CN109741108A - Streaming application recommended method, device and electronic equipment based on context aware - Google Patents
Streaming application recommended method, device and electronic equipment based on context aware Download PDFInfo
- Publication number
- CN109741108A CN109741108A CN201811654907.4A CN201811654907A CN109741108A CN 109741108 A CN109741108 A CN 109741108A CN 201811654907 A CN201811654907 A CN 201811654907A CN 109741108 A CN109741108 A CN 109741108A
- Authority
- CN
- China
- Prior art keywords
- user
- contextual information
- context
- situation
- context data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention provides a kind of streaming application recommended method, device and electronic equipment based on context aware, wherein this method comprises: obtaining the contextual information of user;Contextual information is pre-processed, normalized context data is obtained;Context data is predicted using default context recognition model, obtains situation active tags corresponding with context data;According to situation active tags, streaming application recommendation list is generated and sent.The present invention is handled by the contextual information to user, and is predicted using default context recognition model, to push streaming application recommendation list to user, is improved the accuracy that user individual application is recommended, is also improved using the processing speed recommended.
Description
Technical field
The present invention relates to field of artificial intelligence, apply recommendation side more particularly, to a kind of streaming based on context aware
Method, device and electronic equipment.
Background technique
With the rapid development of current mobile communication technology and popularizing for smart phone, mobile application is increasingly becoming our works
Indispensable a part in making and living.Statistical data shows that China's mobile phone users reach in by the end of June, 2017 for cut-off
7.24 hundred million people, the 96.3% of the total netizen's number of Zhan.Mobile application quantity has surpassed 4,020,000 sections in the market, the movement that we are contacted
Number of applications type while sharp increase is also more and more abundant.It needs to use certain when user is under a specific situation
There is no when these applications in kind application and mobile phone, then need to download and install these applications manually.When user leaves
It after current context, may be very low using frequency to these or use, but application is still resident in the terminal
Memory space is occupied, this not only makes troubles to user, is also unfavorable for popularization of the application developer to application.In addition, present
Social category, purchase by group the mobile applications frameworks such as class, service for life class and game class and service it is substantially similar, homogeneity it is excessively serious.
In order to preferably meet the individual demand of user, following mobile application developing direction should be known based on user context perception
Other active service.
Summary of the invention
In view of this, the streaming application recommended method that the purpose of the present invention is to provide a kind of based on context aware, device
And electronic equipment, to improve the accuracy that user individual application is recommended, while improving using the processing speed recommended.
In a first aspect, the embodiment of the invention provides a kind of streaming application recommended method based on context aware, wherein packet
It includes: obtaining the contextual information of user;Contextual information is pre-processed, normalized context data is obtained;Utilize default situation
Identification model predicts context data, obtains situation active tags corresponding with context data;According to situation activity mark
Label, generate and send streaming application recommendation list.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein feelings
Border information includes time situation, user context, space situation and equipment situation.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein right
Contextual information is pre-processed, and normalized context data is obtained, comprising: is rejected the exception information in contextual information, is obtained the
One contextual information;First contextual information is refined according to default refinement rule, obtains the second contextual information;To the second situation
Information is normalized according to default normalization rule, obtains normalized context data.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein pre-
If the foundation of context recognition model, comprising: obtain the contextual information sample of user;Contextual information sample is pre-processed, is obtained
To normalized context data sample;Build initial xgboost model;Context data sample is input to xgboost model
In be trained, obtain context recognition model.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 4th kind of first aspect
Possible embodiment, wherein this method further include: the contextual information that user increases newly is obtained, according to newly-increased context data pair
Context recognition model is adjusted.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein should
Method further include: the feedback information for receiving user carries out tuning according to feedback information convection type application recommendation list.
The 5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein tuning is carried out according to feedback information convection type application recommendation list, comprising: according to feedback information,
The application degree of liking of the user's degree of liking and/or user that are applied;According to the application of user's degree of liking of application and/or user
Degree of liking, convection type application recommendation list carry out tuning.
Second aspect, the embodiment of the present invention also provide a kind of streaming application recommendation apparatus based on context aware, wherein packet
It includes: module is obtained, for obtaining the contextual information of user;Preprocessing module is returned for pre-processing to contextual information
One context data changed;Prediction module is obtained and situation for being predicted using default context recognition model context data
The corresponding situation active tags of data;List Generating Module, for generating and sending streaming application according to situation active tags
Recommendation list.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment, including memory, processor, deposit in memory
Contain the computer program that can be run on a processor, wherein processor realizes above-mentioned first aspect when executing computer program
The step of described method.
Fourth aspect, the embodiment of the present invention also provide a kind of meter of non-volatile program code that can be performed with processor
Calculation machine readable medium, wherein program code makes processor execute above-mentioned first aspect the method.
The embodiment of the present invention bring it is following the utility model has the advantages that
The embodiment of the invention provides a kind of streaming application recommended method, device and electronic equipment based on context aware,
Wherein, this method comprises: obtaining the contextual information of user;Contextual information is pre-processed, normalized context data is obtained;
Context data is predicted using default context recognition model, obtains situation active tags corresponding with context data;Root
According to situation active tags, streaming application recommendation list is generated and sent.The embodiment of the present invention by the contextual information to user into
Row processing, and predicted using default context recognition model, to push streaming application recommendation list to user, improve use
The accuracy that family personalized application is recommended is also improved using the processing speed recommended.
Other features and advantages of the present invention will illustrate in the following description, alternatively, Partial Feature and advantage can be with
Deduce from specification or unambiguously determine, or by implementing above-mentioned technology of the invention it can be learnt that.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, better embodiment is cited below particularly, and match
Appended attached drawing is closed, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of process of the streaming application recommendation apparatus method based on context aware provided in an embodiment of the present invention
Figure;
Fig. 2 is that a kind of pair of contextual information provided in an embodiment of the present invention carries out pretreated flow chart;
Fig. 3 is a kind of flow chart for establishing context recognition model provided in an embodiment of the present invention;
Fig. 4 is a kind of flow chart for adjusting context recognition model provided in an embodiment of the present invention;
Fig. 5 is a kind of process for generating streaming application recommendation list and obtaining user feedback provided in an embodiment of the present invention
Figure;
Fig. 6 is a kind of structural representation of the streaming application recommendation apparatus based on context aware provided in an embodiment of the present invention
Figure;
Fig. 7 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
Currently, streaming application refers to that mobile application is not stored at mobile terminal, but clothes are stored in as a kind of resource
It is engaged in device end, one kind in the form of data flow from server end on-demand loading to terminal device for users to use when the user desires
Application model.Main " separation is deposited in calculation ", " streaming execution " thought used for reference in lucidification disposal of streaming application.Lucidification disposal is a kind of
Novel common calculating model, user do not need aware operating systems, application program and communication network, and can be according to demand from end
Corresponding calculate is found in end equipment to service.In such a mode, client is not necessarily to storage program area and application program, when need
When using these resources, by network from lucidification disposal Server remote on-demand loading to local.Lucidification disposal service
Device is mainly responsible for management and dispatches these operating systems, application program and data resource.It is provided in an embodiment of the present invention based on this
A kind of streaming application recommended method, device and electronic equipment based on context aware, can apply in user is to meet oneself certainly
Own demand is downloaded in the scene of various applications.
For convenient for understanding the present embodiment, first to a kind of based on context aware disclosed in the embodiment of the present invention
Streaming application recommended method method describes in detail.
A kind of flow chart of streaming application recommended method based on context aware shown in Figure 1, wherein this method tool
Steps are as follows for body:
Step S102 obtains the contextual information of user;
The acquisition of contextual information is acquired at user in real time according to a variety of movable sensors built in mobile terminal
Situation activity, the contextual information of acquisition includes time situation, user context, space situation and equipment situation.
Time situation can embody user in different times section behavior be intended to, such as distinguished using the date working day with
Nonworkdays.
User context is used to describe the essential characteristic of user, type, age, educational background, gender and hobby including user etc.
Information, acquisition modes are provided when being registration by user.
Equipment situation is mainly reflected in the state status of mobile terminal itself, including remaining capacity, network state, Wi-Fi
(Wireless-Fidelity, Wireless Fidelity) state and neighbouring SSID (Service Set Identifier, service set)
The information such as signal strength can be directly acquired by mobile terminal.
Space situation includes location information, light intensity information and action message;Wherein, the acquisition of location information uses
GPS (Global Positioning System, global positioning system) and the Wi-Fi mode that combines of positioning obtains user
Location information;Light intensity information can directly acquire the parameter of optical sensor to judge that environment locating for user is indoor
Or it is outdoor;The acquisition of action message is needed by the acceleration transducer etc. built in mobile terminal, using the arrow of 3-axis acceleration
Amount and MA indicate the acceleration value of equipment, wherein can indicate are as follows:
Wherein, Ax、AyAnd AzWhat is respectively indicated is the linear acceleration in x, y and z axes direction.
Step S104, pre-processes contextual information, obtains normalized context data;
It is as shown in Figure 2 that pretreated specific steps are carried out to contextual information, comprising:
Step S202 rejects the exception information in contextual information, obtains the first contextual information;
The step is rejected primarily directed to the abnormal data occurred in contextual information, and a such as student is during class hours
In teaching area, but speed values are greater than 5m/s, then the data are determined as abnormal data, and by it from context data
It rejects.
Step S204 refines the first contextual information according to default refinement rule, obtains the second contextual information;
First contextual information is refined according to default refinement rule, is to be decomposed into the date in the first context data
Nonworkdays and working day;Time decomposition is morning, the morning, noon, afternoon and evening;Speed is decomposed into quiet according to numerical intervals
Only, the spare time walk, walking, running, cycling and by bus;Intensity of illumination is decomposed into outside fine day room, in fine day room, cloudy day outdoor and cloudy room
It is interior etc., to obtain the second contextual information.
The second contextual information is normalized according to default normalization rule, obtains normalized situation by step S206
Data.
Second contextual information is normalized according to default normalization rule, then is to return according to default value to it
One changes, and if date value represents working day for 1 and 2,1,2 represent day off;Time value is 1,2,3,4,5, respectively represents morning
Upper, the morning, noon, afternoon and evening;Gender value is 0 and 1, represents male and female;Speed value is 1,2,3,4,5,6, respectively
Represent it is static, not busy walk, walking, running, cycling and by bus;Identity type is replaced with the finite sequence started counting from 1, such as 1 generation
List procedure person, 2 represent student, and 3 represent teacher etc., to obtain normalized context data.
Above-mentioned steps S202 to step S204 is to carry out pretreated step to contextual information, next proceeds to description and is based on
The processing step of the streaming application recommended method of context aware.
Step S106 predicts context data using default context recognition model, obtains corresponding with context data
Situation active tags;
Context recognition model is mainly obtained using machine learning classification algorithm xgboost Ensemble Learning Algorithms for collection
Contextual information sample set the processes such as modeled, trained and predicted.Xgboost algorithm performance is in GBDT (Gradient
Boosting Decision Tree, a kind of classification regression algorithm realized based on decision tree) have on the basis of algorithm it is further
It is promoted, not only increases the support to linear classifier (gblinear) on learner, but also compare GBDT on cost function
The second Taylor series are carried out, make algorithmic statement faster.Meanwhile Xgboost is also a kind of Incremental Learning Algorithm.Incremental learning is one
Kind of similar anthropology practises the technology of mode, and when trained algorithm model faces new data, algorithm is to training for it
Model modify to carry out promotion study to the knowledge contained in the data newly to arrive.
It is trained study using the contextual information sample set that machine learning algorithm xgboost obtains arrangement, then needle
The corresponding user context active tags of the data can be predicted to the context data newly to arrive.
Step S108 generates and sends streaming application recommendation list according to situation active tags.
After obtaining the situation active tags of user, according to the situation active tags of user, so that it may be screened for user
Meet the mobile application of the situation active tags, generates streaming application in the form of a list and recommend, and the list is pushed to use
Family.
The feedback information for receiving user can also be received, tuning is carried out according to feedback information convection type application recommendation list,
The accuracy of entire recommendation mechanisms is promoted with this.
Wherein, include: according to the method that feedback information convection type application recommendation list carries out tuning
According to feedback information, the application degree of liking of the user's degree of liking and/or user that are applied;
Tuning is carried out according to user's degree of liking of application and/or the application degree of liking of user, convection type application recommendation list.
The streaming application recommended method based on context aware that the embodiment of the invention provides a kind of, this method comprises: obtaining
The contextual information of user;Contextual information is pre-processed, normalized context data is obtained;Utilize default context recognition model
Context data is predicted, situation active tags corresponding with context data are obtained;According to situation active tags, generate simultaneously
Send streaming application recommendation list.The embodiment of the present invention is handled by the contextual information to user, and utilizes default situation
Identification model is predicted, to push streaming application recommendation list to user, improves the standard that user individual application is recommended
Exactness is also improved using the processing speed recommended.
Corresponding to foregoing invention embodiment, emphasis of the embodiment of the present invention describes the establishment process of context recognition model, such as Fig. 3
It is shown, the specific steps are as follows:
Step S302 obtains the contextual information sample of user;
Step S304 pre-processes contextual information sample, obtains normalized context data sample;
Step S306 builds initial xgboost model;
Context data sample is input in xgboost model and is trained by step S308, obtains context recognition model.
Contextual information sample is trained and is predicted using Xgboost Ensemble Learning Algorithms, while being arranged in algorithm certainly
The depth and quantity of plan tree are respectively 10 and 100.It include n sample to one, for the sample set of m dimensional feature, one includes K
The model of decision tree can be usedIt indicates, i.e.,
Wherein, F indicates the function space being made of all decision trees;
Wherein, q indicate x arrive leaf node mapping relations, w expression leaf on weight;
Definition Model objective function is
Wherein,T represents the number of leaf node, when γ is the segmentation of each leaf node
The penalty constant of revenue function, λ are the L2 regular terms penalty coefficients of objective function.
After context recognition model foundation, when the situation locating for the target user changes, by user terminal one
M context data q is collected in a time window and is uploaded to server.Xgboost algorithm combination context recognition model and situation
Information identifies situation active tags Q locating for user's current time maximum probability.Assuming that i-th context data QiIdentification knot
Fruit is Si, it may be assumed that
In this way, can be so that server pushes streaming application recommendation list according to situation active tags for user.
The contextual information that the embodiment of the present invention can also be increased newly by obtaining user, according to newly-increased context data to situation
Identification model is adjusted, and by user, newly generated situation action message increases in context recognition model daily, the training mould
Type makes recommendation effect more preferable, specifically adjusts process as shown in figure 4, specific steps include:
Step S402 obtains situation active tags using context recognition model;
Situation active tags are sent to user by step S404, so that user judges whether correctly to identify;If correct know
Not, step S406 is executed, if executing step S408 without correctly identifying;
The corresponding context data of situation active tags is stored in context data library, executes step S410 by step S406;
Step S408 corrects situation active tags, and executes step S406;
Step S410 judged whether to the preset model training time, if so, step S412 is executed, if not, executing
Step S414;
Step S412, is trained model;Then step 402 is executed;
Step S414 generates streaming application recommendation list and is sent to user.
After obtaining the situation active tags of target user, recommend this feelings from the application repository on server for user
Associated mobile application under the active tags of border.Application repository refers to that developer submits depositing after being applied to streaming application distribution platform
Store up database.Developer will fill in corresponding information, such as Apply Names, icon, affiliated situation class when submitting the application of oneself
Permission etc. when not and running, server are additional addition user's degree of the liking attribute of each application.Backstage sets each using situation
Class label is up to 10, and when some application is recommended to user 1 time, user's degree of liking of the application adds 1.
And server recommends that an one's own situation application can be established after distribution application for each user to user
Tables of data, and in the application currently pushed and situation active tags deposit tables of data.Assuming that server is living according to user context
Moving the set of applications recommended to user is A={ a1,a2,a3,...,a10, user, which only clicks, uses a2And a5, then in individual subscriber
To a in situation application data sheet2And a5Individual's degree of liking add 1 respectively.When user is again at current context, system meeting
It is first that user recommends application according to degree of liking seniority among brothers and sisters in personal situation application table, if lazy weight 10 from application repository
It transfers and supplies, as shown in figure 5, concrete processing procedure includes:
Step S502 obtains scene active tags;
Step S504, judges whether the user has personal situation application table;If so, step S506 is executed, if not provided,
Execute step S508;
Step S506 screens personal situation table;And execute step S510;
Step S508 obtains quantity to be distributed;And execute step S512;
Step S510 judges whether to meet quantitative requirement;If so, step S514 is executed, if not, executing step
S508;
Step S512 screens application from application repository;And execute step S514
Step S514 generates streaming application recommendation list;
Step S516 obtains user feedback.
User context perception recommendation mechanisms, the situation locating for the user is added in the embodiment of the present invention in streaming application system
When activity changes, system is that user recommends to need under distribution current context automatically according to situation activity locating for user
Application, after user leaves locating situation activity, these applications are passed as situation disappears from terminal, are not take up terminal
Memory space.Individual context aware is established on the basis of streaming mobile application dissemination system in conjunction with user context perception
It is adaptive to recommend distribution channel, the foundation of distribution application has been transferred to user itself by administrator, has been improved using distribution
Efficiency effectively can provide personalized mobile application for user and recommend.
Corresponding to foregoing invention embodiment, the embodiment of the invention also provides a kind of, and the streaming application based on context aware is pushed away
The structural schematic diagram of device is recommended, as shown in Figure 6, wherein the device includes:
Module 60 is obtained, for obtaining the contextual information of user;
Preprocessing module 61 obtains normalized context data for pre-processing to contextual information;
Prediction module 62 is obtained and context data for being predicted using default context recognition model context data
Corresponding situation active tags;
List Generating Module 63, for generating and sending streaming application recommendation list according to situation active tags.
Streaming application recommendation apparatus based on context aware provided by the embodiment of the present invention, realization principle and generation
Technical effect is identical with preceding method embodiment, and to briefly describe, Installation practice part does not refer to place, can refer to aforementioned side
Corresponding contents in method embodiment.
A kind of electronic equipment provided in an embodiment of the present invention, as shown in fig. 7, electronic equipment 7 includes memory 71, processor
72, the computer program that can be run on processor 72 is stored in memory 71, processor is realized when executing computer program
The step of method that foregoing invention embodiment provides.
Referring to Fig. 7, electronic equipment further include: bus 73 and communication interface 74, processor 72, communication interface 74 and memory
71 are connected by bus 73;Processor 72 is for executing the executable module stored in memory 71, such as computer program.
Wherein, memory 71 may include high-speed random access memory (RAM, Random Access Memory),
It may further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.By at least
One communication interface 74 (can be wired or wireless) realizes the communication between the system network element and at least one other network element
Connection, can be used internet, wide area network, local network, Metropolitan Area Network (MAN) etc..
Bus 73 can be isa bus, pci bus or eisa bus etc..It is total that bus can be divided into address bus, data
Line, control bus etc..Only to be indicated with a four-headed arrow in Fig. 7, it is not intended that an only bus or one convenient for indicating
The bus of seed type.
Wherein, memory 71 is for storing program, and processor 72 executes program after receiving and executing instruction, and aforementioned
Method performed by invention any embodiment can be applied in processor 72, or be realized by processor 72.
Processor 72 may be a kind of IC chip, the processing capacity with signal.During realization, above-mentioned side
Each step of method can be completed by the integrated logic circuit of the hardware in processor 72 or the instruction of software form.Above-mentioned
Processor 72 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network
Processor (Network Processor, abbreviation NP) etc.;It can also be digital signal processor (Digital Signal
Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated Circuit, referred to as
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute in the embodiment of the present invention
Disclosed each method, step and logic diagram.General processor can be microprocessor or the processor is also possible to appoint
What conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware decoding processing
Device executes completion, or in decoding processor hardware and software module combination execute completion.Software module can be located at
Machine memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register etc. are originally
In the storage medium of field maturation.The storage medium is located at memory 71, and processor 72 reads the information in memory 71, in conjunction with
Its hardware completes the step of above method.
The embodiment of the present invention also provide it is a kind of with processor can be performed non-volatile program code it is computer-readable
Medium, program code make processor execute the method as described in above-mentioned inventive embodiments.
The computer-readable medium of the non-volatile program code provided in an embodiment of the present invention that can be performed with processor,
It is reached with inventive embodiments provided by the above embodiment technical characteristic having the same so also can solve identical technical problem
To identical technical effect.
Computer program product provided by the embodiment of the present invention, including storing the executable non-volatile journey of processor
The computer readable storage medium of sequence code, the instruction that program code includes can be used for executing previous methods as described in the examples
Method, specific implementation can be found in embodiment of the method, and details are not described herein.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of streaming application recommended method based on context aware characterized by comprising
Obtain the contextual information of user;
The contextual information is pre-processed, normalized context data is obtained;
The context data is predicted using default context recognition model, obtains situation corresponding with the context data
Active tags;
According to the situation active tags, streaming application recommendation list is generated and sent.
2. the method according to claim 1, wherein the contextual information includes time situation, user context, sky
Between situation and equipment situation.
3. being returned the method according to claim 1, wherein described pre-process the contextual information
One context data changed, comprising:
The exception information in the contextual information is rejected, the first contextual information is obtained;
First contextual information is refined according to default refinement rule, obtains the second contextual information;
Second contextual information is normalized according to default normalization rule, obtains the normalized context data.
4. the method according to claim 1, wherein the foundation of the default context recognition model, comprising:
Obtain the contextual information sample of user;
The contextual information sample is pre-processed, normalized context data sample is obtained;
Build initial xgboost model;
The context data sample is input in the xgboost model and is trained, the context recognition model is obtained.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
The contextual information that user increases newly is obtained, the context recognition model is adjusted according to the newly-increased context data.
6. the method according to claim 1, wherein the method also includes:
The feedback information for receiving user carries out tuning to the streaming application recommendation list according to the feedback information.
7. according to the method described in claim 6, it is characterized in that, described push away the streaming application according to the feedback information
It recommends list and carries out tuning, comprising:
According to the feedback information, the application degree of liking of the user's degree of liking and/or user that are applied;
According to user's degree of liking of the application and/or the application degree of liking of user, the streaming application recommendation list is carried out
Tuning.
8. a kind of streaming application recommendation apparatus based on context aware characterized by comprising
Module is obtained, for obtaining the contextual information of user;
Preprocessing module obtains normalized context data for pre-processing to the contextual information;
Prediction module is obtained and the situation number for being predicted using default context recognition model the context data
According to corresponding situation active tags;
List Generating Module, for generating and sending streaming application recommendation list according to the situation active tags.
9. a kind of electronic equipment, including memory, processor, be stored in the memory to run on the processor
Computer program, which is characterized in that the processor realizes that the claims 1 to 7 are any when executing the computer program
The step of method described in item.
10. a kind of computer-readable medium for the non-volatile program code that can be performed with processor, which is characterized in that described
Program code makes the processor execute described any the method for claim 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811654907.4A CN109741108A (en) | 2018-12-29 | 2018-12-29 | Streaming application recommended method, device and electronic equipment based on context aware |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811654907.4A CN109741108A (en) | 2018-12-29 | 2018-12-29 | Streaming application recommended method, device and electronic equipment based on context aware |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109741108A true CN109741108A (en) | 2019-05-10 |
Family
ID=66363058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811654907.4A Pending CN109741108A (en) | 2018-12-29 | 2018-12-29 | Streaming application recommended method, device and electronic equipment based on context aware |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109741108A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516760A (en) * | 2019-09-02 | 2019-11-29 | Oppo(重庆)智能科技有限公司 | Situation identification method, device, terminal and computer readable storage medium |
CN111966921A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Community identification method and system based on user scene |
CN112183741A (en) * | 2020-09-01 | 2021-01-05 | 广州杰赛科技股份有限公司 | Scene data processing method and device and storage medium |
CN114285930A (en) * | 2021-12-10 | 2022-04-05 | 杭州逗酷软件科技有限公司 | Interaction method, interaction device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103294801A (en) * | 2013-05-29 | 2013-09-11 | 中国科学技术大学 | Context-awareness-based contact individuation recommending server, client and method |
CN103955464A (en) * | 2014-03-25 | 2014-07-30 | 南京邮电大学 | Recommendation method based on situation fusion sensing |
-
2018
- 2018-12-29 CN CN201811654907.4A patent/CN109741108A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103294801A (en) * | 2013-05-29 | 2013-09-11 | 中国科学技术大学 | Context-awareness-based contact individuation recommending server, client and method |
CN103955464A (en) * | 2014-03-25 | 2014-07-30 | 南京邮电大学 | Recommendation method based on situation fusion sensing |
Non-Patent Citations (3)
Title |
---|
候营辉 等: "用户情境感知的流式移动应用推荐", 《计算机工程与应用》, pages 1 - 5 * |
郭高尚: "情景感知的移动推荐研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
郭高尚: "情景感知的移动推荐研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 March 2015 (2015-03-15), pages 3 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516760A (en) * | 2019-09-02 | 2019-11-29 | Oppo(重庆)智能科技有限公司 | Situation identification method, device, terminal and computer readable storage medium |
CN111966921A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Community identification method and system based on user scene |
CN112183741A (en) * | 2020-09-01 | 2021-01-05 | 广州杰赛科技股份有限公司 | Scene data processing method and device and storage medium |
CN114285930A (en) * | 2021-12-10 | 2022-04-05 | 杭州逗酷软件科技有限公司 | Interaction method, interaction device, electronic equipment and storage medium |
CN114285930B (en) * | 2021-12-10 | 2024-02-23 | 杭州逗酷软件科技有限公司 | Interaction method, device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109741108A (en) | Streaming application recommended method, device and electronic equipment based on context aware | |
CN109934619A (en) | User's portrait tag modeling method, apparatus, electronic equipment and readable storage medium storing program for executing | |
CN108595497B (en) | Data screening method, apparatus and terminal | |
CN106845644A (en) | A kind of heterogeneous network of the contact for learning user and Mobile solution by correlation | |
CN111523324B (en) | Named entity recognition model training method and device | |
CN111611488B (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
CN114546486A (en) | Method and device for recommending instruction to user, storage medium and electronic device | |
CN113379045B (en) | Data enhancement method and device | |
CN109741818A (en) | Resource allocation management method and device are intervened in medical inferior health based on artificial intelligence | |
CN111191133B (en) | Service search processing method, device and equipment | |
CN110705646A (en) | Mobile equipment streaming data identification method based on model dynamic update | |
CN112115372B (en) | Parking lot recommendation method and device | |
CN111814044A (en) | Recommendation method and device, terminal equipment and storage medium | |
CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
CN110442614A (en) | Searching method and device, electronic equipment, the storage medium of metadata | |
CN115795156A (en) | Material recall and neural network training method, device, equipment and storage medium | |
CN114219663A (en) | Product recommendation method and device, computer equipment and storage medium | |
CN112765479B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
CN110610206A (en) | Image vulgar attribution identification method, device and equipment | |
CN111178925A (en) | User portrait attribute prediction method, device, server and computer readable medium | |
CN113222170B (en) | Intelligent algorithm and model for AI collaborative service platform of Internet of things | |
CN114417944B (en) | Recognition model training method and device, and user abnormal behavior recognition method and device | |
CN109583453A (en) | The recognition methods of image and device, the recognition methods of data, terminal | |
KR102266151B1 (en) | Artificial intelligence-based method of providing consumer preference through voting platform | |
CN116958608A (en) | Method, device, equipment, medium and program product for updating object recognition model |
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 |