CN107911491A - Information recommendation method, device and storage medium, server and mobile terminal - Google Patents
Information recommendation method, device and storage medium, server and mobile terminal Download PDFInfo
- Publication number
- CN107911491A CN107911491A CN201711451195.1A CN201711451195A CN107911491A CN 107911491 A CN107911491 A CN 107911491A CN 201711451195 A CN201711451195 A CN 201711451195A CN 107911491 A CN107911491 A CN 107911491A
- Authority
- CN
- China
- Prior art keywords
- evaluation result
- application program
- default
- information
- prediction model
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application discloses a kind of information recommendation method, device and storage medium, server and mobile terminal, the described method includes:Receive the operation information that the user that mobile terminal is sent holds in the current class of current application program;The operation information and current class are inputted into default evaluation result prediction model corresponding to the current application program, obtain the output result of the default evaluation result prediction model, the default evaluation result prediction model is generated by the historical operation record under current application program based on machine learning method training, for predicting evaluation result of the user to current class content according to operation information;The recommendation information of other classifications is pushed to the mobile terminal according to the output result.Scheme provided by the embodiments of the present application, improves the accuracy and intelligence of mobile terminal recommendation information.
Description
Technical field
The invention relates to play control technology field, more particularly to a kind of information recommendation method, device and storage
Medium, server and mobile terminal.
Background technology
With the development of Internet communication technology, the background server of each application program can be pushed away to application user
Related content is recommended, such as recommends entertainment news, sports news etc. under news application, recommends household electrical appliances, clothes in the case where day cat is applied
Dress, household items etc..Do not pushed away reasonably according to operating habit of the user under application program reasonably in the related art
Relevant information is recommended, it is necessary to improve.
The content of the invention
The embodiment of the present application provides a kind of information recommendation method, device and storage medium, server and mobile terminal, can be with
Rationally meet the recommendation information of user demand to mobile terminal push.
In a first aspect, the embodiment of the present application provides a kind of information recommendation method, including:
Receive the operation information that the user that mobile terminal is sent holds in the current class of current application program;
The operation information and current class are inputted into default evaluation result prediction corresponding to the current application program
Model, obtains the output of the default evaluation result prediction model as a result, the default evaluation result prediction model is by currently should
With the historical operation record under program based on machine learning method training generation, for predicting user to current according to operation information
The evaluation result of category content;
The recommendation information of other classifications is pushed to the mobile terminal according to the output result.
In second aspect, the embodiment of the present application provides another information recommendation method, including:
Obtain the operation information that user holds in the current class of current application program;
The operation information is inputted into default evaluation result prediction model corresponding to the current application program, obtains institute
The output of default evaluation result prediction model is stated as a result, the default evaluation result prediction model is by going through under current application program
History operation note is based on machine learning method training generation, for predicting that user comments current class content according to operation information
Valency result;
The recommendation information of other classifications is determined according to the output result;
The recommendation information of other classifications is obtained from predetermined server and shows user.
In the third aspect, the embodiment of the present application provides a kind of information recommending apparatus, sets in the server, including:
First operation information acquisition module, for receiving current class of the user in current application program of mobile terminal transmission
The not interior operation information held;
First evaluation result prediction module, for inputting the operation information and current class to the current application journey
The corresponding default evaluation result prediction model of sequence, obtains the output of the default evaluation result prediction model as a result, described default
Evaluation result prediction model is generated by the historical operation record under current application program based on machine learning method training, for root
Evaluation result of the user to current class content is predicted according to operation information;
Info push module, for pushing the recommendation information of other classifications to user according to the output result.
In fourth aspect, the embodiment of the present application provides another information recommending apparatus, sets in the terminal, bag
Include:
Second operation information acquisition module, the operation held for obtaining user in the current class of current application program
Information;
Second evaluation result prediction module, it is corresponding pre- to the current application program for inputting the operation information
If evaluation result prediction model, the output of the default evaluation result prediction model is obtained as a result, the default evaluation result is pre-
Model is surveyed by the historical operation record under current application program based on machine learning method training generation, for according to operation information
Predict evaluation result of the user to current class content;
Recommendation information determining module, for determining the recommendation information of other classifications according to the output result;
Recommendation information display module, for obtaining the recommendation information of other classifications from predetermined server and showing
User.
At the 5th aspect, the embodiment of the present application provides a kind of computer-readable recording medium, is stored thereon with computer
Program, realizes the information recommendation method provided such as first aspect when which is executed by processor.
At the 6th aspect, the embodiment of the present application provides a kind of computer-readable recording medium, is stored thereon with computer
Program, realizes the information recommendation method provided such as second aspect when which is executed by processor.
At the 7th aspect, the embodiment of the present application provides a kind of server, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, the information that such as first aspect is provided is realized when the processor performs
Recommendation method.
In eighth aspect, the embodiment of the present application provides a kind of mobile terminal, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, the letter that such as second aspect is provided is realized when the processor performs
Cease recommendation method.
The operation information that the embodiment of the present application is held by obtaining user in the current class of current application program, by this
Operation information and current class are inputted into the corresponding default assessment result prediction model of the current application program, are exported
Prediction result, if prediction result is does not like, terminal where to user pushes the recommendation information of other classifications, realizes base
Operation information in user to current class content, analyzes evaluation result of the user to current class content, recommends to user
Other category content information, are more bonded the real experiences demand of user.Using above-mentioned technical proposal, solve in the prior art not
Rationally recommend the technical problem of respective classes content according to the operation information of user, improve the accurate of mobile terminal recommendation information
Degree and intelligence.
Brief description of the drawings
Fig. 1 is a kind of flow chart of information recommendation method provided by the embodiments of the present application;
Fig. 2 is the flow chart of another information recommendation method provided by the embodiments of the present application;
Fig. 3 is a kind of structure diagram of information recommending apparatus provided by the embodiments of the present application;
Fig. 4 is the structure diagram of another information recommending apparatus provided by the embodiments of the present application;
Fig. 5 is a kind of structure diagram of server provided by the embodiments of the present application;
Fig. 6 is a kind of structure diagram of mobile terminal provided by the embodiments of the present application.
Embodiment
It is specifically real to the application below in conjunction with the accompanying drawings in order to make the purpose, technical scheme and advantage of the application clearer
Example is applied to be described in further detail.It is understood that specific embodiment described herein is used only for explaining the application,
Rather than the restriction to the application.It also should be noted that for the ease of describing, illustrate only in attached drawing related to the application
Part rather than full content.It should be mentioned that some exemplary realities before exemplary embodiment is discussed in greater detail
Apply processing or method that example is described as describing as flow chart.Although operations (or step) are described as order by flow chart
Processing, but many of which operation can be implemented concurrently, concomitantly or at the same time.In addition, the order of operations
It can be rearranged.The processing can be terminated when its operations are completed, it is also possible to being not included in attached drawing
Additional step.The processing can correspond to method, function, code, subroutine, subprogram etc..
Fig. 1 gives a kind of flow chart of information recommendation method provided by the embodiments of the present application, and the method for the present embodiment can
To be performed by information recommending apparatus, which can be realized by way of hardware and/or software, and described device can be used as service
A part for device is arranged on the inside of the server.
As shown in Figure 1, information recommendation method provided in this embodiment comprises the following steps:
Step 101, receive the operation letter that the user that mobile terminal is sent holds in the current class of current application program
Breath.
The current application program is the foreground application that mobile terminal terminal user is operating.The current application
Program can be the application program that mobile terminal user newly installs.The current class is that user is grasping under current application program
The classification of work.Wherein, an application program can include one or more category content.Exemplary, a novel application
Under can include novel classification and short story classification, or describing love affairs, science fiction, suspense, terrified several classifications;One game
Using can be adventure either role playing class or action class or shooting etc..
It is specifically as follows the operation information held in current class of the user in current application program within the setting cycle, institute
It can be one day or one week etc. to state the setting cycle.
Optionally, operation information includes payment amount, operation duration, operating interval time, system time, network mark
At least one of in knowledge, operating frequency and operation expression.
Optionally, the operation letter held in current class of the user that reception mobile terminal is sent in current application program
Further included after breath:The duration that the operation duration is matched according to default first coding rule numbers;According to default
Second coding rule matches the interval time numbering of the operating interval time;The net is matched according to default 3rd coding rule
The network numbering of network mark;The expression that the operation expression is matched according to default 4th coding rule is numbered;According to the default 5th
Coding rule matches the class number of the current class;Period according to belonging to the system time determines that system time is compiled
Number, wherein, the period is respectively obtained to preset time section in consecutive days, the period numbers with system time
Associated storage.
Step 102, by the operation information and current class input default evaluation corresponding to the current application program
Prediction of result model, obtains the output result of the default evaluation result prediction model.The default evaluation result prediction model
By the historical operation record under current application program based on machine learning method training generation, used for being predicted according to operation information
Evaluation result of the family to current class content.
Wherein, evaluation result can include liking and not liking.
The default evaluation result prediction model is to be based on machine according to the historical operation record under the current application program
The training generation of device learning method.The training of the evaluation result prediction model and generating process can carry out in the server,
It can also on mobile terminals carry out, train generation to finish or update in the server when evaluation result prediction model and finish
Afterwards, mobile terminal can be sent directly to be stored, or is stored in predetermined server, wait standby communication terminal actively to obtain
Take.The training generation in service of evaluation result prediction model is preset in the present embodiment.
In the embodiment of the present application, the source of training sample is recorded to the historical operation of current application program and quantity is not done
It is specific to limit.For example, the mobile terminal user that training sample can be the use application program that server obtains was using
Historical operation record in journey.Wherein, historical operation record includes the operation information and evaluation result of user.
In the embodiment of the present application corresponding evaluation knot is established for each application program or same type application program
Fruit prediction model, so set the reason for be:Each attributive character and difference in application program operation information, targetedly
Corresponding evaluation result prediction model is established to each application program or same type application program, commenting for foundation can be made
Valency prediction of result model accuracy higher.
Wherein, the machine learning method includes neural net method, support vector machine method, traditional decision-tree, logic
Homing method, bayes method, K- means clustering methods and random forest method.
Optionally, the operation information and current class are inputted to the corresponding default evaluation of the current application program and tied
Fruit prediction model, obtaining the output result of the default evaluation result prediction model includes:By the payment amount, duration
Numbering, interval time numbering, system time numbering, network numbering, operating frequency, expression numbering and class number are inputted to described
The corresponding default evaluation result prediction model of current application program, obtains the output knot of the default evaluation result prediction model
Fruit.
Step 103, the recommendation information for pushing to the mobile terminal according to the output result other classifications.
If output result can not do any operation, or recommend under the category to the mobile terminal to like
Other guide;If output result pushes the recommendation information of other classifications to the mobile terminal not like.
Wherein, the recommendation information of other classifications can be the classification for having default correspondence with current class, can also
For any classification in addition to the current class, other classifications being specifically as follows under current application program, or its
Other classifications under his application program.Exemplary, current application program reads application program for novel, if current class is length
Piece class novel, then other classifications can be short story, and exemplary, current application program is game application, if currently
Classification is adventure, then other classifications can be role playing class.The recommendation that other classifications are pushed to the mobile terminal
Information, can specifically push the recommendation of other classifications when user is again turned on current application program to mobile terminal where user
Information, or when user opens the category content of the application program, to the recommendation information with other classifications of push.
Based on the above technical solutions, information recommendation method provided by the embodiments of the present application further includes foundation and applies journey
The step of default evaluation result prediction model of sequence, i.e., method provided in this embodiment further include:To the current application program
Under historical operation record be trained based on machine learning method, generate the current application program it is corresponding it is default evaluation knot
Fruit prediction model.
The step of the historical operation record obtained under application program is further included before default evaluation result prediction model is established
Suddenly.Wherein, historical operation record can include operation information and evaluation result.Server can be stored in the form of tables of data
Historical operation record is stated, which can be stored in server database.
After historical operation record is got, historical operation is recorded and carries out data prediction, will can specifically be operated
Each characteristic information in information, and the corresponding classification of operation information are numbered.Optionally, the operation information includes paying
Take the amount of money, operation duration, operating interval time, system time, network identity, operating frequency and operation expression.
Numbered according to the duration of default first coding rule matching operation duration.Exemplary, with 1 hour
The duration is numbered for unit, the duration numbering less than 1 hour is 0, in 1 hour between 2 hours
Duration numbering be 1,2 hours between 3 hours duration numbering be 2 ... ....Wherein, when this continues
Between can be setting the cycle in total duration.
Numbered according to the interval time of default second coding rule matching operation interval time.Exemplary, it is small less than 1
When interval time numbering be 0, be 1 in 1 hour to the duration numbering between 2 hours, in 2 hours to 3 small
When between duration numbering be 2 ... ....Wherein, which can be each interval time in the setting cycle
Weighted value summation, wherein, the weights of longer interval time interval time are larger.
(it can be SSID, Service Set Identifier, take according to default 3rd coding rule matching network mark
Be engaged in set identifier, represent WIFI titles) network numbering.Can be that each SSID assigns nonoverlapping numeral.It is appreciated that
Network label u ∈ [0,1,2 ...], maximum network numbering depend on accessed altogether in the application program operational process number
A different WIFI.
Numbered according to the expression of the 4th coding rule matching operation expression.It can be opened in the operational process of the application program
Open camera collection user's facial expression image, image analyzed to obtain user's expression, the expression can include it is happy, normal,
Frown, agitation etc..Wherein, specifically model can be understood by the face state for pre-establishing the input of user's facial expression image, obtained
To user's expression, the face state understands that model is trained to obtain by the picture sample of setting quantity.If should within the setting cycle
Application program is run multiple times in different time, can gather user's facial expression image during being run multiple times, and analysis is obtained
The most expression of occurrence number is as the operation expression in the setting cycle in multiple expressions.Exemplary, can be by happily, just
Often, frown, numbering is 0,1,2,3 to agitation respectively, the maximum classification quantity numbered depending on operation expression of expression numbering.
The class number of classification in application program is matched according to the 5th coding rule.Exemplary, under novel application program
Can be 0,1,2,3 by describing love affairs, science fiction, suspense, terrified numbering respectively including describing love affairs, science fiction, suspense, terrified several classifications, class
Classification quantity of the maximum numbering do not numbered depending on classification.
Evaluation result is numbered, exemplary, it is 0 that evaluation result is liked numbering, is not like by evaluation result
Numbering is 1.
In advance by consecutive days 24 it is small when be divided into several periods.If for example, using 1 it is small when as time interval, one
A consecutive days 24 have 24 periods when small, and serial number, access time corresponding system time numbering t are carried out for the period
∈ [0,1,2,3 ... 23], as 0 point of morning are to the application program imparting system time domain 0 is operated between 1:00 AM, to insult
1 point of morning to the application program imparting system time domain 1 ... ... is operated between 2:00 AM should for operation between 23 points to 24 points
Application program imparting system time domain 23.So as to which the period according to belonging to operating the application program determines that system time is compiled
Number.It is understood that due to user can not possibly 24 it is small when use mobile terminal, can also according to the use habit of user,
User is divided using the time interval of mobile terminal.For example, user between 12 points of morning to 6 points of morning in sleep
State, will not use mobile terminal, then can divide time of having a rest, obtain to excluding the time interval outside this section
Period.
By payment amount, duration numbering, interval time numbering, system time numbering, network numbering, operating frequency,
Expression is numbered and class number forms operation information set, is formed prediction result set with evaluation result numbering, is believed by operation
Breath set and expected results set form sample set, using supervised mode of learning or unsupervised learning mode, by right
Sample set is trained, and forms evaluation result prediction model.
Based on the above technical solutions, the machine learning method can be supervised learning method, such as nerve
Network method.Neutral net (Neural Networks, be abbreviated as NNs) system refers to artificial neural network, inspires from the mankind
The biological neural network of brain processing information, it includes input layer, hidden layer and output layer, corresponding to include three kinds of nodes (god
Elementary cell through network):Input node, concealed nodes and output node, input node obtain information from the external world;Hide
Node and the external world do not contact directly, these nodes are calculated using activation primitive, and information is passed from input node
It is delivered to output node;Output node is used to transmit information to the external world.
Optionally, the historical operation under the current application program is recorded and is trained based on machine learning method, it is raw
Include into the corresponding default evaluation result prediction model of the current application program:Obtain the history under the current application program
Operation note, as training sample;Operation information during the historical operation is recorded is inputted to the input layer, and by with
The calculating of the corresponding activation primitive of each node of hidden layer, exports prediction and evaluation result;Using the prediction and evaluation result with
The difference between actual evaluation result in the historical operation record, and optimization algorithm is to the weight in the activation primitive
Corrected repeatedly, until the difference between the prediction and evaluation result and the actual evaluation result is in default error range
It is interior, the activation primitive of each node of training completion is obtained, generates default evaluation result prediction model.
Wherein, the activation primitive refers to provide Nonlinear Modeling ability for nerve network system, it is however generally that is non-thread
Property function.Activation primitive can include relu functions, sigmoid functions, tanh functions or maxout functions.
Sigmoid is common nonlinear activation primitive, its mathematical form is as follows:It defeated
Go out the value between 0-1.Tanh with sigmoid still like, in fact, tanh is the deformation of sigmoid:Tanh (x)=
2sigmoid (2x) -1, unlike sigmoid, tanh is 0 average.In recent years, what relu became is becoming increasingly popular.It
Mathematic(al) representation it is as follows:F (x)=max (0, x), wherein, input signal<When 0, output is all 0, input signal>0 situation
Under, output is equal to input.The expression formula of maxout functions is as follows:fi(x)=maxj∈[1,k]Zij.Assuming that input node includes x1
And x2, corresponding weight are respectively w1 and w2, further include weight b, then output node Y=f (w1*x1+w2*x2+b), wherein f
For activation primitive.In addition, the number of input layer and output layer is usually one, hidden layer can be made of multilayer.
The optimization algorithm includes stochastic gradient descent (Stochastic Gradient Descent, SGD) algorithm, fits
Answering property moments estimation (adaptive moment estimation, adam) algorithm or Momentum algorithms.
Based on the above technical solutions, the machine learning method can be unsupervised learning mode, such as K- equal
It is worth clustering method.So-called clustering problem, is exactly to give an element set D, wherein each element has n observable attribute,
D is divided into k subset using certain algorithm, it is desirable to which distinctiveness ratio is as low as possible between the element of each intra-subset, and different
The element distinctiveness ratio of subset is as high as possible.Wherein each subset is called a cluster.Assuming that X=x1, x2, x3 ..., and xn }, Y=
{ y1, y2, y3 ..., yn }, is two element entries in D, each has n mensurable characteristic attributes, then the distinctiveness ratio of X and Y
It is defined as:D=(X, Y)=f (X, Y)->R, wherein R are real number field, the Euclidean distance that wherein d can be between element:Can also be manhatton distance or Minkowski Distance, such as X
={ 2,1,102 } and the distinctiveness ratio of Y={ 1,3,2 }Namely
It is that two elements map one of real number field to say distinctiveness ratio, the distinctiveness ratio of mapped real number two elements of quantificational expression.
Set D, that is, historical operation record sample in the present embodiment, the historical operation are recorded in sample comprising multiple historical operations record member
Element, each historical operation record element have payment amount, operation duration, operating interval time, system time, network mark
Knowledge, operating frequency, operation expression and category content characteristic attribute.
Optionally, the historical operation under the current application program is recorded and is trained based on machine learning method, it is raw
Include into the corresponding default evaluation result prediction model of the current application program:
The historical operation record under the current application program is obtained, as training sample;Recorded from the historical operation
According to predetermined manner choose center of 2 elements as two initial classes clusters;Remaining member in historical operation record is calculated respectively
Element, according to result of calculation, the surplus element is incorporated into respectively different to the distinctiveness ratio at the center of described two initial classes clusters
Spend in minimum initial classes cluster;According to cluster result, two respective centers of class initial classes cluster are recalculated;Historical operation is remembered
Whole elements of record cluster again according to new center, until cluster result no longer changes, obtain default evaluation result prediction mould
Type, the default evaluation result prediction model are used for the evaluation result classification of predicted operation information.Wherein, it is described from the history
2 elements are chosen in operation note according to predetermined manner as the center of two initial classes clusters to be specifically as follows from historical operation note
Center of 2 elements as two initial classes clusters is randomly selected in record, or 2 distinctiveness ratios are chosen most from historical operation record
Big center of the element as two initial classes clusters.
Wherein, after each characteristic attribute is numbered using the coding rule of the above introduction, can also wrap
Include and normalized operation is carried out to each numbering.Specifically following formula can be used to standardize characteristic attribute numbering:
Wherein, wherein max (ai) and min (ai) represent all elements item in ith attribute maximum and minimum value.Example
Such as, after the element of X={ 2,1,102 } and Y={ 1,3,2 } being normalized to [0,1] section, X '={ 1,0,1 }, Y ' have been reformed into
={ 0,1,0 }, it is about 1.732 to recalculate Euclidean distance.
Information recommendation method provided in this embodiment, server is by obtaining current class of the user in current application program
The operation information inside held, the operation information and current class are inputted to the corresponding default assessment of the current application program and tied
In fruit prediction model, the prediction result that is exported, if prediction result is does not like, terminal where to user pushes other classes
Other recommendation information, realizes the operation information to current class content based on user, analyzes user to current class content
Evaluation result, recommend other category content information to user, be more bonded the real experiences demand of user.Using above-mentioned technical side
Case, solves and rationally recommends the technical problem of respective classes content not according to the operation information of user in the prior art, improve
User improves the accuracy and intelligence of mobile terminal recommendation information to the degree of adhesion of current application program.
Fig. 2 gives the flow chart of another information recommendation method provided by the embodiments of the present application.As shown in Fig. 2, this reality
The method for applying example offer comprises the following steps:
Step 201, obtain the operation information that user holds in the current class of current application program.
The step is specifically as follows the behaviour for obtaining that user holds in the current class of current application program in the setting cycle
Make information.Wherein, the setting cycle can be one day or one week etc., can specifically be set according to user demand.
The operation information include payment amount, operation the duration, the operating interval time, system time, network identity,
At least one of in operating frequency and operation expression.Optionally, the operation information include payment amount, operation the duration,
Operating interval time, system time, network identity, operating frequency and operation expression.
Optionally, further included after the operation information held in current class of the user in current application program is obtained:
The duration that the operation duration is matched according to default first coding rule numbers;According to default second coding rule
Interval time numbering with the operating interval time;The network that the network identity is matched according to default 3rd coding rule is compiled
Number;The expression that the operation expression is matched according to default 4th coding rule is numbered;Institute is matched according to default 5th coding rule
State the class number of current class;Period according to belonging to the system time determines that system time is numbered, wherein, to nature
In a few days preset time section is respectively obtained the period, the period and system time numbering associated storage.
Step 202, input the operation information to the corresponding default evaluation result of the current application program and predict mould
Type, obtains the output of the default evaluation result prediction model as a result, the default evaluation result prediction model is by current application
Historical operation record under program is based on machine learning method training generation, for predicting user to current class according to operation information
The evaluation result of other content.
Optionally, described input the operation information and current class to corresponding preset of the current application program is commented
Valency prediction of result model, obtaining the output result of the default evaluation result prediction model includes:By the payment amount, continue
Time domain, interval time numbering, system time numbering, network numbering, operating frequency, expression numbering and class number input to
The corresponding default evaluation result prediction model of the current application program, obtains the output of the default evaluation result prediction model
As a result.
The step of evaluation result prediction model is preset in acquisition is further included in the present embodiment.Optionally, evaluation result is preset
Model can be recorded based on machine learning method training generation in the historical operation under mobile terminal is locally by current application program,
Can also be that the historical operation record under current application program is transplanted again based on machine learning method training generation in the server
Into mobile terminal, the present embodiment is to this and is not limited.Optionally, the machine learning method includes neutral net side
Method, support vector machine method, traditional decision-tree, logistic regression method, bayes method, K- means clustering methods and random gloomy
Woods method.
If default evaluation result prediction model is locally established using neural net method in mobile terminal, then the present embodiment
The information recommendation method of offer can also comprise the following steps:The historical operation record under the current application program is obtained, is made
For training sample;Operation information during the historical operation is recorded is inputted to the input layer, and is passed through and the hidden layer
The calculating of the corresponding activation primitive of each node, exports prediction and evaluation result;Grasped using the prediction and evaluation result and the history
Difference between the actual evaluation result noted down, and optimization algorithm repair the weight in the activation primitive repeatedly
Just, until the difference between the prediction and evaluation result and the actual evaluation result is trained in default error range
The activation primitive for each node completed, generates default evaluation result prediction model.
If default evaluation result prediction model, then this implementation are locally established using K- means clustering methods in mobile terminal
Example, which provides information recommendation method, to be comprised the following steps:The historical operation record under the current application program is obtained, is made
For training sample;From the historical operation record center of 2 elements as two initial classes clusters is chosen according to predetermined manner;
Surplus element in historical operation record is calculated respectively to the distinctiveness ratio at the center of described two initial classes clusters, according to result of calculation,
The surplus element is incorporated into the minimum initial classes cluster of distinctiveness ratio respectively;According to cluster result, at the beginning of recalculating two classes
The respective center of beginning class cluster;Whole elements that historical operation records are clustered again according to new center, until cluster result is not
Change again, obtain default evaluation result prediction model, the default evaluation result prediction model is used for commenting for predicted operation information
Valency result classification.
Step 203, according to the output result determine the recommendation informations of other classifications.
Step 204, the recommendation information for obtaining from predetermined server other classifications simultaneously show user.
The present embodiment provides information recommendation method, mobile terminal is by obtaining current class of the user in current application program
The operation information inside held, the operation information is inputted to the corresponding default evaluation result of the current application program and predicts mould
Type, obtains the output of the default evaluation result prediction model as a result, determining the recommendation of other classifications according to the output result
Information, the recommendation information of other classifications is obtained from predetermined server and shows user, is realized based on user to working as
The operation information of preceding category content, analyzes evaluation result of the user to current class content, recommends to user in other classifications
Hold information, be more bonded the real experiences demand of user, using above-mentioned technical proposal, solve in the prior art not according to user's
Operation information rationally recommends the technical problem of respective classes content, improves degree of adhesion of the user to current application program, lifting
The accuracy and intelligence of mobile terminal recommendation information.
Fig. 3 is a kind of structure diagram of information recommending apparatus provided by the embodiments of the present application, the device can by software and/
Or hardware realization, integrate in the server.As shown in figure 3, the device is evaluated including the first operation information acquisition module 31, first
Prediction of result module 32 and info push module 33.
The first operation information acquisition module 31, for receiving the user of mobile terminal transmission in current application program
The operation information held in current class;
The first evaluation result prediction module 32, for inputting the operation information and current class to described current
The corresponding default evaluation result prediction model of application program, obtains the output of the default evaluation result prediction model as a result, institute
Default evaluation result prediction model is stated to be generated based on machine learning method training by the historical operation record under current application program,
For predicting evaluation result of the user to current class content according to operation information;
Described information pushing module 33, for pushing the recommendation information of other classifications to user according to the output result.
Device provided in this embodiment, realizes the operation information to current class content based on user, analyzes user
To the evaluation result of current class content, recommend other category content information to user, be more bonded the real experiences demand of user,
Solve and rationally recommend the technical problem of respective classes content not according to the operation information of user in the prior art, improve user
To the degree of adhesion of current application program, the accuracy and intelligence of mobile terminal recommendation information are improved.
Optionally, the operation information includes payment amount, operation duration, operating interval time, system time, net
At least one of in network mark, operating frequency and operation expression.
Optionally, described device further includes default evaluation result prediction model generation module, is specifically used for:
Historical operation under the current application program is recorded and is trained based on machine learning method, generation is described to work as
The corresponding default evaluation result prediction model of preceding application program, the machine learning method include neural net method, support to
Amount machine method, traditional decision-tree, logistic regression method, bayes method, K- means clustering methods and random forest method.
Optionally, the machine learning method includes neural net method, and the neural net method includes input layer, hidden
Hide layer and output layer, the default evaluation result prediction model generation module are specifically used for:
The historical operation record under the current application program is obtained, as training sample;
Operation information during the historical operation is recorded is inputted to the input layer, and by respectively being saved with the hidden layer
The calculating of the corresponding activation primitive of point, exports prediction and evaluation result;
Using the difference between the actual evaluation result in the prediction and evaluation result and historical operation record, and
Optimization algorithm corrects the weight in the activation primitive repeatedly, until the prediction and evaluation result and the actual evaluation
As a result the difference between obtains the activation primitive of each node of training completion in default error range, generates default evaluation
Prediction of result model.
Optionally, the operation information includes payment amount, operation duration, operating interval time, system time, net
Network mark, operating frequency and operation expression, described device further include numbering module, are used for:
After the operation information held in current class of the user of mobile terminal transmission in current application program is received,
The duration that the operation duration is matched according to default first coding rule numbers;
The interval time that the operating interval time is matched according to default second coding rule numbers;
The network numbering of the network identity is matched according to default 3rd coding rule;
The expression that the operation expression is matched according to default 4th coding rule is numbered;
The class number of the current class is matched according to default 5th coding rule;
Period according to belonging to the system time determines that system time is numbered, wherein, to preset time in consecutive days
Section is respectively obtained the period, the period and system time numbering associated storage;
The first evaluation result prediction module is specifically used for:By the payment amount, duration numbering, interval time
Numbering, system time numbering, network numbering, operating frequency, expression numbering and class number are inputted to the current application program
Corresponding default evaluation result prediction model, obtains the output result of the default evaluation result prediction model.
Optionally, the machine learning method includes K- means clustering methods, the default evaluation result prediction model life
It is specifically used for into module:
The historical operation record under the current application program is obtained, as training sample;
From the historical operation record center of 2 elements as two initial classes clusters is chosen according to predetermined manner;
Respectively calculate historical operation record in surplus element to the center of described two initial classes clusters distinctiveness ratio, according to meter
Calculate as a result, the surplus element is incorporated into the minimum initial classes cluster of distinctiveness ratio respectively;
According to cluster result, two respective centers of class initial classes cluster are recalculated;
Whole elements that historical operation records are clustered again according to new center, until cluster result no longer changes, are obtained
To default evaluation result prediction model, the default evaluation result prediction model is used for the evaluation result class of predicted operation information
Not.
Fig. 4 is given as the structure diagram of another information recommending apparatus provided by the embodiments of the present application, which can
By software and/or hardware realization, integrate in the terminal.As shown in figure 4, the device includes the second operation information acquisition module
41st, the second evaluation result prediction module 42, recommendation information determining module 43 and recommendation information display module 44.
The second operation information acquisition module 41, holds for obtaining user in the current class of current application program
Operation information;
The second evaluation result prediction module 42, for inputting the operation information to the current application program pair
The default evaluation result prediction model answered, obtains the output of the default evaluation result prediction model as a result, the default evaluation
Prediction of result model is generated by the historical operation record under current application program based on machine learning method training, for according to behaviour
Make evaluation result of the information prediction user to current class content;
The recommendation information determining module 43, for determining the recommendation information of other classifications according to the output result;
The recommendation information display module 44, for obtaining the recommendation information of other classifications from predetermined server simultaneously
Show user.
Device provided in this embodiment, realizes the operation information to current class content based on user, analyzes user
To the evaluation result of current class content, recommend other category content information to user, be more bonded the real experiences demand of user,
Solve and rationally recommend the technical problem of respective classes content not according to the operation information of user in the prior art, improve user
To the degree of adhesion of current application program, the accuracy and intelligence of mobile terminal recommendation information are improved.
The operation information include payment amount, operation the duration, the operating interval time, system time, network identity,
At least one of in operating frequency and operation expression.
Optionally, the operation information includes payment amount, operation duration, operating interval time, system time, net
Network mark, operating frequency and operation expression, described device further include numbering module, for obtaining user in current application program
Current class in after the operation information that holds, continuing for the operation duration is matched according to default first coding rule
Time domain;
The interval time that the operating interval time is matched according to default second coding rule numbers;
The network numbering of the network identity is matched according to default 3rd coding rule;
The expression that the operation expression is matched according to default 4th coding rule is numbered;
The class number of the current class is matched according to default 5th coding rule;
Period according to belonging to the system time determines that system time is numbered, wherein, to preset time in consecutive days
Section is respectively obtained the period, the period and system time numbering associated storage;
The second evaluation result prediction module is specifically used for:By the payment amount, duration numbering, interval time
Numbering, system time numbering, network numbering, operating frequency, expression numbering and class number are inputted to the current application program
Corresponding default evaluation result prediction model, obtains the output result of the default evaluation result prediction model.
The embodiment of the present application also provides a kind of storage medium for including computer executable instructions, and the computer can perform
Instruction is used to perform a kind of information recommendation method when being performed by computer processor, and this method includes:
Receive the operation information that the user that mobile terminal is sent holds in the current class of current application program;
The operation information and current class are inputted into default evaluation result prediction corresponding to the current application program
Model, obtains the output of the default evaluation result prediction model as a result, the default evaluation result prediction model is by currently should
With the historical operation record under program based on machine learning method training generation, for predicting user to current according to operation information
The evaluation result of category content;
The recommendation information of other classifications is pushed to the mobile terminal according to the output result.
The embodiment of the present application also provides a kind of storage medium for including computer executable instructions, and the computer can perform
Instruction is used to perform a kind of information recommendation method when being performed by computer processor, and this method includes:
Obtain the operation information that user holds in the current class of current application program;
The operation information is inputted into default evaluation result prediction model corresponding to the current application program, obtains institute
The output of default evaluation result prediction model is stated as a result, the default evaluation result prediction model is by going through under current application program
History operation note is based on machine learning method training generation, for predicting that user comments current class content according to operation information
Valency result;
The recommendation information of other classifications is determined according to the output result;
The recommendation information of other classifications is obtained from predetermined server and shows user.
Storage medium --- any various types of memory devices or storage device.Term " storage medium " is intended to wrap
Include:Install medium, such as CD-ROM, floppy disk or magnetic tape equipment;Computer system memory or random access memory, such as
DRAM, DDR RAM, SRAM, EDO RAM, blue Bath (Rambus) RAM etc.;Nonvolatile memory, such as flash memory, magnetizing mediums
(such as hard disk or optical storage);Memory component of register or other similar types etc..Storage medium can further include other
The memory of type or its combination.In addition, storage medium can be located at program in the first computer system being wherein performed,
Or can be located in different second computer systems, second computer system is connected to the by network (such as internet)
One computer system.Second computer system can provide programmed instruction and be used to perform to the first computer." storage is situated between term
Matter " can include may reside within diverse location two of (such as in different computer systems by network connection) or
More storage mediums.Storage medium can store the programmed instruction that can be performed by one or more processors and (such as implement
For computer program).
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present application is provided, its computer
The information recommendation operation that executable instruction is not limited to the described above, can also carry out the information that the application any embodiment is provided
Relevant operation in recommendation method.
The embodiment of the present application provides a kind of server, and information provided by the embodiments of the present application can be integrated in the server and is pushed away
Recommend device.Fig. 5 is a kind of structure diagram of server provided by the embodiments of the present application.The server 12 that Fig. 5 is shown is only
One example, should not bring any restrictions to the function and use scope of the embodiment of the present application.
As shown in figure 5, server 12 is showed in the form of universal computing device.The component of server 12 can be included but not
It is limited to:One or more processor or processing unit 16, system storage 28, connection different system component (including system
Memory 28 and processing unit 16) bus 18.The memory 28, for storing executable program code;The processor
16 is corresponding with the executable program code to run by reading the executable program code stored in the memory 28
Program, for performing:Receive the operation letter that the user that mobile terminal is sent holds in the current class of current application program
Breath;The operation information and current class are inputted into default evaluation result prediction model corresponding to the current application program,
The output of the default evaluation result prediction model is obtained as a result, the default evaluation result prediction model is by current application program
Under historical operation record based on machine learning method training generation, for according to operation information predict user in current class
The evaluation result of appearance;The recommendation information of other classifications is pushed to the mobile terminal according to the output result.
Bus 18 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and periphery component interconnection (PCI) bus.
Server 12 typically comprises various computing systems computer-readable recording medium.These media can any can be serviced
The usable medium that device 12 accesses, including volatile and non-volatile medium, moveable and immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Server 12 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, it is not removable to can be used for read-write for storage system 34
Dynamic, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although not shown in Fig. 5, it can provide
For the disc driver to moving non-volatile magnetic disk (such as " floppy disk ") read-write, and to moving anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42, can be stored in such as memory 28
In, such program module 42 include but not limited to operating system, one or more application program, other program modules and
Routine data, may include the realization of network environment in each or certain combination in these examples.Program module 42 is usual
Perform the function and/or method in embodiment described in the invention.
Server 12 can also be logical with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Letter, can also enable a user to the equipment communication interacted with the server 12 with one or more, and/or with causing the server
12 any equipment (such as network interface card, the modem etc.) communications that can be communicated with one or more of the other computing device.
This communication can be carried out by input/output (I/O) interface 22.Also, server 12 can also pass through network adapter 20
With one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communication.
As shown in the figure, network adapter 20 is communicated by bus 18 with other modules of server 12.It should be understood that although do not show in figure
Go out, server 12 can be combined and use other hardware and/or software module, included but not limited to:Microcode, device driver,
Redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc..Processing
Unit 16 is stored in the program in system storage 28 by operation, so as to perform various functions application and data processing, example
The information recommendation method provided as realized the embodiment of the present application.
Information recommending apparatus, storage medium and the server provided in above-described embodiment can perform the embodiment of the present application and be carried
The information recommendation method of confession, possesses and performs the corresponding function module of this method and beneficial effect.It is not detailed in the above-described embodiments
The ins and outs of description, reference can be made to the information recommendation method that the application any embodiment is provided.
The embodiment of the present application provides a kind of mobile terminal, and letter provided by the embodiments of the present application can be integrated in the mobile terminal
Cease recommendation apparatus.Fig. 6 is a kind of structure diagram of mobile terminal provided by the embodiments of the present application.As shown in fig. 6, the movement is whole
End can include:Memory 601, central processing unit (Central Processing Unit, CPU) 602 (also known as processor, with
Lower abbreviation CPU), the memory 601, for storing executable program code;The processor 602 is by reading the storage
The executable program code stored in device 601 runs program corresponding with the executable program code, for performing:Obtain
Take the operation information that family is held in the current class of current application program;The operation information is inputted to described and currently should
With the corresponding default evaluation result prediction model of program, the output of the default evaluation result prediction model is obtained as a result, described
Default evaluation result prediction model, based on machine learning method training generation, is used by the historical operation record under current application program
In the evaluation result according to operation information prediction user to current class content;Other classifications are determined according to the output result
Recommendation information;The recommendation information of other classifications is obtained from predetermined server and shows user.
The mobile terminal further includes:Peripheral Interface 603, RF (Radio Frequency, radio frequency) circuit 605, audio-frequency electric
Road 606, loudspeaker 611, power management chip 608, input/output (I/O) subsystem 609, touch-screen 612, other input/controls
Control equipment 610 and outside port 604, these components are communicated by one or more communication bus or signal wire 607.
It should be understood that diagram mobile terminal 600 is only an example of mobile terminal, and mobile terminal 600
Can have than more or less components shown in figure, can combine two or more components, or can be with
Configured with different components.Various parts shown in figure can be including one or more signal processings and/or special
Hardware, software including integrated circuit are realized in the combination of hardware and software.
Below just the mobile terminal provided in this embodiment for information recommendation be described in detail, the mobile terminal with
Exemplified by mobile phone.
Memory 601, the memory 601 can be accessed by CPU602, Peripheral Interface 603 etc., and the memory 601 can
Including high-speed random access memory, can also include nonvolatile memory, such as one or more disk memories,
Flush memory device or other volatile solid-state parts.
The peripheral hardware that outputs and inputs of equipment can be connected to CPU502 and deposited by Peripheral Interface 603, the Peripheral Interface 603
Reservoir 601.
I/O subsystems 609, the I/O subsystems 609 can be by the input/output peripherals in equipment, such as touch-screen 612
With other input/control devicess 610, Peripheral Interface 603 is connected to.I/O subsystems 609 can include 6091 He of display controller
For controlling one or more input controllers 6092 of other input/control devicess 610.Wherein, one or more input controls
Device 6092 processed receives electric signal from other input/control devicess 610 or sends electric signal to other input/control devicess 610,
Other input/control devicess 610 can include physical button (pressing button, rocker buttons etc.), dial, slide switch, behaviour
Vertical pole, click on roller.What deserves to be explained is input controller 6092 can with it is following any one be connected:Keyboard, infrared port,
The instruction equipment of USB interface and such as mouse.
Touch-screen 612, the touch-screen 612 are the input interface and output interface between user terminal and user, can
User is shown to depending on output, visual output can include figure, text, icon, video etc..
Display controller 6091 in I/O subsystems 609 receives electric signal from touch-screen 612 or is sent out to touch-screen 612
Electric signals.Touch-screen 612 detects the contact on touch-screen, and the contact detected is converted to and shown by display controller 6091
The interaction of user interface object on touch-screen 612, that is, realize human-computer interaction, the user interface being shown on touch-screen 612
Icon that object can be the icon of running game, be networked to corresponding network etc..What deserves to be explained is equipment can also include light
Mouse, light mouse is not show the touch sensitive surface visually exported, or the extension of the touch sensitive surface formed by touch-screen.
RF circuits 605, are mainly used for establishing the communication of mobile phone and wireless network (i.e. network side), realize mobile phone and wireless network
The data receiver of network and transmission.Such as transmitting-receiving short message, Email etc..Specifically, RF circuits 605 receive and send RF letters
Number, RF signals are also referred to as electromagnetic signal, and RF circuits 605 convert electrical signals to electromagnetic signal or electromagnetic signal is converted to telecommunications
Number, and communicated by the electromagnetic signal with communication network and other equipment.RF circuits 605 can include being used to perform
The known circuit of these functions, it includes but not limited to antenna system, RF transceivers, one or more amplifiers, tuner, one
A or multiple oscillators, digital signal processor, CODEC (COder-DECoder, coder) chipset, user identifier mould
Block (Subscriber Identity Module, SIM) etc..
Voicefrequency circuit 606, is mainly used for receiving voice data from Peripheral Interface 603, which is converted to telecommunications
Number, and the electric signal is sent to loudspeaker 611.
Loudspeaker 611, for the voice signal for receiving mobile phone from wireless network by RF circuits 605, is reduced to sound
And play the sound to user.
Power management chip 608, the hardware for being connected by CPU602, I/O subsystem and Peripheral Interface 603 are supplied
Electricity and power management.
Information recommending apparatus, storage medium and the mobile terminal provided in above-described embodiment can perform the embodiment of the present application institute
The information recommendation method of offer, possesses and performs the corresponding function module of this method and beneficial effect.It is not detailed in the above-described embodiments
The ins and outs described to the greatest extent, reference can be made to the information recommendation method that the application any embodiment is provided.
The technical principle that above are only the preferred embodiment of the application and used.The application is not limited to spy described here
Determine embodiment, the various significant changes that can carry out for a person skilled in the art, readjust and substitute all without departing from
The protection domain of the application.Therefore, although being described in further detail by above example to the application, this Shen
Above example please be not limited only to, in the case where not departing from the application design, other more equivalence enforcements can also be included
Example, and scope of the present application is determined by the scope of claim.
Claims (15)
- A kind of 1. information recommendation method, it is characterised in that including:Receive the operation information that the user that mobile terminal is sent holds in the current class of current application program;The operation information and current class are inputted into default evaluation result prediction model corresponding to the current application program, The output of the default evaluation result prediction model is obtained as a result, the default evaluation result prediction model is by current application program Under historical operation record based on machine learning method training generation, for according to operation information predict user in current class The evaluation result of appearance;The recommendation information of other classifications is pushed to the mobile terminal according to the output result.
- 2. according to the method described in claim 1, it is characterized in that, when the operation information includes payment amount, operation continues Between, the operating interval time, system time, network identity, operating frequency and operation expression at least one of.
- 3. according to the method described in claim 2, it is characterized in that, further include:History under the current application program is grasped Note down and be trained based on machine learning method, generate the corresponding default evaluation result prediction mould of the current application program Type, the machine learning method include neural net method, support vector machine method, traditional decision-tree, logistic regression method, shellfish Leaf this method, K- means clustering methods and random forest method.
- 4. according to the method described in claim 3, it is characterized in that, the machine learning method includes neural net method, institute Stating neural net method includes input layer, hidden layer and output layer, and the historical operation under the current application program is remembered Record is trained based on machine learning method, generates the corresponding default evaluation result prediction model bag of the current application program Include:The historical operation record under the current application program is obtained, as training sample;Operation information during the historical operation is recorded is inputted to the input layer, and is passed through and each node pair of the hidden layer The calculating for the activation primitive answered, exports prediction and evaluation result;Utilize the difference between the actual evaluation result in the prediction and evaluation result and historical operation record, and optimization Algorithm corrects the weight in the activation primitive repeatedly, until the prediction and evaluation result and the actual evaluation result Between difference in default error range, obtain the activation primitive of each node of training completion, generate default evaluation result Prediction model.
- 5. according to the method described in claim 2, it is characterized in that, when the operation information includes payment amount, operation continues Between, the operating interval time, system time, network identity, operating frequency and operation expression, receive mobile terminal send user Further included after the operation information held in the current class of current application program:The duration that the operation duration is matched according to default first coding rule numbers;The interval time that the operating interval time is matched according to default second coding rule numbers;The network numbering of the network identity is matched according to default 3rd coding rule;The expression that the operation expression is matched according to default 4th coding rule is numbered;The class number of the current class is matched according to default 5th coding rule;Period according to belonging to the system time determines that system time is numbered, wherein, to preset time section in consecutive days Respectively obtained the period, the period and system time numbering associated storage;Described input the operation information and current class to the corresponding default evaluation result of the current application program is predicted Model, obtaining the output result of the default evaluation result prediction model includes:By the payment amount, the duration numbering, Interval time numbering, system time numbering, network numbering, operating frequency, expression numbering and class number are inputted to described current The corresponding default evaluation result prediction model of application program, obtains the output result of the default evaluation result prediction model.
- 6. according to the method described in claim 3, it is characterized in that, the machine learning method includes K- means clustering methods, The historical operation under the current application program is recorded and is trained based on machine learning method, and generation is described currently should Included with the corresponding default evaluation result prediction model of program:The historical operation record under the current application program is obtained, as training sample;From the historical operation record center of 2 elements as two initial classes clusters is chosen according to predetermined manner;Surplus element in historical operation record is calculated respectively, to the distinctiveness ratio at the center of described two initial classes clusters, to tie according to calculating Fruit, the surplus element is incorporated into the minimum initial classes cluster of distinctiveness ratio respectively;According to cluster result, two respective centers of class initial classes cluster are recalculated;Whole elements that historical operation records are clustered again according to new center, until cluster result no longer changes, are obtained pre- If evaluation result prediction model, the default evaluation result prediction model is used for the evaluation result classification of predicted operation information.
- A kind of 7. information recommendation method, it is characterised in that including:Obtain the operation information that user holds in the current class of current application program;The operation information is inputted into default evaluation result prediction model corresponding to the current application program, is obtained described pre- If the output of evaluation result prediction model is as a result, the default evaluation result prediction model is grasped by the history under current application program Note down based on machine learning method training generation, for predicting evaluation knot of the user to current class content according to operation information Fruit;The recommendation information of other classifications is determined according to the output result;The recommendation information of other classifications is obtained from predetermined server and shows user.
- 8. the method according to the description of claim 7 is characterized in that when the operation information includes payment amount, operation continues Between, the operating interval time, system time, network identity, operating frequency and operation expression at least one of.
- 9. according to the method described in claim 8, it is characterized in that, when the operation information includes payment amount, operation continues Between, the operating interval time, system time, network identity, operating frequency and operation expression, obtain user in current application program Current class in further include after the operation information that holds:The duration that the operation duration is matched according to default first coding rule numbers;The interval time that the operating interval time is matched according to default second coding rule numbers;The network numbering of the network identity is matched according to default 3rd coding rule;The expression that the operation expression is matched according to default 4th coding rule is numbered;The class number of the current class is matched according to default 5th coding rule;Period according to belonging to the system time determines that system time is numbered, wherein, to preset time section in consecutive days Respectively obtained the period, the period and system time numbering associated storage;Described input the operation information and current class to the corresponding default evaluation result of the current application program is predicted Model, obtaining the output result of the default evaluation result prediction model includes:By the payment amount, the duration numbering, Interval time numbering, system time numbering, network numbering, operating frequency, expression numbering and class number are inputted to described current The corresponding default evaluation result prediction model of application program, obtains the output result of the default evaluation result prediction model.
- 10. a kind of information recommending apparatus, is set in the server, it is characterised in that including:First operation information acquisition module, for receiving the user of mobile terminal transmission in the current class of current application program The operation information held;First evaluation result prediction module, for inputting the operation information and current class to the current application program pair The default evaluation result prediction model answered, obtains the output of the default evaluation result prediction model as a result, the default evaluation Prediction of result model is generated by the historical operation record under current application program based on machine learning method training, for according to behaviour Make evaluation result of the information prediction user to current class content;Info push module, for pushing the recommendation information of other classifications to user according to the output result.
- 11. a kind of information recommending apparatus, is set in the terminal, it is characterised in that including:Second operation information acquisition module, the operation letter held for obtaining user in the current class of current application program Breath;Second evaluation result prediction module, is commented for inputting the operation information to corresponding preset of the current application program Valency prediction of result model, obtains the output of the default evaluation result prediction model as a result, the default evaluation result prediction mould Type is generated by the historical operation record under current application program based on machine learning method training, for being predicted according to operation information Evaluation result of the user to current class content;Recommendation information determining module, for determining the recommendation information of other classifications according to the output result;Recommendation information display module, for obtaining the recommendation information of other classifications from predetermined server and showing use Family.
- 12. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The information recommendation method as described in any in claim 1-6 is realized during execution.
- 13. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The information recommendation method as described in any in claim 7-9 is realized during execution.
- 14. a kind of server, including memory, processor and storage are on a memory and the computer that can run on a processor Program, it is characterised in that the processor realizes the letter as described in any in claim 1-6 when performing the computer program Cease recommendation method.
- 15. a kind of mobile terminal, including memory, processor and storage are on a memory and the calculating that can run on a processor Machine program, it is characterised in that the processor is realized as described in any in claim 7-9 when performing the computer program Information recommendation method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711451195.1A CN107911491B (en) | 2017-12-27 | 2017-12-27 | Information recommendation method, device and storage medium, server and mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711451195.1A CN107911491B (en) | 2017-12-27 | 2017-12-27 | Information recommendation method, device and storage medium, server and mobile terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107911491A true CN107911491A (en) | 2018-04-13 |
CN107911491B CN107911491B (en) | 2019-09-27 |
Family
ID=61871595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711451195.1A Active CN107911491B (en) | 2017-12-27 | 2017-12-27 | Information recommendation method, device and storage medium, server and mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107911491B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804656A (en) * | 2018-06-08 | 2018-11-13 | Oppo广东移动通信有限公司 | Information processing method and device, electronic equipment, computer readable storage medium |
CN108989397A (en) * | 2018-06-26 | 2018-12-11 | 腾讯音乐娱乐科技(深圳)有限公司 | Data recommendation method, device and storage medium |
CN109659005A (en) * | 2018-11-23 | 2019-04-19 | 杭州普利复健科技有限公司 | Information-pushing method and system |
CN109766767A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Behavioral data method for pushing, device, computer equipment and storage medium |
CN110069468A (en) * | 2019-03-18 | 2019-07-30 | 平安普惠企业管理有限公司 | It is a kind of to obtain the method and device of user demand, electronic equipment |
CN110677470A (en) * | 2019-09-24 | 2020-01-10 | 北京小米移动软件有限公司 | Service information pushing method and device and computer readable storage medium |
CN110858377A (en) * | 2018-08-22 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Information processing method, page display method, system and equipment |
CN111143698A (en) * | 2020-01-03 | 2020-05-12 | 三星电子(中国)研发中心 | Content recommendation method and system |
CN111274472A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Information recommendation method and device, server and readable storage medium |
CN111859117A (en) * | 2020-06-19 | 2020-10-30 | 腾讯科技(深圳)有限公司 | Information recommendation method and device, electronic equipment and readable storage medium |
CN111859102A (en) * | 2020-02-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Prompt information determination method, system, medium and storage medium |
CN112041858A (en) * | 2018-05-22 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | System and method for providing travel advice |
CN113468409A (en) * | 2020-03-31 | 2021-10-01 | 本田技研工业株式会社 | Recommendation system and recommendation method |
CN113596528A (en) * | 2020-04-30 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Training method and device of video push model, server and storage medium |
CN113827985A (en) * | 2021-08-12 | 2021-12-24 | 中投国信(北京)科技发展有限公司 | Service information evaluation method and system for big data |
CN114399112A (en) * | 2022-01-14 | 2022-04-26 | 成都秦川物联网科技股份有限公司 | User evaluation obtaining method and system for natural gas energy metering |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111503830B (en) * | 2020-04-26 | 2021-11-16 | 珠海格力电器股份有限公司 | Control method and device of air conditioner and air conditioner |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080219256A1 (en) * | 2007-03-09 | 2008-09-11 | Masashi Tanaka | Content delivery system, terminal, and content delivery method |
CN104361063A (en) * | 2014-11-04 | 2015-02-18 | 北京字节跳动网络技术有限公司 | User interest discovering method and device |
CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Data recommendation method and device for application program |
CN105933425A (en) * | 2016-05-18 | 2016-09-07 | 北京奇虎科技有限公司 | Application recommendation method and device |
CN106130756A (en) * | 2016-06-15 | 2016-11-16 | 晶赞广告(上海)有限公司 | A kind of method and device predicting access content clicking rate |
CN106604066A (en) * | 2016-12-13 | 2017-04-26 | 宁夏凯速德科技有限公司 | Improved personalized recommendation method and system applied to video application |
CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
CN106792171A (en) * | 2016-12-14 | 2017-05-31 | 宁夏灵智科技有限公司 | Personalized recommendation method and system in intelligent video app |
-
2017
- 2017-12-27 CN CN201711451195.1A patent/CN107911491B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080219256A1 (en) * | 2007-03-09 | 2008-09-11 | Masashi Tanaka | Content delivery system, terminal, and content delivery method |
CN104361063A (en) * | 2014-11-04 | 2015-02-18 | 北京字节跳动网络技术有限公司 | User interest discovering method and device |
CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Data recommendation method and device for application program |
CN105933425A (en) * | 2016-05-18 | 2016-09-07 | 北京奇虎科技有限公司 | Application recommendation method and device |
CN106130756A (en) * | 2016-06-15 | 2016-11-16 | 晶赞广告(上海)有限公司 | A kind of method and device predicting access content clicking rate |
CN106604066A (en) * | 2016-12-13 | 2017-04-26 | 宁夏凯速德科技有限公司 | Improved personalized recommendation method and system applied to video application |
CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
CN106792171A (en) * | 2016-12-14 | 2017-05-31 | 宁夏灵智科技有限公司 | Personalized recommendation method and system in intelligent video app |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112041858A (en) * | 2018-05-22 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | System and method for providing travel advice |
CN108804656A (en) * | 2018-06-08 | 2018-11-13 | Oppo广东移动通信有限公司 | Information processing method and device, electronic equipment, computer readable storage medium |
CN108989397A (en) * | 2018-06-26 | 2018-12-11 | 腾讯音乐娱乐科技(深圳)有限公司 | Data recommendation method, device and storage medium |
CN110858377B (en) * | 2018-08-22 | 2024-04-05 | 阿里巴巴集团控股有限公司 | Information processing method, page display method, system and equipment |
CN110858377A (en) * | 2018-08-22 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Information processing method, page display method, system and equipment |
CN109659005A (en) * | 2018-11-23 | 2019-04-19 | 杭州普利复健科技有限公司 | Information-pushing method and system |
CN111274472A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Information recommendation method and device, server and readable storage medium |
CN109766767A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Behavioral data method for pushing, device, computer equipment and storage medium |
CN110069468A (en) * | 2019-03-18 | 2019-07-30 | 平安普惠企业管理有限公司 | It is a kind of to obtain the method and device of user demand, electronic equipment |
CN110677470B (en) * | 2019-09-24 | 2022-04-01 | 北京小米移动软件有限公司 | Service information pushing method and device and computer readable storage medium |
CN110677470A (en) * | 2019-09-24 | 2020-01-10 | 北京小米移动软件有限公司 | Service information pushing method and device and computer readable storage medium |
CN111143698A (en) * | 2020-01-03 | 2020-05-12 | 三星电子(中国)研发中心 | Content recommendation method and system |
CN111859102A (en) * | 2020-02-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Prompt information determination method, system, medium and storage medium |
CN113468409A (en) * | 2020-03-31 | 2021-10-01 | 本田技研工业株式会社 | Recommendation system and recommendation method |
CN113596528A (en) * | 2020-04-30 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Training method and device of video push model, server and storage medium |
CN111859117A (en) * | 2020-06-19 | 2020-10-30 | 腾讯科技(深圳)有限公司 | Information recommendation method and device, electronic equipment and readable storage medium |
CN111859117B (en) * | 2020-06-19 | 2024-03-26 | 腾讯科技(深圳)有限公司 | Information recommendation method and device, electronic equipment and readable storage medium |
CN113827985A (en) * | 2021-08-12 | 2021-12-24 | 中投国信(北京)科技发展有限公司 | Service information evaluation method and system for big data |
CN114399112A (en) * | 2022-01-14 | 2022-04-26 | 成都秦川物联网科技股份有限公司 | User evaluation obtaining method and system for natural gas energy metering |
Also Published As
Publication number | Publication date |
---|---|
CN107911491B (en) | 2019-09-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107911491B (en) | Information recommendation method, device and storage medium, server and mobile terminal | |
CN107947951B (en) | Groups of users recommended method, device and storage medium and server | |
CN109902706B (en) | Recommendation method and device | |
CN107392255B (en) | Generation method and device of minority picture sample, computing equipment and storage medium | |
US8788439B2 (en) | Instance weighted learning machine learning model | |
CN108076224A (en) | application control method, device and storage medium and mobile terminal | |
CN108076154A (en) | Application message recommends method, apparatus and storage medium and server | |
CN108319599A (en) | A kind of interactive method and apparatus | |
CN108153463B (en) | Application interface display control method and device, storage medium and mobile terminal | |
CN107995428A (en) | Image processing method, device and storage medium and mobile terminal | |
CN107423442A (en) | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis | |
CN107995370B (en) | Call control method, device, storage medium and mobile terminal | |
CN109948633A (en) | User gender prediction method, apparatus, storage medium and electronic equipment | |
CN107071193A (en) | The method and apparatus of interactive answering system accessing user | |
CN110069715A (en) | A kind of method of information recommendation model training, the method and device of information recommendation | |
CN107943583A (en) | Processing method, device, storage medium and the electronic equipment of application program | |
CN108108743A (en) | Abnormal user recognition methods and the device for identifying abnormal user | |
CN108198041A (en) | A kind of Method of Commodity Recommendation based on time attenuator, terminal and medium | |
CN110472798A (en) | Prediction technique, device and the computer readable storage medium of time series data | |
CN112528164B (en) | User collaborative filtering recall method and device | |
CN109614414A (en) | A kind of determination method and device of user information | |
CN106909560A (en) | Point of interest sort method | |
CN109753275A (en) | Recommended method, device, storage medium and the electronic equipment of Application Programming Interface | |
CN111243604B (en) | Training method for speaker recognition neural network model supporting multiple awakening words, speaker recognition method and system | |
CN113344184A (en) | User portrait prediction method, device, terminal and computer readable storage medium |
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 | ||
CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |