ", sentence
Disconnected " accident insurance " belongs to " insurance " classification, then is judged as the two matching.
(3) if being phase in list of matches by searching for preset list of matches discovery attribute tags and interest tags
The item matched then is judged as the two matching.
Preset list of matches can be rule of thumb, history match result and/or reasoning and sort out and come and protect in advance
The list deposited, wherein having listed which attribute tags matches with which interest tags.
S530 selects one or more as the wake-up content from the content to match.
The possible more than one of the content that the interest tags of attribute tags and user match, can therefrom select one or more
It is a to be pushed to user.In one example, the highest content of history wake-up rate or choosing are selected from the content to match
The higher multiple contents of history wake-up rate are selected as wake-up content.In another example, it selects from the content to match by joyous
It meets the highest content of rate or selects the higher multiple contents of welcome rate as wake-up content.In another example, from
The highest content of weighted sum or selection history that history wake-up rate and welcome rate are selected in the content to match wake up
The higher multiple contents of the weighted sum of rate and welcome rate are as wake-up content.
It has been determined for the user wait wake up after waking up content, has needed to wake up content push to user to be waken up.One
In a example, the contact method (such as mobile phone, mailbox etc.) registered when using by obtaining user's registration passes through the connection
Mode is pushed to user, such as is pushed by sending mail, short message, wechat etc. automatically.In another example, it is used using acquisition
The phone contact mode at family, and will include the subscriber data of the phone contact mode and the wake-up content of determination be sent to it is selected
Rush business personnel living, issue push task to business personnel living is promoted, then promote business personnel living by the phone contact mode and give the use
Family makes a phone call to push identified wake-up content, informs that user logs in application and understands, buys or participate in.Promote industry living in selection
When business person, it can choose to waking up most familiar of rushs of content business personnel living (for example, wake-up content is preferential campaign item, and institute
The rush business personnel living of choosing is the promoter of the project), highest rushs of wake-up rate business personnel living or most popular rush live business personnel,
Etc..
The above are each embodiments of user's awakening method to additionally provide Installation practice according to another aspect of the present disclosure.
Fig. 6 shows the signal composition block diagram of user's Rouser 601 according to an exemplary embodiment.User's Rouser 601 is used
In each embodiment for executing user's awakening method as described above, wherein the application is operated on user's Rouser 601.Such as figure
Shown in 6 example, user's Rouser 601 may include interest tags determining module 610 and wake-up content determination module
620, in which:
Interest tags determining module 610 is configured for: for the user to be waken up of application, it is upper in application to analyze user
Behavior to obtain the interest tags of user;And
It wakes up content determination module 620 to be configured for: be determined according to the interest tags of user for being pushed to the user
With the wake-up content waken up.
Fig. 7 shows the signal composition block diagram of interest tags determining module 610 in user's Rouser of Fig. 6 embodiment.
As shown in fig. 7, interest tags determining module 610 may further include:
Behavioral data obtains module 710, is configured for: it is predetermined before enlivening behavior for the last time to obtain user
Upper behavioral data is being applied in period;
Label distribution module 720, is configured for: being every row according to the type of the type of object of action and behavior
Behavior object tag and behavior type label are distributed for data, wherein the object of action label and the behavior type label
It is to be chosen from scheduled object of action tag set and behavior type tag set;
Statistical module 730, is configured for: for the row of object of action label having the same and behavior type label
To count the Frequency and time of origin of the behavior;
Interest score computing module 740, is configured for: for each object of action label distributed, according to it
It is emerging that one or more in the behavior type label of belonging behavioral data, the Frequency and time of origin of behavior calculates its
Interesting score;And
Interest tags determining module 750, is configured for: selecting interest score from the object of action label distributed
A highest object of action label selects interest mark of the higher multiple object of action labels of interest score as user
Label.
Fig. 8 shows the signal composition block diagram that content determination module 620 is waken up in user's Rouser of Fig. 6 embodiment.
As shown in figure 8, waking up content determination module 620 may further include:
Attribute tags obtain module 810, be configured for: obtain properties collection in each content attribute tags with
The interest tags of the user are compared;
Matching module 820, is configured for: determining attribute from the properties collection according to scheduled matching rule
The content that label and the interest tags match;And
Selecting module 830, is configured for: one or more as in the wake-up from selecting in the content to match
Hold.
Each unit/module function and the realization process and correlative detail of effect are specifically detailed in above-mentioned in above-mentioned apparatus
The realization process of step is corresponded in user's awakening method, details are not described herein.
User's Rouser in the above various embodiments can be by way of hardware, software, firmware or combinations thereof come real
It is existing, and which can be implemented as an individual device, also may be implemented as each composition units/modules be dispersed in one or
The logic integrated system of corresponding function is executed in multiple calculating equipment and respectively.
Each unit/module of user's Rouser is formed in the above various embodiments to be divided according to logic function, it
Can be repartitioned according to logic function, such as can realize data processing by more or fewer units/modules
User's Rouser.These component units/modules can realize by way of hardware, software, firmware or combinations thereof respectively,
They can be the individual components of difference, be also possible to multiple components and combine execute the integrated list of corresponding logic function
Member/module.The mode of the hardware, software, firmware or combinations thereof may include: the hardware component of separation, pass through programming mode
The functional module of realization, the functional module realized by programmable logic device, etc., or with the combination of upper type.
According to an exemplary embodiment, user's Rouser can be implemented as a kind of calculating equipment, the calculating equipment packet
Memory and processor are included, computer program is stored in the memory, the computer program is held by the processor
When row, so that the processor executes any of each embodiment of user's awakening method as described above, that is, the computer
Program makes the calculating equipment realize the group of each embodiment of user's Rouser as described above when being executed by the processor
The function of being realized at units/modules.The calculating equipment can be server or terminal device.Wherein, the application deployment/fortune
On the computing device, the service that user can directly use the application to provide by the calculating equipment can also pass through peace to row
Client end AP P equipped with the application and the terminal device communicated with the calculating equipment by network (for example, mobile phone, computer,
Tablet computer etc.) service provided using the application is provided.
Processor described in above embodiment can refer to single processing unit, such as central processing unit CPU, can also
Be include multiple dispersions processing unit distributed processor system.
Memory described in above embodiment may include one or more memories, can be and calculates equipment
Internal storage, such as transient state or non-transient various memories, are also possible to be connected to calculating equipment by memory interface
External memory.
Fig. 9 shows the signal composition block diagram of such exemplary embodiment for calculating equipment 901.As shown in figure 9,
Calculating equipment 901 may include: processor 910, communication interface 920, memory 930 and bus 940.Storage in memory 930
There is the computer program that can be executed by processor 910.Processor 910 is realized in above-described embodiment when executing the computer program
User's awakening method and user's Rouser function.The quantity of memory 930 and processor 910 respectively can for one or
It is multiple.Communication interface 920 is for the communication between processor 910 and external equipment.
Wherein, processor 910 can be central processing unit, general processor, digital signal processor, dedicated integrated electricity
Road, field programmable gate array or other programmable logic device, transistor logic, hardware component or its any group
It closes.It, which may be implemented or executes, combines various illustrative process steps, functional unit/mould described in the disclosure of invention
Block and/or circuit.The processor is also possible to realize the combination of computing function, such as includes one or more microprocessors group
Conjunction, digital signal processor etc..
Memory 930 may include volatile memory and/or nonvolatile memory, such as non-volatile dynamic random
Access memory, phase change random access memory devices, magnetic random access memory, magnetic disk storage, Electrical Erasable can be compiled
Journey read-only memory, flush memory device, semiconductor devices (such as solid state hard disk) etc..Memory 930 optionally can also be external
Remote storage.
It is total that bus 940 can be industry standard architecture (ISA, Industry Standard Architecture)
Line, external equipment interconnection (PCI, Peripheral Component) bus or extended industry-standard architecture (EISA,
Extended Industry Standard Component) bus etc..It is total that the bus can be divided into address bus, data
Line, control bus etc..Only to be indicated with a thick line in Fig. 9, it is not intended that an only bus or a type convenient for indicating
The bus of type.Optionally, if memory 930, processor 910 and communication interface 920 are integrated on one chip, memory
930, processor 910 and communication interface 920 can complete mutual communication by internal interface.
The above each method and Installation practice are also implemented as the form of computer program, are stored in storage medium
On, and can be distributed.Therefore, according to another aspect of the present disclosure, a kind of storage medium is also provided, is stored thereon with for place
The computer program that device executes is managed, the computer program realizes each method as described above and device when being executed by processor
Any of embodiment.
The storage medium can be and any can keep and store and can be set by the tangible of the instruction that instruction execution equipment uses
It is standby.For example, it can be-- but be not limited to-- storage device electric, magnetic storage apparatus, light storage device, electromagnetism storage set
Standby, semiconductor memory apparatus or above-mentioned any appropriate combination.More specific example (the non exhaustive column of storage medium
Table) it include: that portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), static random access memory (SRAM), Portable compressed disk read-only memory (CD-
ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, the punch card for being for example stored thereon with instruction or
Groove internal projection structure and above-mentioned any appropriate combination.
Computer program/computer instruction as described herein can download to each meter from computer readable storage medium
Calculation/processing equipment, or outer computer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Or External memory equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger,
Gateway computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment connect from network
Computer-readable program instructions are received, and forward the computer-readable program instructions, for being stored in each calculating/processing equipment
Computer readable storage medium in.
Computer program instructions described in the disclosure can be assembly instruction, instruction set architecture (ISA) instructs, machine refers to
It enables, machine-dependent instructions, microcode, firmware instructions, condition setup data or with any group of one or more programming languages
The source code or object code write are compiled in collaboration with, the programming language includes programming language-such as Smalltalk, C+ of object-oriented
+ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer-readable program instructions
It can fully execute on the user computer, partly execute, held as an independent software package on the user computer
Part executes on the remote computer or holds on a remote computer or server completely on the user computer for row, part
Row.In situations involving remote computers, remote computer can include local area network (LAN) by the network-of any kind
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).In some embodiments, by the status information using computer-readable program instructions come
Personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or programmable logic array
(PLA), which can execute computer-readable program instructions, to realize various aspects of the invention.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or block diagram describes various aspects of the invention.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show the system of multiple embodiments according to the present invention, method and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.It is right
For those skilled in the art it is well known that, by hardware mode realize, by software mode realize and pass through software and
It is all of equal value that the mode of combination of hardware, which is realized,.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
But it will be clear for those skilled in the art that the various embodiments described above, which can according to need exclusive use or be combined with each other, to be made
With.In addition, for device embodiment, since it is corresponding with embodiment of the method, so describe fairly simple, it is related
Place referring to the corresponding part of embodiment of the method explanation.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of user's awakening method characterized by comprising
For the user to be waken up of application, behavior of the user in the application is analyzed to obtain the interest of the user
Label;And
The wake-up content for being pushed to the user to be waken up is determined according to the interest tags of the user.
2. user's awakening method as described in claim 1, which is characterized in that the analysis user is in the application
Behavior includes: with the interest tags for obtaining the user
Obtain behavioral data of the user in the predetermined amount of time before enlivening behavior for the last time in the application;
It is that every behavioral data distributes behavior object tag and behavior kind category according to the type of the type of object of action and behavior
Label, wherein the object of action label and the behavior type label are from scheduled object of action tag set and behavior kind
What class tag set was chosen;
Behavior for object of action label having the same and behavior type label counts Frequency and the generation of the behavior
Time;
For each object of action label distributed, the behavior type label of the behavioral data according to belonging to it, behavior
One or more in Frequency and time of origin calculates its interest score;And
The highest object of action label of interest score or selection interest is selected to obtain from the object of action label distributed
Divide interest tags of the higher multiple object of action labels as the user.
3. such as user's awakening method of any of claims 1-2, which is characterized in that described according to the emerging of the user
Interesting label is determined for being pushed to the user
The attribute tags of each content in properties collection are obtained to be compared with the interest tags of the user;
According to scheduled matching rule out of determined in the properties collection attribute tags and the interest tags match
Hold;And
Select one or more as the wake-up content from the content to match.
4. user's awakening method as claimed in claim 3, which is characterized in that it is described from the content to match select one or
It is multiple to be used as the wake-up content including at least one of following:
Select the highest content of history wake-up rate or selection history wake-up rate higher multiple from the content to match
Content is as the wake-up content;
The highest content of welcome rate or the welcome higher multiple contents of rate of selection are selected from the content to match
As the wake-up content;
The highest content of weighted sum or selection that history wake-up rate and welcome rate are selected from the content to match are gone through
The higher multiple contents of the weighted sum of history wake-up rate and welcome rate are as the wake-up content.
5. user's awakening method as claimed in claim 2, which is characterized in that each object of action mark for being distributed
Label, the behavior type label of the behavioral data according to belonging to it, the Frequency of behavior and time of origin calculate its interest and obtain
Point, comprising:
For each object of action label, calculated respectively according to behavior type label, the Frequency of behavior and time of origin
Three initial interest scores of behavior object tag out;
Described three initial interest scores multiplied by respective weighted value and are summed, using resulting result as behavior object mark
The weighted sum interest score of label;And
Using highest weighted sum interest score in the obtained weighted sum interest score of the object of action label as the behavior
The interest score of object tag.
6. user's awakening method as claimed in claim 2, which is characterized in that each object of action mark for being distributed
Label, the behavior type label of the behavioral data according to belonging to it, the Frequency of behavior and time of origin calculate its interest and obtain
Point, comprising:
In the case where the behavior type label is the first behavior type label, the object of action label highest interest is assigned
Score.
7. user's awakening method as claimed in claim 6, which is characterized in that further include:
There is the object of action label greater than predetermined number that there is highest interest score in the object of action label of the user
In the case of:
According to behavior time of origin by newly to old sequence, assign again the object of action label greater than predetermined number by
The first high to Low interest score;Or
According to the Frequency sequence from high to low of behavior, assign again the object of action label greater than predetermined number by
The second high to Low interest score;Or
For each object of action label in the object of action label greater than predetermined number, calculate the first interest score and
The weighted sum of second interest score is as its final interest score.
8. a kind of user's Rouser characterized by comprising
Interest tags determining module, is configured for: for the user to be waken up of application, analyzing the user and answers described
With behavior to obtain the interest tags of the user;And
Content determination module is waken up, is configured for: being determined according to the interest tags of the user for being pushed to the use
Wake-up content of the family to be waken up.
9. a kind of calculating equipment, including memory and processor, computer program, the computer are stored in the memory
Program by the processor when being executed, so that the processor executes the method as described in any one of claims 1 to 7.
10. a kind of storage medium, is stored thereon with computer program, the computer program is held by one or more processors
The method as described in any one of claims 1 to 7 is realized when row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810960826.0A CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810960826.0A CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109241417A true CN109241417A (en) | 2019-01-18 |
CN109241417B CN109241417B (en) | 2023-07-25 |
Family
ID=65068364
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810960826.0A Active CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109241417B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144935A (en) * | 2019-12-17 | 2020-05-12 | 武汉海云健康科技股份有限公司 | Big data-based sleep member awakening method and system, server and medium |
CN112950266A (en) * | 2021-02-26 | 2021-06-11 | 北京达佳互联信息技术有限公司 | Media resource display method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103378976A (en) * | 2012-04-19 | 2013-10-30 | 深圳市快播科技有限公司 | Method of waking up sound asleep user and system |
CN104933134A (en) * | 2015-06-12 | 2015-09-23 | 海信集团有限公司 | User feature analysis method and user feature analysis device |
CN105718184A (en) * | 2014-12-05 | 2016-06-29 | 北京搜狗科技发展有限公司 | Data processing method and apparatus |
CN106055617A (en) * | 2016-05-26 | 2016-10-26 | 乐视控股(北京)有限公司 | Data pushing method and device |
-
2018
- 2018-08-22 CN CN201810960826.0A patent/CN109241417B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103378976A (en) * | 2012-04-19 | 2013-10-30 | 深圳市快播科技有限公司 | Method of waking up sound asleep user and system |
CN105718184A (en) * | 2014-12-05 | 2016-06-29 | 北京搜狗科技发展有限公司 | Data processing method and apparatus |
CN104933134A (en) * | 2015-06-12 | 2015-09-23 | 海信集团有限公司 | User feature analysis method and user feature analysis device |
CN106055617A (en) * | 2016-05-26 | 2016-10-26 | 乐视控股(北京)有限公司 | Data pushing method and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144935A (en) * | 2019-12-17 | 2020-05-12 | 武汉海云健康科技股份有限公司 | Big data-based sleep member awakening method and system, server and medium |
CN112950266A (en) * | 2021-02-26 | 2021-06-11 | 北京达佳互联信息技术有限公司 | Media resource display method and device |
CN112950266B (en) * | 2021-02-26 | 2024-05-03 | 北京达佳互联信息技术有限公司 | Media resource display method and device |
Also Published As
Publication number | Publication date |
---|---|
CN109241417B (en) | 2023-07-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015055067A1 (en) | Method and apparatus for pushing messages | |
US8732015B1 (en) | Social media pricing engine | |
CN105893406A (en) | Group user profiling method and system | |
US10621616B2 (en) | Systems, methods, and devices for generating metrics associated with advertisement data objects | |
CN112017060B (en) | Method and device for allocating resources for target user and electronic equipment | |
CN104951544A (en) | User data processing method and system and method and system for providing user data | |
US20160350815A1 (en) | Representing entities relationships in online advertising | |
US20210082026A1 (en) | Content-recommendation method and apparatus, electronic device, and system | |
CN108777701A (en) | A kind of method and device of determining receiver | |
CN112686717B (en) | Data processing method and system for advertisement recall | |
US20160350800A1 (en) | Detecting coalition fraud in online advertising | |
CN111210255B (en) | Advertisement pushing method and device and electronic equipment | |
CN107992500A (en) | A kind of information processing method and server | |
CN113297287B (en) | Automatic user policy deployment method and device and electronic equipment | |
CN110796480A (en) | Real-time advertisement putting management method, device and system | |
CN104063799A (en) | Promotion message pushing method and device | |
CN112819528A (en) | Crowd pack online method and device and electronic equipment | |
CN108073672A (en) | Business object recommends method, apparatus and electronic equipment | |
CN108694174B (en) | Content delivery data analysis method and device | |
CN109241417A (en) | User's awakening method and device calculate equipment and storage medium | |
CN110428277B (en) | Touch method of recommended product, storage medium and program product | |
US20130179223A1 (en) | Method and arrangement for segmentation of telecommunication customers | |
CN108694609B (en) | Advertisement network alliance platform | |
CN111199454A (en) | Real-time user transformation evaluation method and device and electronic equipment | |
CN111612508A (en) | Financial resource allocation request processing method and device and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |