CN109756541A - Information-pushing method, device, server and computer readable storage medium - Google Patents
Information-pushing method, device, server and computer readable storage medium Download PDFInfo
- Publication number
- CN109756541A CN109756541A CN201711081581.6A CN201711081581A CN109756541A CN 109756541 A CN109756541 A CN 109756541A CN 201711081581 A CN201711081581 A CN 201711081581A CN 109756541 A CN109756541 A CN 109756541A
- Authority
- CN
- China
- Prior art keywords
- user
- sample
- algorithm model
- sorting algorithm
- operation message
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of information-pushing method, device, server and computer readable storage mediums, wherein information-pushing method includes: to be divided using sorting algorithm model to user's sample, with the multiple user's sample sets of determination；According to the mapping relations between user's sample set and operation message, operation message orientation is pushed to the client device of corresponding user's sample set.Technical solution of the present invention improves the accuracy and timeliness of push operation message, reduces artificial operation cost, improve the quality of operating service.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of information-pushing method, a kind of information push dress
It sets, a kind of server and a kind of computer readable storage medium.
Background technique
Operation management refers to plan, tissue, implementation and the control to operation process, is that close phase is created in production and service
The general name of every management work of pass.The range of modern operation management is expanded to nonmanufacturing industry from traditional manufacturing enterprise.
Its research contents has also been not limited to plan, tissue and the control of production process, but is expanded to the formulation of operations strategy, operation
The multi-level content such as system design and operation system operation.Operations strategy, new product development, product design, purchase and supply,
It manufactures, product delivery is until one complete " value chain " is regarded in after-sale service as, to its integrated management.
In the related technology, operation personnel is generally required in operation management to be disappeared according to the corresponding operation of migration efficiency push
Breath, it is also desirable to operation personnel determines the user group of push, not only low efficiency but also directionality is poor, in addition, can not be timely
Know whether the user group being pushed has response to operate operation message, and needs to put into a large amount of human cost to support to transport
Battalion's service.
Summary of the invention
The present invention is directed to solve at least one of the technical problems existing in the prior art or related technologies.
For this purpose, it is an object of the present invention to provide a kind of information-pushing methods.
It is another object of the present invention to provide a kind of devices of information push.
Yet another object of the invention is that providing a kind of server.
Yet another object of the invention is that providing a kind of computer readable storage medium.
To achieve the goals above, the technical solution of first aspect present invention provides a kind of information-pushing method, comprising:
User's sample is divided using sorting algorithm model, with the multiple user's sample sets of determination；According to user's sample set with
The mapping relations between message are runed, operation message orientation is pushed to the client device of corresponding user's sample set.
In the technical scheme, user's sample is divided by using sorting algorithm model, with the multiple users of determination
Sample set accurately and securely distinguishes different user sample, for orienting push, wherein orientation, which pushes, is
It is realized based on the mapping relations between user's sample set and operation message, it is to be understood that since mapping relations are roots
It is determined according to migration efficiency, therefore, not only increases the efficiency of operation push, and the operation message of push is made more to meet use
The use demand at family improves user to the Experience Degree of operating service while saving operating service cost of labor.
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: determining migration efficiency and the corresponding default sorting algorithm model of migration efficiency belonging to operation message；Construct seed specimen
Set and non-seed sample set；Default sorting algorithm model is instructed using seed specimen set and non-seed sample set
Practice, the default sorting algorithm model for completing training is determined as sorting algorithm model.
In the technical scheme, by using seed specimen set and non-seed sample set to default sorting algorithm model
It is trained, available more accurate sorting algorithm model, it is to be understood that determining the corresponding classification of migration efficiency
After algorithm model, classifying and dividing may be implemented after user's sample is inputted sorting algorithm model, obtain multiple user's sample sets,
Every kind of operation message orientation is pushed into corresponding user's sample set further according to mapping relations, operation is really effectively promoted
The accuracy and reliability of push.
For example, migration efficiency includes the strategy for pulling in new client and the strategy for keeping frequent customer here, then pulls in the plan of new client
Slightly corresponding operation message is promotion message, and the corresponding operation message of strategy for keeping frequent customer here is favor information, as cash certificate,
Coupons and completely subtract certificate etc..
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: the mapping relations between pre-set user sample set and operation message, wherein operation message includes application program operation message
And/or short message runs message.
In the technical scheme, by the mapping relations between pre-set user sample set and operation message, further
It ensure that the reliability of orientation push operation message to corresponding user's sample set.
Wherein, mapping relations can be the corresponding a kind of operation message of user's sample set, in order to promote operating service
Diversity, mapping relations are also possible to user's sample set and correspond to multiclass operation message or multiple user's sample sets
Close corresponding a kind of operation message.
In the above-mentioned technical solutions, it is preferable that further include: the specified label conduct of pre-set user sample can be classified calculation
The identification information of method model identification, wherein the specified label of user's sample includes age of user, user's income, user's occupation class
Not, at least one of user's education degree, customer consumption index, user's affiliated area and user activity label.
It in the technical scheme, is the mark that can be classified algorithm model identification by the specified label of pre-set user sample
Know information, sorting algorithm model need to only determine user's sample set belonging to user's sample according to label, use without parsing
The specific data content of family sample, wherein each user's sample may have multiple labels, according to migration efficiency setting wherein one
A or multiple labels are as specified label, to improve the efficiency for dividing user group.
Wherein, above-mentioned specified label can be soft label or hard label, and soft label is commonly used in elastic research,
Have high flexibility and operability, as data update, the corresponding relationship between soft label and user's sample may be sent out
It is raw to change, and hard label is the attribute tags that cannot be modified, the corresponding relationship between hard label and user's sample does not change.
In the above-mentioned technical solutions, it is preferable that further include: client device is received to the response record of operation message；Root
Sorting algorithm model is modified according to response record.
In the technical scheme, by receiving client device to the response record of operation message for correcting sorting algorithm
Model, namely message orientation push will runed after corresponding user's sample set according to migration efficiency, it needs to grab client
End equipment pushes effect to the response record of operation message with registration confirmed according to response, as response record is lower than expected sound
Index is answered, then needs extensive work to correct sorting algorithm model, or even need to re-start model training.
Wherein, response record includes that user checks the frequency, editor's frequency and feedback frequency etc..
In the above-mentioned technical solutions, it is preferable that further include: by user's sample set and corresponding operation message, user's sample
This specified label and the response record of operation message in the form of three-dimensional figure real-time display in user's interaction circle of operation client
Face；Mapping relations are shown in user interface, and according to predetermined period freshness map relationship, wherein user interface
It is preset with edition interface, edition interface is used to receive the edit operation to three-dimensional figure and/or mapping relations, and edit operation includes adding
Add operation, delete operation save at least one of operation and remarks operation operation.
In the technical scheme, by by user's sample set and it is corresponding operation message, user's sample specified label
With operation message response record in the form of three-dimensional figure real-time display in operation client user interface, and display reflect
Relationship is penetrated, friendly intuitive operation interface can be provided for operation personnel, in addition, setting edition interface is in order to operation personnel couple
Three-dimensional figure and/or mapping relations are modified, to improve manual maintenance efficiency, in addition, operation personnel can pass through user's interaction
The dynamic change of related data during objective interface monitoring push, stimulates consumption further to formulate new migration efficiency
Or promotional.
The technical solution of the second aspect of the present invention provides a kind of information push-delivery apparatus, comprising: division unit, for adopting
User's sample is divided with sorting algorithm model, with the multiple user's sample sets of determination；Push unit, for according to user
Operation message orientation is pushed to the client of corresponding user's sample set by the mapping relations between sample set and operation message
End equipment.
In the technical scheme, user's sample is divided by using sorting algorithm model, with the multiple users of determination
Sample set accurately and securely distinguishes different user sample, for orienting push, wherein orientation, which pushes, is
It is realized based on the mapping relations between user's sample set and operation message, it is to be understood that since mapping relations are roots
It is determined according to migration efficiency, therefore, not only increases the efficiency of operation push, and the operation message of push is made more to meet use
The use demand at family improves user to the Experience Degree of operating service while saving operating service cost of labor.
In the above-mentioned technical solutions, it is preferable that further include: determination unit, for determining operation plan belonging to operation message
Summary and the corresponding default sorting algorithm model of migration efficiency；Construction unit, for constructing seed specimen set and non-seed sample
This set；Training unit, for being instructed using seed specimen set and non-seed sample set to default sorting algorithm model
Practice, the default sorting algorithm model for completing training is determined as sorting algorithm model.
In the technical scheme, by using seed specimen set and non-seed sample set to default sorting algorithm model
It is trained, available more accurate sorting algorithm model, it is to be understood that determining the corresponding classification of migration efficiency
After algorithm model, classifying and dividing may be implemented after user's sample is inputted sorting algorithm model, obtain multiple user's sample sets,
Every kind of operation message orientation is pushed into corresponding user's sample set further according to mapping relations, operation is really effectively promoted
The accuracy and reliability of push.
For example, migration efficiency includes the strategy for pulling in new client and the strategy for keeping frequent customer here, then pulls in the plan of new client
Slightly corresponding operation message is promotion message, and the corresponding operation message of strategy for keeping frequent customer here is favor information, as cash certificate,
Coupons and completely subtract certificate etc..
In the above-mentioned technical solutions, it is preferable that further include: default unit disappears for pre-set user sample set with operation
Mapping relations between breath, wherein operation message includes application program operation message and/or short message operation message.
In the technical scheme, by the mapping relations between pre-set user sample set and operation message, further
It ensure that the reliability of orientation push operation message to corresponding user's sample set.
Wherein, mapping relations can be the corresponding a kind of operation message of user's sample set, in order to promote operating service
Diversity, mapping relations are also possible to user's sample set and correspond to multiclass operation message or multiple user's sample sets
Close corresponding a kind of operation message.
In the above-mentioned technical solutions, it is preferable that default unit is also used to: the specified label of pre-set user sample is used as can
It is classified the identification information of algorithm model identification, wherein the specified label of user's sample includes age of user, user's income, uses
At least one of family occupational group, user's education degree, customer consumption index, user's affiliated area and user activity mark
Label.
It in the technical scheme, is the mark that can be classified algorithm model identification by the specified label of pre-set user sample
Know information, sorting algorithm model need to only determine user's sample set belonging to user's sample according to label, use without parsing
The specific data content of family sample, wherein each user's sample may have multiple labels, according to migration efficiency setting wherein one
A or multiple labels are as specified label, to improve the efficiency for dividing user group.
Wherein, above-mentioned specified label can be soft label or hard label, and soft label is commonly used in elastic research,
Have high flexibility and operability, as data update, the corresponding relationship between soft label and user's sample may be sent out
It is raw to change, and hard label is the attribute tags that cannot be modified, the corresponding relationship between hard label and user's sample does not change.
In the above-mentioned technical solutions, it is preferable that further include: receiving unit, for receiving client to the sound of operation message
It should record；Amending unit is modified sorting algorithm model for recording according to response.
In the technical scheme, by receiving client device to the response record of operation message for correcting sorting algorithm
Model, namely message orientation push will runed after corresponding user's sample set according to migration efficiency, it needs to grab client
End equipment pushes effect to the response record of operation message with registration confirmed according to response, as response record is lower than expected sound
Index is answered, then needs extensive work to correct sorting algorithm model, or even need to re-start model training.
Wherein, response record includes that user checks the frequency, editor's frequency and feedback frequency etc..
In the above-mentioned technical solutions, it is preferable that further include: display unit is used for user's sample set and corresponding fortune
Seek message, user's sample specified label and run message response record in the form of three-dimensional figure real-time display in operation client
User interface；Display unit is also used to: mapping relations being shown in user interface, and are refreshed according to predetermined period
Mapping relations, wherein user interface is preset with edition interface, and edition interface closes three-dimensional figure and/or mapping for receiving
The edit operation of system, edit operation include addition operation, delete operation, save at least one of operation and remarks operation behaviour
Make.
In the technical scheme, by by user's sample set and it is corresponding operation message, user's sample specified label
With operation message response record in the form of three-dimensional figure real-time display in operation client user interface, and display reflect
Relationship is penetrated, friendly intuitive operation interface can be provided for operation personnel, in addition, setting edition interface is in order to operation personnel couple
Three-dimensional figure and/or mapping relations are modified, to improve manual maintenance efficiency, in addition, operation personnel can pass through user's interaction
The dynamic change of related data during objective interface monitoring push, stimulates consumption further to formulate new migration efficiency
Or promotional.
The technical solution of the third aspect of the present invention provides a kind of server, comprising: memory, processor and is stored in
On memory and the computer program that can run on a processor, processor realize any of the above-described letter when executing computer program
Cease the step of method for pushing limits, and/or the information push-delivery apparatus including any of the above-described.
The technical solution of the fourth aspect of the present invention provides a kind of computer readable storage medium, is stored thereon with calculating
Machine program realizes the step of any of the above-described information-pushing method limits when computer program is executed by processor.
Advantages of the present invention will provide in following description section, partially will become apparent from the description below, or
Practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 shows the schematic flow diagram of the information-pushing method of embodiment according to the present invention；
Fig. 2 shows the schematic block diagrams of the information push-delivery apparatus of embodiment according to the present invention；
Fig. 3 shows the schematic block diagram of the server of embodiment according to the present invention；
Fig. 4 shows the schematic diagram of the operation push process of embodiment according to the present invention；
Fig. 5 shows the schematic diagram of the user interface of embodiment according to the present invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Fig. 1 shows the schematic flow diagram of information-pushing method according to an embodiment of the invention.
As shown in Figure 1, the communication means of the WLAN of embodiment according to the present invention, comprising: step S102 is used
Sorting algorithm model divides user's sample, with the multiple user's sample sets of determination；Step S104, according to user's sample set
The mapping relations between operation message are closed, the client that operation message orientation pushes to corresponding user's sample set is set
It is standby.
In the technical scheme, user's sample is divided by using sorting algorithm model, with the multiple users of determination
Sample set accurately and securely distinguishes different user sample, for orienting push, wherein orientation, which pushes, is
It is realized based on the mapping relations between user's sample set and operation message, it is to be understood that since mapping relations are roots
It is determined according to migration efficiency, therefore, not only increases the efficiency of operation push, and the operation message of push is made more to meet use
The use demand at family improves user to the Experience Degree of operating service while saving operating service cost of labor.
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: determining migration efficiency and the corresponding default sorting algorithm model of migration efficiency belonging to operation message；Construct seed specimen
Set and non-seed sample set；Default sorting algorithm model is instructed using seed specimen set and non-seed sample set
Practice, the default sorting algorithm model for completing training is determined as sorting algorithm model.
In the technical scheme, by using seed specimen set and non-seed sample set to default sorting algorithm model
It is trained, available more accurate sorting algorithm model, it is to be understood that determining the corresponding classification of migration efficiency
After algorithm model, classifying and dividing may be implemented after user's sample is inputted sorting algorithm model, obtain multiple user's sample sets,
Every kind of operation message orientation is pushed into corresponding user's sample set further according to mapping relations, operation is really effectively promoted
The accuracy and reliability of push.
For example, migration efficiency includes the strategy for pulling in new client and the strategy for keeping frequent customer here, then pulls in the plan of new client
Slightly corresponding operation message is promotion message, and the corresponding operation message of strategy for keeping frequent customer here is favor information, as cash certificate,
Coupons and completely subtract certificate etc..
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: the mapping relations between pre-set user sample set and operation message, wherein operation message includes application program operation message
And/or short message runs message.
In the technical scheme, by the mapping relations between pre-set user sample set and operation message, further
It ensure that the reliability of orientation push operation message to corresponding user's sample set.
Wherein, mapping relations can be the corresponding a kind of operation message of user's sample set, in order to promote operating service
Diversity, mapping relations are also possible to user's sample set and correspond to multiclass operation message or multiple user's sample sets
Close corresponding a kind of operation message.
In the above-mentioned technical solutions, it is preferable that further include: the specified label conduct of pre-set user sample can be classified calculation
The identification information of method model identification, wherein the specified label of user's sample includes age of user, user's income, user's occupation class
Not, at least one of user's education degree, customer consumption index, user's affiliated area and user activity label.
It in the technical scheme, is the mark that can be classified algorithm model identification by the specified label of pre-set user sample
Know information, sorting algorithm model need to only determine user's sample set belonging to user's sample according to label, use without parsing
The specific data content of family sample, wherein each user's sample may have multiple labels, according to migration efficiency setting wherein one
A or multiple labels are as specified label, to improve the efficiency for dividing user group.
Wherein, above-mentioned specified label can be soft label or hard label, and soft label is commonly used in elastic research,
Have high flexibility and operability, as data update, the corresponding relationship between soft label and user's sample may be sent out
It is raw to change, and hard label is the attribute tags that cannot be modified, the corresponding relationship between hard label and user's sample does not change.
In the above-mentioned technical solutions, it is preferable that further include: client device is received to the response record of operation message；Root
Sorting algorithm model is modified according to response record.
In the technical scheme, by receiving client device to the response record of operation message for correcting sorting algorithm
Model, namely message orientation push will runed after corresponding user's sample set according to migration efficiency, it needs to grab client
End equipment pushes effect to the response record of operation message with registration confirmed according to response, as response record is lower than expected sound
Index is answered, then needs extensive work to correct sorting algorithm model, or even need to re-start model training.
Wherein, response record includes that user checks the frequency, editor's frequency and feedback frequency etc..
In the above-mentioned technical solutions, it is preferable that further include: by user's sample set and corresponding operation message, user's sample
This specified label and the response record of operation message in the form of three-dimensional figure real-time display in user's interaction circle of operation client
Face；Mapping relations are shown in user interface, and according to predetermined period freshness map relationship, wherein user interface
It is preset with edition interface, edition interface is used to receive the edit operation to three-dimensional figure and/or mapping relations, and edit operation includes adding
Add operation, delete operation save at least one of operation and remarks operation operation.
In the technical scheme, by by user's sample set and it is corresponding operation message, user's sample specified label
With operation message response record in the form of three-dimensional figure real-time display in operation client user interface, and display reflect
Relationship is penetrated, friendly intuitive operation interface can be provided for operation personnel, in addition, setting edition interface is in order to operation personnel couple
Three-dimensional figure and/or mapping relations are modified, to improve manual maintenance efficiency, in addition, operation personnel can pass through user's interaction
The dynamic change of related data during objective interface monitoring push, stimulates consumption further to formulate new migration efficiency
Or promotional.
Fig. 2 shows the schematic block diagrams of the information push-delivery apparatus of embodiment according to the present invention.
As shown in Fig. 2, the information push-delivery apparatus 200 of embodiment according to the present invention, comprising: division unit 202, for adopting
User's sample is divided with sorting algorithm model, with the multiple user's sample sets of determination；Push unit 204 is used for basis
Operation message orientation is pushed to corresponding user's sample set by the mapping relations between user's sample set and operation message
Client device.
In the technical scheme, user's sample is divided by using sorting algorithm model, with the multiple users of determination
Sample set accurately and securely distinguishes different user sample, for orienting push, wherein orientation, which pushes, is
It is realized based on the mapping relations between user's sample set and operation message, it is to be understood that since mapping relations are roots
It is determined according to migration efficiency, therefore, not only increases the efficiency of operation push, and the operation message of push is made more to meet use
The use demand at family improves user to the Experience Degree of operating service while saving operating service cost of labor.
In the above-mentioned technical solutions, it is preferable that further include: determination unit 206, for determining operation belonging to operation message
Strategy and the corresponding default sorting algorithm model of migration efficiency；Construction unit 208, for constructing seed specimen set and non-
Seed specimen set；Training unit 210, for using seed specimen set and non-seed sample set to default sorting algorithm mould
Type is trained, and the default sorting algorithm model for completing training is determined as sorting algorithm model.
In the technical scheme, by using seed specimen set and non-seed sample set to default sorting algorithm model
It is trained, available more accurate sorting algorithm model, it is to be understood that determining the corresponding classification of migration efficiency
After algorithm model, classifying and dividing may be implemented after user's sample is inputted sorting algorithm model, obtain multiple user's sample sets,
Every kind of operation message orientation is pushed into corresponding user's sample set further according to mapping relations, operation is really effectively promoted
The accuracy and reliability of push.
For example, migration efficiency includes the strategy for pulling in new client and the strategy for keeping frequent customer here, then pulls in the plan of new client
Slightly corresponding operation message is promotion message, and the corresponding operation message of strategy for keeping frequent customer here is favor information, as cash certificate,
Coupons and completely subtract certificate etc..
In the above-mentioned technical solutions, it is preferable that further include: default unit 212, for pre-set user sample set and operation
Mapping relations between message, wherein operation message includes application program operation message and/or short message operation message.
In the technical scheme, by the mapping relations between pre-set user sample set and operation message, further
It ensure that the reliability of orientation push operation message to corresponding user's sample set.
Wherein, mapping relations can be the corresponding a kind of operation message of user's sample set, in order to promote operating service
Diversity, mapping relations are also possible to user's sample set and correspond to multiclass operation message or multiple user's sample sets
Close corresponding a kind of operation message.
In the above-mentioned technical solutions, it is preferable that default unit 212 is also used to: the specified label conduct of pre-set user sample
The identification information of algorithm model identification can be classified, wherein the specified label of user's sample includes age of user, Yong Hushou
Enter, at least one in user occupational group, user's education degree, customer consumption index, user's affiliated area and user activity
Kind label.
It in the technical scheme, is the mark that can be classified algorithm model identification by the specified label of pre-set user sample
Know information, sorting algorithm model need to only determine user's sample set belonging to user's sample according to label, use without parsing
The specific data content of family sample, wherein each user's sample may have multiple labels, according to migration efficiency setting wherein one
A or multiple labels are as specified label, to improve the efficiency for dividing user group.
Wherein, above-mentioned specified label can be soft label or hard label, and soft label is commonly used in elastic research,
Have high flexibility and operability, as data update, the corresponding relationship between soft label and user's sample may be sent out
It is raw to change, and hard label is the attribute tags that cannot be modified, the corresponding relationship between hard label and user's sample does not change.
In the above-mentioned technical solutions, it is preferable that further include: receiving unit 214, for receiving client to operation message
Response record；Amending unit 216 is modified sorting algorithm model for recording according to response.
In the technical scheme, by receiving client device to the response record of operation message for correcting sorting algorithm
Model, namely message orientation push will runed after corresponding user's sample set according to migration efficiency, it needs to grab client
End equipment pushes effect to the response record of operation message with registration confirmed according to response, as response record is lower than expected sound
Index is answered, then needs extensive work to correct sorting algorithm model, or even need to re-start model training.
Wherein, response record includes that user checks the frequency, editor's frequency and feedback frequency etc..
In the above-mentioned technical solutions, it is preferable that further include: display unit 218, for by user's sample set and corresponding
Run message, user's sample specified label and run message response record in the form of three-dimensional figure real-time display in operation client
The user interface at end；Display unit 218 is also used to: mapping relations being shown in user interface, and according to default week
Phase freshness map relationship, wherein user interface is preset with edition interface, edition interface for receiving to three-dimensional figure and/or
The edit operation of mapping relations, edit operation include at least one added in operation, delete operation, preservation operation and remarks operation
Kind operation.
In the technical scheme, by by user's sample set and it is corresponding operation message, user's sample specified label
With operation message response record in the form of three-dimensional figure real-time display in operation client user interface, and display reflect
Relationship is penetrated, friendly intuitive operation interface can be provided for operation personnel, in addition, setting edition interface is in order to operation personnel couple
Three-dimensional figure and/or mapping relations are modified, to improve manual maintenance efficiency, in addition, operation personnel can pass through user's interaction
The dynamic change of related data during objective interface monitoring push, stimulates consumption further to formulate new migration efficiency
Or promotional.
Fig. 3 shows the schematic block diagram of the server of embodiment according to the present invention.
As shown in figure 3, the server 300 of embodiment according to the present invention, comprising: memory 302, processor 304 and deposit
The computer program that can be run on memory 302 and on a processor is stored up, processor is realized above-mentioned when executing computer program
The step of any one information-pushing method limits, and/or the information push-delivery apparatus 200 including any of the above-described.
According to an embodiment of the invention, also proposed a kind of computer readable storage medium, it is stored thereon with computer journey
Sequence, realization when computer program is executed by processor: dividing user's sample using sorting algorithm model, multiple with determination
User's sample set；According to the mapping relations between user's sample set and operation message, operation message orientation is pushed to pair
The client device for the user's sample set answered.
In the technical scheme, user's sample is divided by using sorting algorithm model, with the multiple users of determination
Sample set accurately and securely distinguishes different user sample, for orienting push, wherein orientation, which pushes, is
It is realized based on the mapping relations between user's sample set and operation message, it is to be understood that since mapping relations are roots
It is determined according to migration efficiency, therefore, not only increases the efficiency of operation push, and the operation message of push is made more to meet use
The use demand at family improves user to the Experience Degree of operating service while saving operating service cost of labor.
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: determining migration efficiency and the corresponding default sorting algorithm model of migration efficiency belonging to operation message；Construct seed specimen
Set and non-seed sample set；Default sorting algorithm model is instructed using seed specimen set and non-seed sample set
Practice, the default sorting algorithm model for completing training is determined as sorting algorithm model.
In the technical scheme, by using seed specimen set and non-seed sample set to default sorting algorithm model
It is trained, available more accurate sorting algorithm model, it is to be understood that determining the corresponding classification of migration efficiency
After algorithm model, classifying and dividing may be implemented after user's sample is inputted sorting algorithm model, obtain multiple user's sample sets,
Every kind of operation message orientation is pushed into corresponding user's sample set further according to mapping relations, operation is really effectively promoted
The accuracy and reliability of push.
For example, migration efficiency includes the strategy for pulling in new client and the strategy for keeping frequent customer here, then pulls in the plan of new client
Slightly corresponding operation message is promotion message, and the corresponding operation message of strategy for keeping frequent customer here is favor information, as cash certificate,
Coupons and completely subtract certificate etc..
In the above-mentioned technical solutions, it is preferable that before being divided using sorting algorithm model to user's sample, also wrap
It includes: the mapping relations between pre-set user sample set and operation message, wherein operation message includes application program operation message
And/or short message runs message.
In the technical scheme, by the mapping relations between pre-set user sample set and operation message, further
It ensure that the reliability of orientation push operation message to corresponding user's sample set.
Wherein, mapping relations can be the corresponding a kind of operation message of user's sample set, in order to promote operating service
Diversity, mapping relations are also possible to user's sample set and correspond to multiclass operation message or multiple user's sample sets
Close corresponding a kind of operation message.
In the above-mentioned technical solutions, it is preferable that further include: the specified label conduct of pre-set user sample can be classified calculation
The identification information of method model identification, wherein the specified label of user's sample includes age of user, user's income, user's occupation class
Not, at least one of user's education degree, customer consumption index, user's affiliated area and user activity label.
It in the technical scheme, is the mark that can be classified algorithm model identification by the specified label of pre-set user sample
Know information, sorting algorithm model need to only determine user's sample set belonging to user's sample according to label, use without parsing
The specific data content of family sample, wherein each user's sample may have multiple labels, according to migration efficiency setting wherein one
A or multiple labels are as specified label, to improve the efficiency for dividing user group.
Wherein, above-mentioned specified label can be soft label or hard label, and soft label is commonly used in elastic research,
Have high flexibility and operability, as data update, the corresponding relationship between soft label and user's sample may be sent out
It is raw to change, and hard label is the attribute tags that cannot be modified, the corresponding relationship between hard label and user's sample does not change.
In the above-mentioned technical solutions, it is preferable that further include: client device is received to the response record of operation message；Root
Sorting algorithm model is modified according to response record.
In the technical scheme, by receiving client device to the response record of operation message for correcting sorting algorithm
Model, namely message orientation push will runed after corresponding user's sample set according to migration efficiency, it needs to grab client
End equipment pushes effect to the response record of operation message with registration confirmed according to response, as response record is lower than expected sound
Index is answered, then needs extensive work to correct sorting algorithm model, or even need to re-start model training.
Wherein, response record includes that user checks the frequency, editor's frequency and feedback frequency etc..
In the above-mentioned technical solutions, it is preferable that further include: by user's sample set and corresponding operation message, user's sample
This specified label and the response record of operation message in the form of three-dimensional figure real-time display in user's interaction circle of operation client
Face；Mapping relations are shown in user interface, and according to predetermined period freshness map relationship, wherein user interface
It is preset with edition interface, edition interface is used to receive the edit operation to three-dimensional figure and/or mapping relations, and edit operation includes adding
Add operation, delete operation save at least one of operation and remarks operation operation.
In the technical scheme, by by user's sample set and it is corresponding operation message, user's sample specified label
With operation message response record in the form of three-dimensional figure real-time display in operation client user interface, and display reflect
Relationship is penetrated, friendly intuitive operation interface can be provided for operation personnel, in addition, setting edition interface is in order to operation personnel couple
Three-dimensional figure and/or mapping relations are modified, to improve manual maintenance efficiency, in addition, operation personnel can pass through user's interaction
The dynamic change of related data during objective interface monitoring push, stimulates consumption further to formulate new migration efficiency
Or promotional.
Fig. 4 shows the schematic diagram of the operation push process of embodiment according to the present invention.
Fig. 5 shows the schematic diagram of the user interface of embodiment according to the present invention.
Information according to the present invention push scheme is specifically described below with reference to the embodiment of Fig. 4 and Fig. 5.
As shown in figure 4, information push frame according to the present invention includes server 300,400 He of user client (equipment)
Client (equipment) 500 is runed, user client (equipment) 400 includes Client client and Business client, wherein
Server 300 is based on the application request that above- mentioned information method for pushing obtains user client (equipment) 400 first, is asked according to application
The executive condition asked carries out clustering to label to create the label (label can have priority attribute) of each user
User's sample set is formed, message orientation will be runed according to migration efficiency and push to corresponding user client (equipment) 400, and
The response record for grabbing user client (equipment) 400 pairs of operation message, runs the user interface of client (equipment) 500
User's sample set and corresponding operation message, the specified label of user's sample and response note are shown in the form of three-dimensional figure in real time
Record, operation client (equipment) 500 can report edit operation to server 300 by edition interface, and server 300 will be edited
As a result operation client (equipment) 500 is fed back to.
Wherein, operation client (equipment) 500 can be PC (Personal Computer, PC) and computer
Cluster etc., user client (equipment) 400 can be PC, tablet computer or other have the display equipment of wireless communication ability.
Above-mentioned user interface as shown in figure 5, be different from the data exhibition method of two dimension in the related technology and static state,
The application shows the data dynamic change of multiple sample sets in the form of three-dimensional figure, such as distinguishes user with label, and with instruction of classifying
Practice model partition and obtains user's sample set 1, user's sample set 2 ... ..., user's sample set n (n >=2), other two dimension
Degree is respectively the frequency (times/day) of response record and pushed information (i.e. above-mentioned operation message), in addition, mapping relations such as Fig. 5 institute
Show, user's sample set 1 corresponds to pushed information (library) 1, and user's sample set 2 corresponds to pushed information (library) 2 ... ..., uses
Family sample set n corresponds to pushed information (library) n, and operation personnel can modify above-mentioned three-dimensional figure by edition interface and mapping is closed
System for example can modify display format, the modification frequency and modification display content etc..
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, it is contemplated that the operation cost that the relevant technologies propose is high
And the technical problems such as low efficiency, the invention proposes a kind of information-pushing methods, by using sorting algorithm model to user's sample
This is divided, and with the multiple user's sample sets of determination, is accurately and securely distinguished to different user sample, to be used for
Orientation push, wherein orientation push is realized based on the mapping relations between user's sample set and operation message, Ke Yili
Solution, since mapping relations are determined according to migration efficiency, the efficiency of operation push is not only increased, and make
The operation message that must be pushed more meets the use demand of user, while saving operating service cost of labor, improves user
To the Experience Degree of operating service.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (14)
1. a kind of information-pushing method characterized by comprising
User's sample is divided using sorting algorithm model, with the multiple user's sample sets of determination；
According to the mapping relations between user's sample set and operation message, operation message orientation is pushed into correspondence
User's sample set client device.
2. information-pushing method according to claim 1, which is characterized in that in use sorting algorithm model to user's sample
Before being divided, further includes:
Determine migration efficiency belonging to the operation message and the corresponding default sorting algorithm model of the migration efficiency；
Construct seed specimen set and non-seed sample set；
The default sorting algorithm model is trained using the seed specimen set and the non-seed sample set, it will
The default sorting algorithm model for completing training is determined as the sorting algorithm model.
3. information-pushing method according to claim 2, which is characterized in that in use sorting algorithm model to user's sample
Before being divided, further includes:
The mapping relations between user's sample set and the operation message are preset,
Wherein, the operation message includes application program operation message and/or short message operation message.
4. information-pushing method according to claim 3, which is characterized in that further include:
The specified label of user's sample is preset as the identification information that can be identified by the sorting algorithm model,
Wherein, the specified label of user's sample includes age of user, user's income, user occupational group, user's education journey
At least one of degree, customer consumption index, user's affiliated area and user activity label.
5. information-pushing method according to any one of claim 1 to 4, which is characterized in that further include:
The client device is received to the response record of the operation message；
The sorting algorithm model is modified according to the response record.
6. information-pushing method according to any one of claim 1 to 4, which is characterized in that further include:
User's sample set and the corresponding operation message, the specified label of user's sample and the operation are disappeared
The response record of breath in the form of three-dimensional figure real-time display in operation client user interface；
The mapping relations are shown in the user interface, and refresh the mapping relations according to predetermined period,
Wherein, the user interface is preset with edition interface, the edition interface for receiving to the three-dimensional figure and/or
The edit operation of the mapping relations, the edit operation include addition operation, delete operation, save in operation and remarks operation
At least one operation.
7. a kind of information push-delivery apparatus characterized by comprising
Division unit, for being divided using sorting algorithm model to user's sample, with the multiple user's sample sets of determination；
Push unit, for according to user's sample set and operation message between mapping relations, by the operation message
Orientation pushes to the client device of corresponding user's sample set.
8. information push-delivery apparatus according to claim 7, which is characterized in that further include:
Determination unit, for determining that migration efficiency belonging to the operation message and the migration efficiency are default point corresponding
Class algorithm model；
Construction unit, for constructing seed specimen set and non-seed sample set；
Training unit, for using the seed specimen set and the non-seed sample set to the default sorting algorithm mould
Type is trained, and the default sorting algorithm model for completing training is determined as the sorting algorithm model.
9. information push-delivery apparatus according to claim 8, which is characterized in that further include:
Default unit, for presetting the mapping relations between user's sample set and the operation message,
Wherein, the operation message includes application program operation message and/or short message operation message.
10. information push-delivery apparatus according to claim 9, which is characterized in that
The default unit is also used to: the specified label for presetting user's sample is used as and can be known by the sorting algorithm model
Other identification information,
Wherein, the specified label of user's sample includes age of user, user's income, user occupational group, user's education journey
At least one of degree, customer consumption index, user's affiliated area and user activity label.
11. information push-delivery apparatus according to any one of claims 7 to 10, which is characterized in that further include:
Receiving unit, for receiving the client device to the response record of the operation message；
Amending unit, for being modified according to the response record to the sorting algorithm model.
12. information push-delivery apparatus according to any one of claims 7 to 10, which is characterized in that further include:
Display unit, for by user's sample set and it is corresponding it is described operation message, user's sample specified mark
Label and it is described operation message response record in the form of three-dimensional figure real-time display in operation client user interface；
The display unit is also used to: the mapping relations being shown in the user interface, and according to predetermined period brush
The new mapping relations,
Wherein, the user interface is preset with edition interface, the edition interface for receiving to the three-dimensional figure and/or
The edit operation of the mapping relations, the edit operation include addition operation, delete operation, save in operation and remarks operation
At least one operation.
13. a kind of server, including memory, processor and it is stored on the memory and can runs on the processor
Computer program, which is characterized in that the processor is realized when executing the computer program as appointed in claim 1 to 6
The step of one information-pushing method limits, and/or include the information push dress as described in any one of claim 7 to 12
It sets.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of limiting such as any one of claims 1 to 6 information-pushing method is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711081581.6A CN109756541A (en) | 2017-11-07 | 2017-11-07 | Information-pushing method, device, server and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711081581.6A CN109756541A (en) | 2017-11-07 | 2017-11-07 | Information-pushing method, device, server and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109756541A true CN109756541A (en) | 2019-05-14 |
Family
ID=66400035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711081581.6A Pending CN109756541A (en) | 2017-11-07 | 2017-11-07 | Information-pushing method, device, server and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109756541A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351673A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Note transmission method, device, system and electronic equipment based on label model |
| CN112184005A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Operation task classification method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103685502A (en) * | 2013-12-09 | 2014-03-26 | 腾讯科技（深圳）有限公司 | Message pushing method, device and system |
| US20160117595A1 (en) * | 2013-07-11 | 2016-04-28 | Huawei Technologies Co., Ltd. | Information recommendation method and apparatus in social media |
| CN106559681A (en) * | 2016-11-10 | 2017-04-05 | 中广热点云科技有限公司 | A kind of super focus platform of CMMB |
-
2017
- 2017-11-07 CN CN201711081581.6A patent/CN109756541A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160117595A1 (en) * | 2013-07-11 | 2016-04-28 | Huawei Technologies Co., Ltd. | Information recommendation method and apparatus in social media |
| CN103685502A (en) * | 2013-12-09 | 2014-03-26 | 腾讯科技（深圳）有限公司 | Message pushing method, device and system |
| CN106559681A (en) * | 2016-11-10 | 2017-04-05 | 中广热点云科技有限公司 | A kind of super focus platform of CMMB |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110351673A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Note transmission method, device, system and electronic equipment based on label model |
| CN112184005A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Operation task classification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lau et al. | Impact of information sharing on inventory replenishment in divergent supply chains | |
| Green et al. | Thirty years of conjoint analysis: Reflections and prospects | |
| Witt et al. | The implementation of total quality management in tourism: some guidelines | |
| WO2019056710A1 (en) | Supplier recommendation method and apparatus, and computer readable storage medium | |
| US20220292999A1 (en) | Real time training | |
| Strong | Marketing and management models: a guide to understanding and using business models | |
| WO2019061997A1 (en) | Method for enriching wechat customer tags, electronic device and storage medium | |
| Ermagun et al. | Crowd-shipping delivery performance from bidding to delivering | |
| TWI818176B (en) | Planning aids and planning aids | |
| CN109756541A (en) | Information-pushing method, device, server and computer readable storage medium | |
| US10102774B2 (en) | Systems and methods for organizing and presenting skill progressions | |
| Hajiheydari et al. | BPM implementation critical success factors: applying meta-synthesis approach | |
| US20180253811A1 (en) | Career gap identifier | |
| Saltzman et al. | Simulating student flow through a college of business for policy and structural change analysis | |
| CN104834990A (en) | Passenger informatization coding method and device | |
| US20170140487A1 (en) | Student graduation requirements records system and method | |
| CN113468402A (en) | Target object determination method, device and storage medium | |
| Nunes et al. | How transformational leadership influences museums’ performance: A contextual ambidexterity view | |
| US20230325944A1 (en) | Adaptive wellness collaborative media system | |
| CN108053237A (en) | A kind of crowd portrayal report-generating method, advertisement placement method and platform | |
| US20200160359A1 (en) | User-experience development system | |
| Fernandes et al. | Stakeholder management in university-industry collaboration programs: A case study | |
| Marzo‐Navarro | The educational gap in higher education: The Spanish case | |
| Nan et al. | [Retracted] Corporate Marketing Strategy Analysis with Machine Learning Algorithms | |
| Nandi | Maintaining database: Business intelligence tool for competitive advantage |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190514 |
|
| RJ01 | Rejection of invention patent application after publication |