CN106126591A - Music data recommends method and system - Google Patents
Music data recommends method and system Download PDFInfo
- Publication number
- CN106126591A CN106126591A CN201610446374.5A CN201610446374A CN106126591A CN 106126591 A CN106126591 A CN 106126591A CN 201610446374 A CN201610446374 A CN 201610446374A CN 106126591 A CN106126591 A CN 106126591A
- Authority
- CN
- China
- Prior art keywords
- data
- context
- project
- user
- music 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000008878 coupling Effects 0.000 claims abstract description 27
- 238000010168 coupling process Methods 0.000 claims abstract description 27
- 238000005859 coupling reaction Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims description 31
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000008447 perception Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 230000036651 mood Effects 0.000 description 6
- 241000394440 Viola arvensis Species 0.000 description 2
- 235000004031 Viola x wittrockiana Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 206010037180 Psychiatric symptoms Diseases 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000000567 combustion gas Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 208000035824 paresthesia Diseases 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of music data to recommend method and system, gather environment surrounding automobile data and motoring condition data, according to environment surrounding automobile data and motoring condition data, from preset musical data base, select the music data of coupling, push the music data found.Whole process, it is considered to environment surrounding automobile data and motoring condition data, data based on these applied environments are searched from preset musical data and recommend to be suitable for current scene music data.
Description
Technical field
The present invention relates to data recommendation technical field, particularly relate to music data and recommend method and system.
Background technology
At present, in order to meet the life requirement of people, increasing people needs long-duration driving automobile.Such as passenger on long-distance routes
Shipping driver, city bus driver etc..On the one hand automobile of driving over a long distance consumes a large amount of muscle power, on the other hand consumes the spirit of people
Power, fatigue, mood are irritated easily to make people feel.
For above-mentioned situation, current automobile is typically all equipped with entertainment systems, after the leisure, automatically can recommend one
A little music datas, allow driver keep joyful mood.
General entertainment systems is the broadcasting music data that passive response user selects, or based on historical record data
Recommend music data.And driver is likely to be due to the factor such as road conditions, surrounding in actual driving procedure and can be in different
Mood states, if simple employing recommends music data to be cannot to realize accurately recommending to be suitable for current scene music based on historical data
Data.
Summary of the invention
Based on this, it is necessary to recommend method cannot accurately recommend to be suitable for current scene music data for general music data
Problem, it is provided that a kind of can accurately recommend be suitable for current scene music data method and system.
A kind of music data recommends method, including step:
Gather environment surrounding automobile data and motoring condition data;
According to environment surrounding automobile data and motoring condition data, from preset musical data base, select coupling
Music data;
Push the music data found.
A kind of music data commending system, including:
Data acquisition module, is used for gathering environment surrounding automobile data and motoring condition data;
Matching module, for according to environment surrounding automobile data and motoring condition data, from preset musical data
Storehouse selects the music data of coupling;
Pushing module, for pushing the music data found.
Music data of the present invention recommends method and system, gathers environment surrounding automobile data and motoring condition number
According to, according to environment surrounding automobile data and motoring condition data, from preset musical data base, select the music of coupling
Data, push the music data found.Whole process, it is considered to environment surrounding automobile data and motoring condition data, base
Data in these applied environments are searched from preset musical data and recommend to be suitable for current scene music data.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that music data of the present invention recommends first embodiment of method;
Fig. 2 is the schematic flow sheet that music data of the present invention recommends second embodiment of method;
Fig. 3 is the structural representation of first embodiment of music data commending system of the present invention;
Fig. 4 is the structural representation of second embodiment of music data commending system of the present invention.
Detailed description of the invention
As it is shown in figure 1, a kind of music data recommends method, including step:
S200: gather environment surrounding automobile data and motoring condition data.
Environment surrounding automobile and motoring condition data can pass through OBD, and (On-Board Diagnostic vehicle-mounted examines
Disconnected system) acquisition module obtains the data of automobile ECU (Electronic Control Unit, car running computer) and is installed on vapour
Sensor on car realizes.Specifically, environment surrounding automobile data can include temperature and humidity, motoring condition number
According to including the data such as car speed and acceleration.Temperature and humidity can affect the mood of driver, such as higher when temperature
And humidity higher time (summer had just rained sunny when maybe will rain) driver paraesthesia sultry, heart can be more tired
Hot-tempered, at this moment need to recommend to allow the music data of driver's heartsease, such as light music etc., when the temperature is low (winter) driver
May feel that cold, heart may feel that loneliness, boring, at this moment need to recommend cheerful and light-hearted lively music data.Car speed with
Acceleration can affect the mood of driver equally, when car speed is relatively low, and during frequent acceleration-deceleration (acceleration is often), and table
Bright it be currently in one and compare situation about blocking up, at this moment need also exist for recommending allowing the music data of driver's heartsease.In reality
In the application of border, temperature data can be by being installed on the temperature sensor collection of automobile, and humidity can be by being installed on automobile
Humidity sensor gathers, and speed and acceleration can be gathered by the OBD being inserted on automobile OBD interface.Non-essential, can be right
These data buffer storages collected on OBD are to terminal unit, it can in addition contain read vehicle trouble by vehicle diagnosing system
Information, distance, vehicle condition and combustion gas mileage etc..So can additionally provide the user maintenance, termination of risk remind,
Roadside assistance service and provide the user maintenance, termination of risk is reminded and the service such as roadside assistance service.
S400: according to environment surrounding automobile data and motoring condition data, selects from preset musical data base
The music data of coupling.
Preset musical data base is the data base built in advance, can store a large amount of music data in this data base,
We based on step S200 gather environmental data and transport condition data, in this data base search coupling current application environment
Music data.Specifically, preset musical data base can also store applied environment classification pass corresponding with music data
Series of tables, such as different temperature, humidity, car speed and acceleration can be drawn respectively be set to different classes of, inhomogeneity
Type corresponding different music data in advance thus build above-mentioned corresponding relation list, then this corresponding relation list is stored to default sound
In happy data base, non-essential, big data analysing method can be used about this category division and data analysis and combine
Historical empirical data obtains.
It addition, wherein in an embodiment, can be according to environment surrounding automobile data and motoring condition number
According to, use context-aware commending system, and model based on Gaussian process selects the sound of coupling from preset musical data base
Happy data.
The two-dimentional commending system of general commending system model essentially " user items ", i.e. " user * project=grading etc.
Level (recommendation grade) ", use context-aware commending system at the present embodiment, by above-mentioned general commending system model extension be
Comprise multidimensional the scoring utility models, i.e. " user's * project * contextual information=opinion rating (recommendation etc. of multiple contextual information
Level) " wherein contextual information can comprise the information of various dimensions, i.e. directly integrate the pass of contextual information and user items
System, directly interacts (strong coupling) and can obtain stochastic variable set between threes two.Gaussian process refer to one group random
The set of variable, arbitrary finite the stochastic variable inside this set all obeys Joint Gaussian distribution.Based on Gaussian process
The result of model can obtain the music data that grading system is the highest from preset musical data base, i.e. obtains the music number of coupling
According to.In order to improve the accuracy rate of model, need to use OBD and collect the historical data of ECU as history data set, also solve to push away
The problem recommending the cold start-up that algorithm exists.
S600: push the music data found.
The music data of acquisition is pushed to intelligent terminal's (smart mobile phone) that driver carries with, plays this music number
Joyful mood is brought according to driver.Non-essential, while playing music, it is also possible to obtain virtual scene data, will
Virtual scene data-pushing is to augmented reality device (AR), and such user may be at enjoying beautiful music in virtual scene,
Bring good Consumer's Experience.
Music data of the present invention recommends method, gathers environment surrounding automobile data and motoring condition data, according to
Environment surrounding automobile data and motoring condition data, select the music data of coupling from preset musical data base, push away
Send the music data found.Whole process, it is considered to environment surrounding automobile data and motoring condition data, should based on these
Search from preset musical data by the data of environment and recommend to be suitable for current scene music data.
As in figure 2 it is shown, wherein in an embodiment, step S400 includes:
S410: according to environment surrounding automobile data and motoring condition data, obtains context.
Context is any information for describing entity state.Specifically, here, entity state refers to step
In S200 obtain environment surrounding automobile data and motoring condition data, further for, entity state here
The object of intercorrelation including temperature, humidity, speed and acceleration etc. and between user and project.Because user is to project (sound
Happy data) preference ordering often with context-sensitive system.These information can include temperature, humidity, speed and acceleration etc.
And the object (including user and application program itself) of intercorrelation between user and application program.Because inclined to project of user
The most often with context-sensitive system.
S420: based on context perception commending system, builds context, user and project three-dimensional scoring utility models.
Specifically, project refers to music data to be recommended, such as, be " China's heart " song when music data to be recommended
Qu Shi, project is song " China's heart ".Here use context-aware commending system, build as " user's * project * is upper and lower
Literary composition information=opinion rating " the three-dimensional scoring utility models comprising multiple contextual information.
S430: by context, user and project three-dimensional scoring utility models, integrate context, user and project
Corresponding relation.
Directly integrate the relation of contextual information and user items, between threes two, directly interact (strong coupling
Close), integrate and obtain context, user and project corresponding relation.
S440: based on context, user and project corresponding relation, model based on Gaussian process, obtain project effectiveness
Function.
Model based on Gaussian process, sets up a kind of nonlinear matrix disassembling method Gaussian process disassembler, makes
With linear combination, the hidden factor of user items context is interacted.Specifically, above-mentioned interaction specifically includes
Following steps: first, based on latent factor model method, are expressed as potential d Wei Te by described user, project and context
Levy vector Vi,Vj,Vc1,Vc2,...,VcM, wherein, i is user, and j is project, c context condition, and M is described context condition
Number;Afterwards, by potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcMTiling is converted into context, user and project
D dimensional feature vector t (j, c)=[Vi T,Vj T,Vc1 T,Vc2 T...VcM T]T, c=(c1,c2,...,cM), wherein, D=(M+1) d, T
For vector calculation;Finally, obtain customer-centric, user i effectiveness to project j in the case of context condition c
Function fi(t(j,c))。
S450: according to project utility function, select the music data of coupling from preset musical data base.
According to the project utility function obtained in step S440, calculate the evaluation result of each project, choose evaluation knot
The music data of fruit optimum is as the music data of coupling.Such as according to the project utility function in step S440, it is calculated
Playing " China's heart " this project of song scoring under current application environment is A, must be calculated under current application environment broadcasting phase
The scoring of this project of sound video is B, and when A is higher than B, will select " China's heart " song is music data, when B is higher than A, and will choosing
Take the music data that this cross-talk video is coupling.More particularly, we can carry out prioritization for evaluation result, choosing
Take the music data that the highest project of priority is coupling.
Realize process for further explain in detail above-mentioned steps S440, rigorous mathematical formulae mode will be used below,
In an introduction embodiment wherein, the content that step S440 includes.
Model based on Gaussian process, establishes a kind of nonlinear matrix disassembling method Gaussian process disassembler,
Use linear combination that the hidden factor of user items context is interacted.APP on user's recommending mobile phone
In (Application, application program), user collects U={user1, user2, user3 ..}, the set V={A1 of mobile phone A PP,
A2, A3 ... }, the information that context is the various dimensions such as temperature, humidity, speed and acceleration that user is current, therefore we can
To use C1, C2, C3, C4 etc. represent contextual information respectively, such as C1={10 °, 20 °, 30 ° }, C2={40%, 60%,
80%}, C3={40m/s, 60m/s, 80m/s}, C4={10m/s2, 20m/s2, 30m/s2}.Observe sample and can use many tuples
It is expressed as U*V*C*R, such as: (user1, A1, (10 °, 40%, 40m/s, 10m/s2), 4), (user2, A3, (30 °, 80%,
60m/s, 20m/s2), 11), wherein, in above-mentioned two set, last figure place 4 and 11 is respectively digit score result.Based on latent
In the method for factor model, the most respectively by user, project, context is expressed as potential d dimensional feature vector Vi,Vj,Vc1,
Vc2,...,VcM.(project, context) tiling is converted into D dimensional feature vector,
D=(M+1) d, t (j, c)=[Vi T,Vj T,Vc1 T,Vc2 T...VcM T]T, c=(c1,c2,...,cM)
T is vector calculation, so that by observation vector function t, (j c) becomes column vector from row vector.In with user being
The heart, user i evaluation expression to project j in the case of context condition is c is (utility function): fi(t(j,c))。
Gaussian process refers to the set of one group of stochastic variable, and arbitrary finite the stochastic variable inside this set all takes
From Joint Gaussian distribution.Gauss distribution is determined by mean μ and covariance X completely, and Gaussian process (GP) is completely by mean value function m
(x) and covariance function k (x, x ';θ) determine.Such as,It is a set with N number of vector, real-valued functionMeet Multi-dimensional Gaussian distribution p (f | X)=N (f;M, k) so claiming f (x) is a Gaussian process, f (x)
~GP (m (x), k (x, x ';θ)), wherein,For mean value function, Kn,n=k (xn,xn,;θ) K is covariance letter
Number, Radial basis kernel function is:At Gaussian process disassembler (GPFM)
In, make xiRepresent user i all of hidden factor expression observation vector t (j, c), yiRepresent corresponding value of utility, then f ↓ i (x)
Obey Gaussian process, i.e.
Therefore, the prior distribution of all f ↓ i (x) is
Actual observed value yizThere is Gaussian noise, therefore can be modeled as Gaussian distributed
p(yiz|fi(xz),σi)=N (y;fi(xz),σi 2)
The likelihood function of the most complete all observed quantities is
During above-mentioned, the mean value function of Gaussian process is assumed to be 0 by us always.In view of in real life,
The scoring slackness of different users has certain deflection, therefore adds amount of bias in utility function
Therefore, by the average in the prior distribution of fi plus after amount of bias
Model solution and training: use Joint Distribution probability to solve marginal probability distribution
p(y|X,Xbias, θ, σ) and=p (y | f, σ) p (y | X, Xbias,θ)
Respectively substitute into y and f probability distribution obtain p (y | X, Xbias, θ, σ), after then seeking logarithm, obtain-log p (y).Optimize
Variable is U={X, Xbias,θ,σ}.Use stochastic gradient descent method to be trained, minimize function-log p (y)
U(n+1)=Un+ Δ n@Δ n=h Δ (n-1) ad log N (yi,mi,Kyi)/(dUn)
Use Gaussian process to return (GSR) and be predicted distribution, the hidden factor vector x of the observed quantity of a given test*
=t (j*,c*), then its prediction utility function fi(x*) necessarily meet p (f (x*)i|Xi,θi,yi)=N (μ*,s*)。
As it is shown on figure 3, a kind of music data commending system, including:
Data acquisition module 200, is used for gathering environment surrounding automobile data and motoring condition data;
Matching module 400, for according to environment surrounding automobile data and motoring condition data, from preset musical number
According to the music data selecting coupling in storehouse;
Pushing module 600, for pushing the music data found.
Music data commending system of the present invention, data acquisition module 200 gathers environment surrounding automobile data and garage
Sailing status data, matching module 400 is according to environment surrounding automobile data and motoring condition data, from preset musical data
Selecting the music data of coupling in storehouse, pushing module 600 pushes the music data found.Whole process, it is considered to motor vehicle environment
Environmental data and motoring condition data, data based on these applied environments are searched from preset musical data and recommend to fit
Close current scene music data.
Wherein in an embodiment, matching module 400 is specifically for according to environment surrounding automobile data and garage
Sail status data, use context-aware commending system, and model based on Gaussian process selects from preset musical data base
The music data of coupling.
As shown in Figure 4, wherein in an embodiment, matching module 400 includes:
Context acquiring unit 410, is used for according to environment surrounding automobile data and motoring condition data, in acquisition
Hereafter.
Model construction unit 420, for based on context perception commending system, builds context, user and project three
Dimension scoring utility models.
Integral unit 430, for by context, user and project three-dimensional scoring utility models, integrating context, use
Family and project corresponding relation.
Evaluation function acquiring unit 440, for based on context, user and project corresponding relation, based on Gaussian process
Model, obtain project utility function.
Matching unit 450, for according to project utility function, selecting the music number of coupling from preset musical data base
According to.
Wherein in an embodiment, evaluation function acquiring unit 440 includes:
First eigenvector acquiring unit, for based on latent factor model method, by described user, project and up and down
Literary composition is expressed as potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcM, wherein, i is user, and j is project, c context condition,
M is the number of described context condition.
Second feature vector acquiring unit, for by potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcMTiling turns
Turn to D dimensional feature vector t (j, c)=[V of context, user and projecti T,Vj T,Vc1 T,Vc2 T...VcM T]T, c=(c1,
c2,...,cM), wherein, D=(M+1) d.
Function acquiring unit, is used for obtaining customer-centric, user i in the case of context condition c to project j
Utility function.
Wherein in an embodiment, environment surrounding automobile data include temperature and humidity, motoring condition packet
Include speed and acceleration.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes more concrete and detailed, but also
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that, come for those of ordinary skill in the art
Saying, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement, these broadly fall into the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. a music data recommends method, it is characterised in that include step:
Gather environment surrounding automobile data and motoring condition data;
According to described environment surrounding automobile data and motoring condition data, from preset musical data base, select coupling
Music data;
Push the music data found.
Music data the most according to claim 1 recommends method, it is characterised in that described according to described environment surrounding automobile
Data and motoring condition data, select the step of the music data of coupling to include from preset musical data base:
According to described environment surrounding automobile data and motoring condition data, use context-aware commending system, and base
Model in Gaussian process selects the music data of coupling from preset musical data base.
Music data the most according to claim 2 recommends method, it is characterised in that described according to described environment surrounding automobile
Data and motoring condition data, use context-aware commending system, and model based on Gaussian process be from default sound
The step selecting the music data of coupling in happy data base includes:
According to described environment surrounding automobile data and motoring condition data, obtain context;
Based on context perception commending system, builds context, user and project three-dimensional scoring utility models, wherein;
By described context, user and project three-dimensional scoring utility models, integrate context, user and project correspondence and close
System;
According to described context, user and project corresponding relation, model based on Gaussian process, obtain project utility function;
According to described project utility function, from preset musical data base, select the music data of coupling.
Music data the most according to claim 3 recommends method, it is characterised in that described according to described context, user
And project corresponding relation, model based on Gaussian process, the step obtaining project utility function includes:
Based on latent factor model method, described user, project and context are expressed as potential d dimensional feature vector Vi,
Vj,Vc1,Vc2,...,VcM, wherein, i is user, and j is project, c context condition, and M is the number of described context condition;
By described potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcMTiling is converted into the D of context, user and project
Dimensional feature vector t (j, c)=[Vi T,Vj T,Vc1 T,Vc2 T...VcM T]T, c=(c1,c2,...,cM), wherein, D=(M+1) d;
Obtain customer-centric, user i utility function to project j in the case of context condition c.
Music data the most according to claim 1 recommends method, it is characterised in that described environment surrounding automobile data include
Temperature and humidity, described motoring condition data include speed and acceleration.
6. a music data commending system, it is characterised in that including:
Data acquisition module, is used for gathering environment surrounding automobile data and motoring condition data;
Matching module, for according to described environment surrounding automobile data and motoring condition data, from preset musical data
Storehouse selects the music data of coupling;
Pushing module, for pushing the music data found.
Music data commending system the most according to claim 6, it is characterised in that described matching module is specifically for basis
Described environment surrounding automobile data and motoring condition data, use context-aware commending system, and based on Gauss mistake
The model of journey selects the music data of coupling from preset musical data base.
Music data commending system the most according to claim 7, it is characterised in that described matching module includes:
Context acquiring unit, for according to described environment surrounding automobile data and motoring condition data, obtains up and down
Literary composition;
Model construction unit, for based on context perception commending system, builds context, user and project three-dimensional scoring effect
Use model;
Integral unit, for by described context, user and project three-dimensional scoring utility models, integrating context, user
And project corresponding relation;
Evaluation function acquiring unit, for according to described context, user and project corresponding relation, mould based on Gaussian process
Type, obtains project utility function;
Matching unit, for according to described project utility function, selecting the music data of coupling from preset musical data base.
Music data commending system the most according to claim 8, it is characterised in that described evaluation function acquiring unit bag
Include:
First eigenvector acquiring unit, for based on latent factor model method, by described user, project and context table
State as potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcM, wherein, i is user, and j is project, c context condition, and M is
The number of described context condition;
Second feature vector acquiring unit, for by described potential d dimensional feature vector Vi,Vj,Vc1,Vc2,...,VcMTiling turns
Turn to D dimensional feature vector t (j, c)=[V of context, user and projecti T,Vj T,Vc1 T,Vc2 T...VcM T]T, c=(c1,
c2,...,cM), wherein, D=(M+1) d;
Function acquiring unit, is used for obtaining customer-centric, user i effectiveness to project j in the case of context condition c
Function.
Music data commending system the most according to claim 6, it is characterised in that described environment surrounding automobile packet
Including temperature and humidity, described motoring condition data include speed and acceleration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610446374.5A CN106126591B (en) | 2016-06-16 | 2016-06-16 | Music data recommended method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610446374.5A CN106126591B (en) | 2016-06-16 | 2016-06-16 | Music data recommended method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106126591A true CN106126591A (en) | 2016-11-16 |
CN106126591B CN106126591B (en) | 2019-09-20 |
Family
ID=57470040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610446374.5A Active CN106126591B (en) | 2016-06-16 | 2016-06-16 | Music data recommended method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106126591B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107506419A (en) * | 2017-08-16 | 2017-12-22 | 桂林电子科技大学 | A kind of recommendation method based on heterogeneous context-aware |
CN108399928A (en) * | 2017-02-06 | 2018-08-14 | 厦门雅迅网络股份有限公司 | The shuffle method of onboard audio |
CN109325142A (en) * | 2018-09-13 | 2019-02-12 | 上海擎感智能科技有限公司 | A kind of song recommendations method based on vehicle running environment |
CN109885719A (en) * | 2019-01-24 | 2019-06-14 | 广州小鹏汽车科技有限公司 | A kind of song recommendations method, system, terminal and storage medium |
CN110134821A (en) * | 2019-05-06 | 2019-08-16 | 深圳市尼欧科技有限公司 | A kind of accurate method for pushing of intelligent vehicle-carried audio for driving congestion |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982107A (en) * | 2012-11-08 | 2013-03-20 | 北京航空航天大学 | Recommendation system optimization method with information of user and item and context attribute integrated |
CN103870529A (en) * | 2012-12-13 | 2014-06-18 | 现代自动车株式会社 | Music recommendation system and method for vehicle |
CN103970873A (en) * | 2014-05-14 | 2014-08-06 | 中国联合网络通信集团有限公司 | Music recommending method and system |
CN105045865A (en) * | 2015-07-13 | 2015-11-11 | 电子科技大学 | Kernel-based collaborative theme regression tag recommendation method |
CN105160539A (en) * | 2015-06-17 | 2015-12-16 | 南京邮电大学 | Probability matrix decomposition recommendation method |
-
2016
- 2016-06-16 CN CN201610446374.5A patent/CN106126591B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982107A (en) * | 2012-11-08 | 2013-03-20 | 北京航空航天大学 | Recommendation system optimization method with information of user and item and context attribute integrated |
CN103870529A (en) * | 2012-12-13 | 2014-06-18 | 现代自动车株式会社 | Music recommendation system and method for vehicle |
CN103970873A (en) * | 2014-05-14 | 2014-08-06 | 中国联合网络通信集团有限公司 | Music recommending method and system |
CN105160539A (en) * | 2015-06-17 | 2015-12-16 | 南京邮电大学 | Probability matrix decomposition recommendation method |
CN105045865A (en) * | 2015-07-13 | 2015-11-11 | 电子科技大学 | Kernel-based collaborative theme regression tag recommendation method |
Non-Patent Citations (1)
Title |
---|
郭珈辰: "电影推荐算法的研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108399928A (en) * | 2017-02-06 | 2018-08-14 | 厦门雅迅网络股份有限公司 | The shuffle method of onboard audio |
CN108399928B (en) * | 2017-02-06 | 2021-08-31 | 厦门雅迅网络股份有限公司 | Random playing method of vehicle-mounted audio |
CN107506419A (en) * | 2017-08-16 | 2017-12-22 | 桂林电子科技大学 | A kind of recommendation method based on heterogeneous context-aware |
CN107506419B (en) * | 2017-08-16 | 2020-08-04 | 桂林电子科技大学 | Recommendation method based on heterogeneous context sensing |
CN109325142A (en) * | 2018-09-13 | 2019-02-12 | 上海擎感智能科技有限公司 | A kind of song recommendations method based on vehicle running environment |
CN109885719A (en) * | 2019-01-24 | 2019-06-14 | 广州小鹏汽车科技有限公司 | A kind of song recommendations method, system, terminal and storage medium |
CN110134821A (en) * | 2019-05-06 | 2019-08-16 | 深圳市尼欧科技有限公司 | A kind of accurate method for pushing of intelligent vehicle-carried audio for driving congestion |
Also Published As
Publication number | Publication date |
---|---|
CN106126591B (en) | 2019-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106126591B (en) | Music data recommended method and system | |
US9562786B2 (en) | Candidate path recommendation | |
CN109154509A (en) | The user's efficiency improved in route planning using route preferences | |
US20130046466A1 (en) | Selecting a Route to Optimize Fuel Efficiency for a Given Vehicle and a Given Driver | |
DE102014203724A1 (en) | Method and system for selecting navigation routes and providing advertising on the route | |
CN103995804B (en) | Cross-media topic detection method and device based on multimodal information fusion and graph clustering | |
Bader et al. | Context-aware POI recommendations in an automotive scenario using multi-criteria decision making methods | |
Saerens et al. | Assessment of alternative polynomial fuel consumption models for use in intelligent transportation systems applications | |
CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
CN107562947A (en) | A kind of Mobile Space-time perceives the lower dynamic method for establishing model of recommendation service immediately | |
CN109840654A (en) | Analysis method, device, system and the computer equipment of vehicle drive behavior | |
CN107870990A (en) | A kind of automobile recommends method and device | |
DE112020002293T5 (en) | Computer-implemented method and system for recommending content to a user on board a vehicle | |
CN109408710A (en) | Search result optimization method, device, system and storage medium | |
Peng et al. | A driving cycle construction methodology combining k-means clustering and Markov model for urban mixed roads | |
CN110304068A (en) | Acquisition method, device, equipment and the storage medium of running car environmental information | |
US20180197192A1 (en) | Method and device for identifying preferential region of product | |
CN106777169A (en) | A kind of user's trip hobby analysis method based on car networking data | |
CN107577736A (en) | A kind of file recommendation method and system based on BP neural network | |
WO2023109423A1 (en) | Driving mode processing method and apparatus, electronic device, storage medium, and vehicle | |
CA3108517A1 (en) | Comparative ranking system | |
Bera et al. | Identification of priority areas of improvement for small passenger car segment in Indian market | |
CN115221234A (en) | Method and system for portraying user based on power assembly data | |
CN110516823A (en) | A kind of vehicle wisdom maintenance model based on temporal model | |
CN117788224A (en) | 5G+ cloud fusion global travel data management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |