CN105472413B - Method for ordering television channels, system and server - Google Patents
Method for ordering television channels, system and server Download PDFInfo
- Publication number
- CN105472413B CN105472413B CN201510810947.3A CN201510810947A CN105472413B CN 105472413 B CN105472413 B CN 105472413B CN 201510810947 A CN201510810947 A CN 201510810947A CN 105472413 B CN105472413 B CN 105472413B
- Authority
- CN
- China
- Prior art keywords
- channel
- viewing
- server
- information
- weight
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26283—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for associating distribution time parameters to content, e.g. to generate electronic program guide data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
- H04N21/4586—Content update operation triggered locally, e.g. by comparing the version of software modules in a DVB carousel to the version stored locally
Abstract
The invention discloses a kind of method for ordering television channels, system and server, this method includes:Server receives the channel information of multiple television sets, and channel information includes channel number, corresponding first viewing information of channel number;Server is trained according to corresponding first viewing information of the channel number and channel number using multiple linear regression model, and to model coefficient, and weight order function is generated;Server receives the channel sequencing request that television set is sent, and channel sequencing request includes channel designation, corresponding second viewing information of channel;Server calculates the corresponding channel weight value of each channel designation according to channel sequencing request and weight order function;Server is ranked up according to the corresponding channel weight value of each channel, to each channel according to channel weight value from big to small, generates new channel list, and new channel list is returned to television set.Using the present invention, it can be achieved that personalized carries out intelligent sequencing to television channel.
Description
Technical field
The present invention relates to a kind of channel sequencing field more particularly to method for ordering television channels, system and servers.
Background technology
Currently, television set has become the important tool that people entertained or obtained in daily life information.It is common,
The quantity of television channel is very more, such as in CONTINENTAL AREA OF CHINA, television channel has more than 3,000, if user will find and want to see
Channel needs ceaselessly to press remote controler to be transferred to corresponding channel (as traversed entire television channel lists successively), and user
The channel often watched is usually a few, cumbersome, not humane.In the prior art, occur to television channel
The technical solution of sequence is accustomed to according to the viewing of user, provides easy personalized ordering function, existing common sort method
It is as follows:Viewing duration according to television channel in single television set is ranked up television channel, is cut according to television channel
It changes number to be ranked up television channel, be ranked up television channel according to the type of television channel, above-mentioned sort method, arrange
Ordinal number is accustomed to according to the viewing from single television set, and is ranked up using single dimension, and intelligence degree is low, Bu Nengjie
The viewing custom that a variety of dimensional informations accurately reflect user to television channel is closed, and then user can not be facilitated quickly to watch and liked
Program.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
Invention content
The main purpose of the present invention is to provide a kind of method for ordering television channels, system and servers, it is intended to solve existing
Have in technology, television channel sequence intelligence degree is low, cannot accurately reflect user to television channel in conjunction with a variety of dimensional informations
The technical issues of viewing custom.
To achieve the above object, the present invention provides a kind of method for ordering television channels, and this method includes:
Server receives the channel information of multiple television sets, and the channel information includes channel number, channel number correspondence
The first viewing information, first viewing information includes more than two viewing parameters;
The server is according to the channel number and corresponding first viewing information of the channel number, using polynary line
Property regression model, and multiple linear regression model coefficient is trained, generates weight order function;
The server receives the channel sequencing request that television set is sent, the channel sequencing request include channel designation,
Corresponding second viewing information of channel designation, second viewing information include more than two viewing parameters;
The server calculates each channel designation and corresponds to according to channel sequencing request and the weight order function
Channel weight value;
The server according to the corresponding channel weight value of each channel, to each channel according to channel weight value from greatly to
It is small to be ranked up, new channel list is generated, and the new channel list is returned into television set, for the television set according to
The local channel list of new channel list update television set.
Optionally, the server obtains the step of channel information of multiple television sets and includes:
The server receives the channel information that multiple television sets are reported when networking with the server triggers.
Optionally, first viewing information includes viewing duration, switching times, viewing population ages distribution and viewing ground
Area;
The server is according to the channel number and corresponding first viewing information of the channel number, using polynary line
Property regression model, the step of and being trained to multiple linear regression model coefficient, generating weight order function is:
The server is according to the channel number, viewing duration, switching times, viewing population ages distribution and viewing ground
Area is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates weight order function;Institute
Stating multiple linear regression model is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein A1、B1、C1、D1、E1It is constant, X1、
X2、X3、X4It is independent variable.
Optionally, first viewing information includes viewing duration, switching times, viewing population ages distribution and viewing ground
Area;The weight order function includes multiple channel weight subfunctions;
The server is according to the channel number and corresponding first viewing information of the channel number, using polynary line
Property regression model, the step of and being trained to multiple linear regression model coefficient, generating weight order function is:
The server is according to the channel number, viewing duration, switching times, viewing population ages distribution, viewing ground
Area is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates the corresponding of each area
Channel weight subfunction;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3, wherein A2、B2、C2、D2It is
Constant, X1、X2、X3It is independent variable.
Optionally, the channel sequencing request further includes regional belonging to the television set, and second viewing information includes
Watch duration, switching times and viewing population ages' distribution;
The server calculates each channel designation and corresponds to according to channel sequencing request and the weight order function
Channel weight value the step of include:
According to area belonging to the television set, corresponding channel weight subfunction is selected from the weight order function;
The second viewing information in being asked according to the channel sequencing and the selected channel weight subfunction calculate each
The corresponding channel weight value of a channel designation.
In addition, to achieve the above object, the present invention also provides a kind of server, the server includes the first transmitting-receiving mould
Block, the first generation module, the second transceiver module, computing module and the second generation module, wherein:
First transceiver module, the channel information for receiving multiple television sets, the channel information include that channel is compiled
Number, corresponding first viewing information of channel number;First viewing information includes more than two viewing parameters;
First generation module, for being believed according to corresponding first viewing of the channel number and the channel number
Breath, is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates weight order function;
Second transceiver module, the channel sequencing request for receiving television set transmission, the channel sequencing request bag
Corresponding second viewing information of channel designation, channel designation is included, second viewing information includes more than two viewing parameters;
The computing module, for according to channel sequencing request and the weight order function, calculating each channel
The corresponding channel weight value of title;
Second generation module is used for according to the corresponding channel weight value of each channel, to each channel according to channel
Weighted value is ranked up from big to small, generates new channel list;
Second transceiver module is additionally operable to the new channel list returning to television set, for the television set according to
The local channel list of the new channel list update television set.
Optionally, first transceiver module is additionally operable to receive multiple television sets when networking with the server triggers
The channel information reported.
Optionally, first viewing information includes viewing duration, switching times, viewing population ages distribution and viewing ground
Area;
First generation module, be additionally operable to the server according to the channel number, viewing duration, switching times,
Population ages' distribution and viewing area are watched, is carried out using multiple linear regression model, and to multiple linear regression model coefficient
Training generates weight order function;The multiple linear regression model is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein
A1、B1、C1、D1、E1It is constant, X1、X2、X3、X4It is independent variable.
Optionally, first viewing information includes viewing duration, switching times, viewing population ages distribution and sees
See area;The weight order function includes multiple channel weight subfunctions;
First generation module is additionally operable to according to the channel number, viewing duration, switching times, viewing crowd year
Age is distributed and viewing area, is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates each
The corresponding channel weight subfunction in a area;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3,
In, A2、B2、C2、D2It is constant, X1、X2、X3It is independent variable.
Optionally, the channel sequencing request further includes regional belonging to the television set, and second viewing information includes
Watch duration, switching times and viewing population ages' distribution;
The computing module includes:
Searching unit, for according to area belonging to the television set, corresponding frequency to be selected from the weight order function
Road weight subfunction;
Computing unit, the second viewing information in being used to be asked according to the channel sequencing and the selected channel weight
Subfunction calculates the corresponding channel weight value of each channel designation.
In addition, to achieve the above object, the present invention also provides a kind of television channel ordering systems, and the system comprises above-mentioned
Server, and multiple television sets for being connect with the server.
Method for ordering television channels, system and the server of the present invention, this method include:Server receives multiple television sets
Channel information, which includes channel number, corresponding first viewing information of channel number, the first viewing information packet
Include more than two viewing parameters;The server is used according to the channel number the first viewing information corresponding with the channel number
Multiple linear regression model, and multiple linear regression model coefficient is trained, generate weight order function;The server connects
The channel sequencing request that television set is sent is received, channel sequencing request includes channel designation, corresponding second viewing of channel designation
Information, second viewing information include more than two viewing parameters;The server is asked according to the channel sequencing and the sequence is weighed
Weight function, calculates the corresponding channel weight value of each channel designation;The server according to the corresponding channel weight value of each channel,
Each channel is ranked up from big to small according to channel weight value, generates new channel list, and the new channel list is returned
To television set, for the television set according to the local channel list of the new channel list update television set;Sortord is intelligent, can
The interested channel designation of user is accurately come into front, it is user-friendly to achieve the purpose that, improve user experience.
Description of the drawings
Fig. 1 is the flow diagram of the first embodiment of method for ordering television channels of the present invention;
Fig. 2 is the flow diagram of the second embodiment of method for ordering television channels of the present invention;
Fig. 3 is the flow diagram of the second embodiment of method for ordering television channels of the present invention;
Fig. 4 is the flow diagram of the fourth embodiment of method for ordering television channels of the present invention;
Fig. 5 is the structural schematic diagram of the first embodiment of server of the present invention;
Fig. 6 is the structural schematic diagram of the second embodiment of server of the present invention;
Fig. 7 is the structural schematic diagram of an embodiment of television channel ordering system of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the flow diagram of the first embodiment of method for ordering television channels of the present invention, this method packet
It includes:
S10, server receive the channel information of multiple television sets, which includes that channel number, channel are corresponding
First viewing information, first viewing information include more than two viewing parameters.
The server establishes wired or wireless connection with multiple television sets, as the server can be with multiple television sets by having
Gauze network or wireless network (such as wifi), which are established, to be wirelessly connected.
The channel information includes channel number, corresponding first viewing information of channel number, television set source type etc., is somebody's turn to do
Channel number includes the channel number of all channels on television set, which may also include channel designation.First sight
See that information includes the viewing parameters such as viewing duration, switching times, viewing area, viewing population ages distribution, viewing time information
In two or arbitrary multinomial.Such as, the channel information obtained from television set A is as shown in Table 1, the frequency obtained from television set B
Road information is as shown in Table 2.
Table one:
Table two:
The viewing population ages in the first viewing information in the channel information are distributed to be indicated with numerical value, according to preset rules
It defines each viewing population ages and is distributed corresponding numerical value, if numerical value 1 corresponds to 0 to 10 years old, 2 years old correspondence of numerical value 10 years old to 20 years old,
Numerical value 3 corresponds to 20 years old to 30 years old, and so on, numerical value 15 corresponds to 140 years old to 150 years old etc.;The first viewing in the channel information
Viewing area in information is also indicated with numerical value, and (common, viewing is obtained according to the Chinese phonetic alphabet natural ordering in viewing area
Area is city-level area), such as when viewing area is Shenzhen, the Shenzhen is in all viewing areas according to Chinese phonetic alphabet nature
It is ordered as the 200th, then the corresponding numerical value in the Shenzhen is 200;When viewing area is Guangzhou, Guangzhou is in all viewing areas
It is the 100th according to Chinese phonetic alphabet natural ordering, then the corresponding numerical value in the Guangzhou is 100.
In one embodiment, which receives the channel letter that multiple television sets are reported when networking with the server triggers
Breath.The multiple television sets being connect with the server actively send channel when networking with the server triggers to the server
Information.Optionally, the viewing time information in first viewing information is that user currently joins with server triggers in the television set
Net and the last viewing time information between server triggers networking of the television set, the viewing time information include at least one
A viewing start time and viewing finish time can obtain viewing duration by the viewing time information, specifically, viewing is tied
The beam moment with upper one viewing start time subtract each other, obtain viewing the period of the day from 11 p.m. to 1 a.m it is long, by each viewing period of the day from 11 p.m. to 1 a.m length be added obtain watch when
It is long;Switching times can be obtained by the viewing time information, specifically, when calculating switching times, can be believed according to viewing time
It watches the number of start time in breath to obtain, as there is 5 viewing start times in the viewing information, then switching times are 5.
In one embodiment, server can send to obtain to multiple television sets and ask simultaneously according to prefixed time interval timing
Ask, to obtain the channel information of multiple television sets, if the prefixed time interval be 30 days, then the server with every 30 days be one
Period periodically sends to multiple television sets and obtains request, to obtain the channel information of multiple television sets.First viewing information is
User nearest 1 first preset time viewing information, as first preset time be 7 days.In this step, server is also
Obtaining the usage time of each television set, (usage time typically refers to user and buys back the usage time after television set, such as exists
On January 1st, 2014 is bought back, then on January 15th, 2014, the usage time of the television set is 15 days), when the use of the television set
When time is less than the first preset time, then server gives up the channel information got from the television set.The first viewing letter
A length of user switches time in first preset time to the viewing duration of some channel in first viewing information when being watched in breath
Number is for user in first preset time to the switching times of some channel.
In this step, server can obtain the channel information of television sets more as possible, i.e. the server is got as possible
More channel information samples.
S11, the server are according to the channel number the first viewing information corresponding with the channel number, using multiple linear
Regression model, and multiple linear regression model coefficient is trained, generate weight order function.
The server according to the channel number the first viewing information corresponding with the channel number, using the channel number as
Dependent variable, corresponding first viewing information of the channel number is as independent variable, using multiple linear regression model, and to polynary line
Property regression model coefficient be trained, generate weight order function, that is, be collected into the big of channel number and the first viewing information
On data set, multiple linear regression model coefficient is trained, obtains the corresponding system of each independent variable in weight order function
Number.Preferably, machine learning frame scikit-learn, which can be used, carries out parameter training, weight order function is generated.The sequence
Weighting function is Multiple Linear Regression Function.
S12, the server receive television set send channel sequencing request, the channel sequencing request include channel designation,
Corresponding second viewing information of channel designation, second viewing information include more than two viewing parameters.
Channel sequencing request includes channel designation, corresponding second viewing information of channel designation, channel number etc., the frequency
Road title includes the channel designation of all channels on television set.Second viewing information includes viewing duration, switching times, sight
See two or arbitrary multinomial in the viewing parameters such as area, viewing population ages' distribution.Second viewing information is user most
The viewing information of nearly 1 second preset time, if second preset time is 7 days.Such as, the channel sequencing received from television set F
Request is as shown in Table 3.
Table three:
In one embodiment, television set just established with server connect when, from trend server send channel sequencing ask
It asks.
In another embodiment, television set can also be in the channel sequencing instruction for receiving user's transmission, to server
Send channel sequencing request.User can send channel sequencing instruction, e.g., pressing by pressing the button on remote controler to television set
Menu key on remote controler opens corresponding menu, and channel sequencing option is got in menu, is then chosen, and is sent out to television set
Channel sequencing is sent to instruct;Alternatively, user directly presses the specific keys on remote controler, channel sequencing instruction is sent to television set.
S13, the server is asked according to the channel sequencing and the weight order function, and it is corresponding to calculate each channel designation
Channel weight value.
The server calculates the corresponding channel weight value of each channel designation in channel sequencing request, by channel designation pair
The second viewing information answered is updated to weight order function, obtains channel weight value.Such as in one embodiment, weight order function
For:H=a+b*X1+c*X2+d*X3+e*X4, wherein:A, b, c, d, e are constant, X1Indicate viewing duration, X2Indicate switching times,
X3Indicate viewing population ages' distribution, X4Indicate viewing area;Channel sequencing request in channel designation be CCTV1, CCTV1 pairs
A length of t1, switching times n1, viewing population ages are distributed as m1 and viewing area when viewing in the second viewing information answered
For z1, t1, n1, m1 and z1 are substituted into H=a+b*X1+c*X2+d*X3+e*X4, h=a+b*t1+c*n1+d*m1+e*z1 is obtained,
Calculate the corresponding channel weight values of CCTV1;Channel designation in channel sequencing request is CCTV2, and CCTV2 corresponding second is seen
It is z2 that a length of t2 when the viewing seen in information, switching times n2, viewing population ages, which are distributed as m2 and viewing area, by t2,
N2, m2 and z2 substitute into H=a+b*X1+c*X2+d*X3+e*X4, h=a+b*t2+c*n2+d*m2+e*z2 is obtained, CCTV2 is calculated
Corresponding channel weight value;And so on, calculate the corresponding channel weight value of each channel designation.
S14, the server are according to the corresponding channel weight value of each channel, to each channel according to channel weight value from big
It is ranked up to small, new channel list is generated, and the new channel list is returned into television set, for the television set according to the new frequency
The local channel list of road list update television set.
In this step, server is according to the corresponding channel weight value of each channel, from big to small according to channel weight value
It is ranked up, in front by the big channel bank of channel weight value, channel weight is worth small channel bank later, generates new channel row
Table, the new channel list include channel and new channel number, and the channel corresponding new channel number for coming first is 1, come the
The corresponding new channel number of two channel is 2, and so on, to each channel into line renumbering.Optionally, which arranges
Table can also include the corresponding channel weight value of channel.The new channel list is as shown in Table 4.
Table four:
New channel is numbered | Channel |
1 | CCTV1 |
2 | CCTV6 |
3 | CCTV12 |
4 | CCTV10 |
…… | …… |
After the television set receives the new channel list, arranged according to the local channel of the new channel list update television set
Table so that the sorting television channels are more intelligent.
Using above-described embodiment, server receives the channel information of multiple television sets, the channel information include channel number,
Corresponding first viewing information of channel number, first viewing information include more than two viewing parameters;The server is according to this
Channel number the first viewing information corresponding with the channel number, the multiple linear regression model of use generate weight order letter
Number;The server receives the channel sequencing request that television set is sent, and channel sequencing request includes channel designation, channel designation pair
The second viewing information answered, second viewing information include more than two viewing parameters;The server is asked according to the channel sequencing
It sums the weight order function, calculates the corresponding channel weight value of each channel designation;The server is corresponded to according to each channel
Channel weight value, each channel is ranked up from big to small according to channel weight value, generates new channel list, and this is new
Channel list returns to television set, for the television set according to the local channel list of the new channel list update television set;Sequence
Mode is intelligent, can the interested channel designation of user accurately be come front, user-friendly to achieve the purpose that,
Improve user experience.
It is the flow diagram of the second embodiment of method for ordering television channels of the present invention with reference to Fig. 2, Fig. 2.
Based on the first embodiment of above-mentioned method for ordering television channels, which includes viewing duration, switching
Number, viewing population ages distribution and viewing area;
The server is according to the channel number the first viewing information corresponding with the channel number, using multiple linear regression
Model, and the step of being trained to multiple linear regression model coefficient, generating weight order function is:
S111, the server are according to the channel number, viewing duration, switching times, viewing population ages distribution and viewing
Area is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates weight order function;
The multiple linear regression model is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein A1、B1、C1、D1、E1It is constant, X1、
X2、X3、X4It is independent variable.
The server using the channel number as dependent variable, will viewing duration, switching times, viewing population ages distribution and
Viewing area is used as independent variable, is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates
Weight order function, i.e., on the large data sets for being collected into channel number and the first viewing information, to multiple linear regression model
Coefficient (A1、B1、C1、D1、E1) be trained, the corresponding coefficient of each independent variable in weight order function is obtained, weight is such as generated
It is b that independent variable, which is the corresponding coefficient of viewing duration, in function1, independent variable is that the corresponding coefficient of switching times is c1, independent variable is to see
It is d to see that population ages are distributed corresponding coefficient1, independent variable is that the corresponding coefficient in viewing area is e1, which is four
First linear regression function;Such as, which is indicated by following formula:H=a1+b1*X1+c1*X2+d1*X3+e1*X4,
Wherein:a1、b1、c1、d1、e1It is constant, X1Indicate viewing duration, X2Indicate switching times, X3Indicate viewing population ages' distribution,
X4Indicate viewing area.
It is the flow diagram of the 3rd embodiment of method for ordering television channels of the present invention with reference to Fig. 3, Fig. 3.
Based on the first embodiment of above-mentioned method for ordering television channels, which includes viewing duration, switching
Number, viewing population ages distribution and viewing area;Channel sequencing request further includes regional belonging to the television set, second sight
See that information includes viewing duration, switching times and viewing population ages' distribution;
The server is according to the channel number the first viewing information corresponding with the channel number, using multiple linear regression
Model, and the step of being trained to multiple linear regression model coefficient, generating weight order function is:
S112, the server are according to the channel number, viewing duration, switching times, viewing population ages distribution and viewing
Area is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates the correspondence in each area
Channel weight subfunction;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3, wherein A2、B2、C2、D2It is
Constant, X1、X2、X3It is independent variable.
The server is asked according to the channel sequencing and the weight order function, calculates the corresponding channel of each channel designation
The step of weighted value includes:
S131, according to regional belonging to the television set, corresponding channel weight subfunction is selected from the weight order function;
S132, according to the channel sequencing ask in the second viewing information and the selection channel weight subfunction, calculate
The corresponding channel weight value of each channel designation.
The weight order function includes multiple channel weight subfunctions, wherein a channel weight subfunction corresponds to one
Area, this area can or township levels at county level for provincial, city.
In step S112, which first sorts out the channel information of reception, and first in channel information is seen
The viewing area seen in information is identical and/or the regional channel information for belonging to same higher level area of viewing forms a channel information
Then subset is distributed according to channel number, viewing duration, switching times and the viewing population ages in the channel information subset,
Using multiple linear regression model, channel weight subfunction is generated.Such as in one embodiment, the channel information which receives
When being sorted out, the channel information that the viewing area in the first viewing information in channel information is Shenzhen is formed into a channel
The channel information that viewing area in the first viewing information in channel information is Guangzhou is formed a channel letter by information subset
Subset is ceased, the channel information that the viewing area in the first viewing information in channel information is Dongguan is formed into a channel information
Subset;And/or it is the viewing in the first viewing information in channel information is regional for Shenzhen and Guangzhou, the channel information group of Dongguan
At a channel information subset (the upper level area of Shenzhen and Guangzhou and Dongguan is all Guangdong).
The server is according to channel number, viewing duration, switching times and the viewing crowd year in the channel information subset
Age is distributed, and is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates pair in each area
The channel weight subfunction answered be specially:The server, will using the channel number in the channel information subset as dependent variable
Viewing duration, switching times and viewing population ages' distribution in channel information subset are used as independent variable, are returned using multiple linear
Return model, and multiple linear regression model coefficient is trained, generates channel weight subfunction, that is, be collected into channel number
On the large data sets of the first viewing information, to multiple linear regression model coefficient (A2、B2、C2、D2) be trained, it is arranged
The corresponding coefficient of each independent variable in sequence weighting function is that the corresponding coefficient of viewing duration is as generated independent variable in weighting function
b2, independent variable is that the corresponding coefficient of switching times is c2, independent variable is that the corresponding coefficient of viewing population ages' distribution is d2, the frequency
Road weight subfunction is ternary linear regression function;Such as, which is indicated by following formula:H=a2+b2*X1
+c2*X2+d2*X3, wherein:a2、b2、c2、d2It is constant, X1Indicate viewing duration, X2Indicate switching times, X3Indicate viewing crowd
Age distribution.
In step S112, the mapping relations in each area and the channel weight subfunction are also saved.
In step S131, which chooses according to area belonging to the television set from the weight order function
The corresponding channel weight subfunction in area belonging to the television set, specifically, reflecting according to each area and channel weight subfunction
Relationship is penetrated, corresponding channel weight subfunction is obtained.Optionally, when server is according to regional belonging to the television set, not in the row
When choosing regional corresponding channel weight subfunction belonging to the television set in sequence weighting function, then the television set institute is first got
Then the upper level region in possession area is selected according to upper level region regional belonging to the television set in the weight order function
To the corresponding channel weight subfunction in area belonging to the television set, if not choosing corresponding channel weight subfunction yet, according to
Secondary to analogize, continuation is selected according to the upper level region in upper level region regional belonging to the television set, until choosing pair
The channel weight subfunction answered.As in one embodiment, area belonging to the television set is Shenzhen, if the weight order function includes
The corresponding channel weight subfunction in Shenzhen then can directly find the corresponding channel weight subfunction in the Shenzhen, if the sequence is weighed
Weight function does not include the corresponding channel weight subfunction in Shenzhen, then the upper level region for first getting Shenzhen is Guangdong, is then existed
The corresponding channel weight subfunction in Guangdong is selected in weight order function, as the corresponding channel weight in area belonging to the television set
Subfunction.
In step S132, which calculates the corresponding channel weight of each channel designation in channel sequencing request
Viewing duration, switching times and viewing population ages' distribution in corresponding second viewing information of channel designation is updated to by value
The channel weight subfunction of selection, obtains channel weight value.As in one embodiment, which passes through following formula
It indicates:H=a2+b2*X1+c2*X2+d2*X3, wherein:a2、b2、c2、d2It is constant, X1Indicate viewing duration, X2Indicate switching time
Number, X3Indicate that viewing population ages' distribution, the channel designation in channel sequencing request are CCTV1, corresponding second viewings of CCTV1
A length of t1, switching times n1, viewing population ages are distributed as m1 when viewing in information, and t1, n1 and m1 are substituted into H=a2+
b2*X1+c2*X2+d2*X3, obtain h=a2+b2*t1+c2*n1+d2* m1 calculates the corresponding channel weight values of CCTV1.
It is the flow diagram of the fourth embodiment of method for ordering television channels of the present invention, this method packet with reference to Fig. 4, Fig. 4
It includes:
S20, multiple television sets send channel information, the channel information when networking with server triggers, to the server
Including channel number, corresponding first viewing information of channel number;First viewing information includes more than two viewing parameters.
Multiple television set can be established with server by cable network or wireless network (such as wifi) and is wirelessly connected.
The channel information includes channel number, corresponding first viewing information of channel number, television set source type etc., is somebody's turn to do
Channel number includes the channel number of all channels on television set, which may also include channel designation.First sight
See that information includes two or arbitrary watched in the viewing parameters such as duration, switching times, viewing area, viewing population ages' distribution
It is multinomial.The channel information that television set A is sent to server is as shown in Table 1, and television set B is sent to the channel information of server such as
Shown in table two.
The viewing population ages in the first viewing information in the channel information are distributed to be indicated with numerical value, according to preset rules
It defines each viewing population ages and is distributed corresponding numerical value, if numerical value 1 corresponds to 0 to 10 years old, 2 years old correspondence of numerical value 10 years old to 20 years old,
Numerical value 3 corresponds to 20 years old to 30 years old, and so on, numerical value 15 corresponds to 140 years old to 150 years old etc.;The first viewing in the channel information
Viewing area in information is also indicated with numerical value, and (common, viewing is obtained according to the Chinese phonetic alphabet natural ordering in viewing area
Area is city-level area), such as when viewing area is Shenzhen, the Shenzhen is in all viewing areas according to Chinese phonetic alphabet nature
Being ordered as the 200th, then the corresponding numerical value in the Shenzhen is 200,;When viewing area is Guangzhou, Guangzhou is in all viewing areas
According to Chinese phonetic alphabet natural ordering be the 100th, then the corresponding numerical value in the Guangzhou be 100.
Optionally, a length of user currently networks with server triggers in the television set when viewing in first viewing information
With the last viewing duration between server triggers networking of the television set, the switching times in first viewing information are to use
Family television set currently with server triggers networking and the television set on once server triggers network between switching times.
S21, the server receive the channel information that multiple television set is sent.
S22, the server are according to the channel number the first viewing information corresponding with the channel number, using multiple linear
Regression model, and multiple linear regression model coefficient is trained, generate weight order function.
Step S22 is identical as the step S11 in above-described embodiment, and this will not be repeated here.
S23, server receive the channel sequencing request that television set is sent, and channel sequencing request includes channel designation, frequency
Corresponding second viewing information of road title, second viewing information include more than two viewing parameters.
Step S23 is identical as the step S12 in above-described embodiment, and this will not be repeated here.
S24, server is asked according to the channel sequencing and the weight order function, calculates the corresponding frequency of each channel designation
Road weighted value.
Step S24 is identical as the step S13 in above-described embodiment, and this will not be repeated here.
S25, the server are according to the corresponding channel weight value of each channel, to each channel according to channel weight value from big
It is ranked up to small, generates new channel list, and the new channel list is returned into television set.
Step S25 is identical as the step S14 in above-described embodiment, and this will not be repeated here.
S26, the television set receive the new channel list of server return, and according to the new channel list update television set
Local channel list.
After the television set receives the new channel list, arranged according to the local channel of the new channel list update television set
Table so that the sorting television channels are more intelligent.
It is the structural schematic diagram of the first embodiment of server of the present invention with reference to Fig. 5, Fig. 5, which includes first
Transceiver module 11, the first generation module 12, the second transceiver module 13, computing module 14 and the second generation module 15, wherein:
First transceiver module 11, the channel information for receiving multiple television sets, the channel information include channel number,
Corresponding first viewing information of channel number;First viewing information includes more than two viewing parameters;
First generation module 12, for according to the channel number the first viewing information corresponding with the channel number, adopting
With multiple linear regression model, and multiple linear regression model coefficient is trained, generates weight order function;
Second transceiver module 13, the channel sequencing request for receiving television set transmission, channel sequencing request include
Corresponding second viewing information of channel designation, channel designation, second viewing information include more than two viewing parameters;
The computing module 14, for according to channel sequencing request and the weight order function, calculating each channel designation
Corresponding channel weight value;
Second generation module 15 is used for according to the corresponding channel weight value of each channel, to each channel according to channel
Weighted value is ranked up from big to small, generates new channel list;
Second transceiver module 13 is additionally operable to the new channel list returning to television set, new according to this for the television set
Channel list updates the local channel list of television set.
The server 10 establishes wired or wireless connection with multiple television sets, as the server 10 can be logical with multiple television sets
It crosses cable network or wireless network (such as wifi) is established and is wirelessly connected.
The channel information includes channel number, corresponding first viewing information of channel number, television set source type etc., is somebody's turn to do
Channel number includes the channel number of all channels on television set, which may also include channel designation.First sight
See that information includes the viewing parameters such as viewing duration, switching times, viewing area, viewing population ages distribution, viewing time information
In two or arbitrary multinomial.Such as, the channel information obtained from television set A is as shown in Table 1, the frequency obtained from television set B
Road information is as shown in Table 2.
The viewing population ages in the first viewing information in the channel information are distributed to be indicated with numerical value, according to preset rules
It defines each viewing population ages and is distributed corresponding numerical value, if numerical value 1 corresponds to 0 to 10 years old, 2 years old correspondence of numerical value 10 years old to 20 years old,
Numerical value 3 corresponds to 20 years old to 30 years old, and so on, numerical value 15 corresponds to 140 years old to 150 years old etc.;The first viewing in the channel information
Viewing area in information is also indicated with numerical value, and (common, viewing is obtained according to the Chinese phonetic alphabet natural ordering in viewing area
Area is city-level area), such as when viewing area is Shenzhen, the Shenzhen is in all viewing areas according to Chinese phonetic alphabet nature
It is ordered as the 200th, then the corresponding numerical value in the Shenzhen is 200;When viewing area is Guangzhou, Guangzhou is in all viewing areas
It is the 100th according to Chinese phonetic alphabet natural ordering, then the corresponding numerical value in the Guangzhou is 100.
In one embodiment, first transceiver module 11 receive multiple television sets with the server 10 trigger network when on
The channel information of report.The multiple television sets being connect with the server 10 with the server 10 when triggering networking, actively to this
Server 10 sends channel information, and optionally, the viewing time information in first viewing information is that user works as in the television set
It is preceding to trigger networking and the last viewing time information between the triggering networking of server 10 of the television set, the sight with server 10
It sees that temporal information includes at least one viewing start time and viewing finish time, can be watched by the viewing time information
Duration, specifically, will viewing finish time with upper one viewing start time subtract each other, obtain watch the period of the day from 11 p.m. to 1 a.m it is long, by each viewing
Period of the day from 11 p.m. to 1 a.m length, which is added, obtains viewing duration;Switching times can be obtained by the viewing time information, specifically, calculating switching times
When, it can be obtained according to the number of start time is watched in viewing time information, when as there is 5 viewings to start in the viewing information
It carves, then switching times are 5.
In one embodiment, which can send out to multiple television sets simultaneously according to prefixed time interval timing
Acquisition is sent to ask, to obtain the channel information of multiple television sets, if the prefixed time interval is 30 days, then the server 10 is with every
30 days are a cycle, are periodically sent to multiple television sets and obtain request, to obtain the channel information of multiple television sets.This first
Viewing information is viewing information of the user in nearest 1 first preset time, if first preset time is 7 days.First transmitting-receiving
Module 11 also obtains the usage time of each television set (when the usage time typically refers to the use after user buys back television set
Between, such as bought back on January 1st, 2014, then on January 15th, 2014, the usage time of the television set is 15 days), when the TV
When the usage time of machine is less than the first preset time, then first transceiver module 11 will be got from the television set channel information
Give up.A length of user is in first preset time to the viewing duration of some channel when being watched in first viewing information, this
In one viewing information switching times be user in first preset time to the switching times of some channel.
First transceiver module 11 can obtain the channel information of television sets more as possible, i.e. first transceiver module 11 obtains
To channel information samples more as possible.
First generation module 12 is according to the channel number the first viewing information corresponding with the channel number, by the channel
Number is used as dependent variable, and corresponding first viewing information of the channel number is as independent variable, using multiple linear regression model, and
Multiple linear regression model coefficient is trained, weight order function is generated, that is, is being collected into channel number and the first viewing
On the large data sets of information, multiple linear regression model coefficient is trained, obtains each independent variable in weight order function
Corresponding coefficient.Preferably, machine learning frame scikit-learn, which can be used, carries out parameter training, weight order letter is generated
Number.The weight order function is Multiple Linear Regression Function.
Channel sequencing request includes channel designation, corresponding second viewing information of channel designation, channel number etc., the frequency
Road title includes the channel designation of all channels on television set.Second viewing information includes viewing duration, switching times, sight
See two or arbitrary multinomial in the viewing parameters such as area, viewing population ages' distribution.Second viewing information is user most
The viewing information of nearly 1 second preset time, if second preset time is 7 days.Such as, the channel sequencing received from television set F
Request is as shown in Table 3.
In one embodiment, television set sends channel bank when just establishing connection with server 10 from trend server 10
Sequence is asked.
In another embodiment, television set can also be in the channel sequencing instruction for receiving user's transmission, to server
10 send channel sequencing request.User can send channel sequencing instruction by pressing the button on remote controler to television set, e.g., press
It presses the Menu key on remote controler to open corresponding menu, channel sequencing option is got in menu, is then chosen, to television set
Send channel sequencing instruction;Alternatively, user directly presses the specific keys on remote controler, sending channel sequencing to television set refers to
It enables.
The computing module 14 calculates the corresponding channel weight value of each channel designation in channel sequencing request, by channel name
Claim corresponding second viewing information to be updated to weight order function, obtains channel weight value.Such as in one embodiment, weight order
Function is:H=a+b*X1+c*X2+d*X3+e*X4, wherein:A, b, c, d, e are constant, X1Indicate viewing duration, X2Indicate switching
Number, X3Indicate viewing population ages' distribution, X4Indicate viewing area;Channel designation in channel sequencing request is CCTV1,
A length of t1, switching times n1, viewing population ages are distributed as m1 and sight when viewing in corresponding second viewing informations of CCTV1
It sees that area is z1, t1, n1, m1 and z1 is substituted into H=a+b*X1+c*X2+d*X3+e*X4, obtain h=a+b*t1+c*n1+d*m1+
E*z1 calculates the corresponding channel weight values of CCTV1;Channel designation in channel sequencing request is CCTV2, and CCTV2 is corresponding
It is z2 that a length of t2 when viewing in the second viewing information, switching times n2, viewing population ages, which are distributed as m2 and viewing area,
T2, n2, m2 and z2 are substituted into H=a+b*X1+c*X2+d*X3+e*X4, h=a+b*t2+c*n2+d*m2+e*z2 is obtained, is calculated
The corresponding channel weight values of CCTV2;And so on, calculate the corresponding channel weight value of each channel designation.
Second generation module 15 according to the corresponding channel weight value of each channel, according to channel weight value from big to small into
Row sequence, in front by the big channel bank of channel weight value, channel weight is worth small channel bank later, generates new channel row
Table, the new channel list include channel and new channel number, and the channel corresponding new channel number for coming first is 1, come the
The corresponding new channel number of two channel is 2, and so on, to each channel into line renumbering.Optionally, which arranges
Table can also include the corresponding channel weight value of channel designation.The new channel list is as shown in Table 4.
After the television set receives the new channel list, arranged according to the local channel of the new channel list update television set
Table so that the sorting television channels are more intelligent.
Further, which includes viewing duration, switching times, viewing population ages distribution and viewing ground
Area;
First generation module 12 is additionally operable to the server 10 according to the channel number, viewing duration, switching times, sight
It sees population ages' distribution and viewing area, is instructed using multiple linear regression model, and to multiple linear regression model coefficient
Practice, generates weight order function;The multiple linear regression model is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein A1、
B1、C1、D1、E1It is constant, X1、X2、X3、X4It is independent variable.
First generation module 12 is using the channel number as dependent variable, by viewing duration, switching times, viewing crowd year
Age is distributed and viewing area is used as independent variable, is carried out using multiple linear regression model, and to multiple linear regression model coefficient
Training generates weight order function, i.e., on the large data sets for being collected into channel number and the first viewing information, to multiple linear
Regression model coefficient (A1、B1、C1、D1、E1) be trained, the corresponding coefficient of each independent variable in weight order function is obtained, such as
It is b that independent variable, which is the corresponding coefficient of viewing duration, in generation weighting function1, independent variable is that the corresponding coefficient of switching times is c1, from
Variable is that the corresponding coefficient of viewing population ages' distribution is d1, independent variable is that the corresponding coefficient in viewing area is e1, the weight order
Function is quaternary linear regression function;.Such as, which is indicated by following formula:H=a1+b1*X1+c1*X2+d1*
X3+e1*X4, wherein:a1、b1、c1、d1、e1It is constant, X1Indicate viewing duration, X2Indicate switching times, X3Indicate viewing crowd year
Age is distributed, X4Indicate viewing area.
Further, as shown in fig. 6, first viewing information includes viewing duration, switching times, viewing population ages point
Cloth and viewing area;The weight order function includes multiple channel weight subfunctions;Channel sequencing request further includes the TV
Regional belonging to machine, which includes viewing duration, switching times and viewing population ages' distribution;
First generation module 12 is additionally operable to according to the channel number, viewing duration, switching times, viewing population ages
Distribution and viewing area, are trained using multiple linear regression model, and to multiple linear regression model coefficient, are generated each
The corresponding channel weight subfunction in area;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3, wherein A2、
B2、C2、D2It is constant, X1、X2、X3It is independent variable.
The computing module 14 includes:
Searching unit 141, for according to area belonging to the television set, corresponding channel to be selected from the weight order function
Weight subfunction;
Computing unit 142, the channel weight for the second viewing information and the selection in being asked according to the channel sequencing
Subfunction calculates the corresponding channel weight value of each channel designation.
The weight order function includes multiple channel weight subfunctions, wherein a channel weight subfunction corresponds to one
Area, this area can or township levels at county level for provincial, city.
First generation module 12 first sorts out the channel information of reception, by the first viewing information in channel information
In viewing area it is identical and/or viewing area belong to same higher level area channel information composition one channel information subset,
Then according to channel number, viewing duration, switching times and the viewing population ages' distribution in the channel information subset, using more
First linear regression model (LRM) generates channel weight subfunction.As in one embodiment, the channel information which receives carries out
When classification, the channel information that the viewing area in the first viewing information in channel information is Shenzhen is formed into a channel information
The channel information that viewing area in the first viewing information in channel information is Guangzhou is formed channel information by subset
The channel information that viewing area in the first viewing information in channel information is Dongguan is formed channel information by collection
Collection;And/or the regional channel information for Shenzhen and Guangzhou, Dongguan of the viewing in the first viewing information in channel information is formed
One channel information subset (the upper level area of Shenzhen and Guangzhou and Dongguan is all Guangdong).
First generation module 12 is according to channel number, viewing duration, switching times and the sight in the channel information subset
It sees that population ages are distributed, is trained using multiple linear regression model, and to multiple linear regression model coefficient, generated each
Area corresponding channel weight subfunction be specially:First generation module 12 compiles the channel in the channel information subset
Number be used as dependent variable, by channel information subset viewing duration, switching times and viewing population ages distribution be used as independent variable,
It is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates channel weight subfunction, that is, exist
It is collected on channel number and the large data sets of the first viewing information, to multiple linear regression model coefficient (A2、B2、C2、D2) into
Row training obtains the corresponding coefficient of each independent variable in weight order function, as when generating that independent variable is viewing in weighting function
Long corresponding coefficient is b2, independent variable is that the corresponding coefficient of switching times is c2, independent variable is that viewing population ages' distribution is corresponding
Coefficient is d2, which is ternary linear regression function;Such as, which passes through following formula table
Show:H=a2+b2*X1+c2*X2+d2*X3, wherein:a2、b2、c2、d2It is constant, X1Indicate viewing duration, X2Indicate switching times, X3
Indicate viewing population ages' distribution.
First generation module 12 also saves the mapping relations in each area and the channel weight subfunction.
The searching unit 141 chooses the television set institute according to area belonging to the television set from the weight order function
The corresponding channel weight subfunction in possession area obtains specifically, according to the mapping relations in each area and channel weight subfunction
Corresponding channel weight subfunction.Optionally, when searching unit 141 is according to regional belonging to the television set, not in the weight order
When choosing regional corresponding channel weight subfunction belonging to the television set in function, then first get regional belonging to the television set
Upper level region, the electricity is then chosen in the weight order function according to upper level region regional belonging to the television set
Depending on the corresponding channel weight subfunction in area belonging to machine, if not choosing corresponding channel weight subfunction yet, and so on,
Continuation is selected according to the upper level region in upper level region regional belonging to the television set, until choosing corresponding channel
Weight subfunction.As in one embodiment, area belonging to the television set is Shenzhen, is corresponded to if the weight order function includes Shenzhen
Channel weight subfunction, then the corresponding channel weight subfunction in the Shenzhen can be directly found, if the weight order function is not
Including the corresponding channel weight subfunction in Shenzhen, then the upper level region for first getting Shenzhen is Guangdong, then in weight order
The corresponding channel weight subfunction in Guangdong is selected in function, as the corresponding channel weight subfunction in area belonging to the television set.
The computing unit 142 calculates the corresponding channel weight value of each channel designation in channel sequencing request, by channel
Viewing duration, switching times, viewing population ages' distribution in corresponding second viewing information of title are updated to the channel of selection
Weight subfunction obtains channel weight value.As in one embodiment, which is indicated by following formula:H=a2
+b2*X1+c2*X2+d2*X3, wherein:a2、b2、c2、d2It is constant, X1Indicate viewing duration, X2Indicate switching times, X3It indicates to see
See that population ages are distributed, the channel designation in channel sequencing request is CCTV1, the sight in corresponding second viewing informations of CCTV1
A length of t1, switching times n1, viewing population ages are distributed as m1 when seeing, t1, n1 and m1 are substituted into H=a2+b2*X1+c2*X2+
d2*X3, obtain h=a2+b2*t1+c2*n1+d2* m1 calculates the corresponding channel weight values of CCTV1.
With reference to Fig. 7, Fig. 7 is sorting television channels system of the present invention, which includes the service of any of the above-described embodiment
Device 10, and multiple television sets 20 for being connect with the server 10.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (11)
1. a kind of method for ordering television channels, which is characterized in that this method includes:
Server receives the channel information of multiple television sets, and the channel information includes channel number, channel number corresponding
One viewing information, first viewing information include more than two viewing parameters;
The server is returned according to the channel number and corresponding first viewing information of the channel number using multiple linear
Return model, and multiple linear regression model coefficient is trained, generates weight order function;
The server receives the channel sequencing request that television set is sent, and the channel sequencing request includes channel designation, channel
Corresponding second viewing information of title, second viewing information include more than two viewing parameters;
The server calculates the corresponding frequency of each channel designation according to channel sequencing request and the weight order function
Road weighted value;
The server according to the corresponding channel weight value of each channel, to each channel according to channel weight value from big to small into
Row sequence, generates new channel list, and the new channel list is returned to television set, for the television set according to the new frequency
The local channel list of road list update television set.
2. method for ordering television channels as described in claim 1, which is characterized in that the server obtains multiple television sets
The step of channel information includes:
The server receives the channel information that multiple television sets are reported when networking with the server triggers.
3. method for ordering television channels as claimed in claim 1 or 2, which is characterized in that first viewing information includes seeing
See duration, switching times, viewing population ages distribution and viewing area;
The server is returned according to the channel number and corresponding first viewing information of the channel number using multiple linear
Return model, and multiple linear regression model coefficient be trained, generate weight order function the step of be:
The server is adopted according to the channel number, viewing duration, switching times, viewing population ages distribution, viewing area
With multiple linear regression model, and multiple linear regression model coefficient is trained, generates weight order function;It is described polynary
Linear regression model (LRM) is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein A1、B1、C1、D1、E1It is constant, X1、X2、X3、X4
It is independent variable.
4. method for ordering television channels as claimed in claim 1 or 2, which is characterized in that first viewing information includes seeing
See duration, switching times, viewing population ages distribution and viewing area;The weight order function includes multiple channel weight
Function;
The server is returned according to the channel number and corresponding first viewing information of the channel number using multiple linear
Return model, and multiple linear regression model coefficient be trained, generate weight order function the step of be:
The server is regional according to the channel number, viewing duration, switching times, viewing population ages distribution and viewing,
It is trained using multiple linear regression model, and to multiple linear regression model coefficient, generates the corresponding frequency in each area
Road weight subfunction;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3, wherein A2、B2、C2、D2It is normal
Number, X1、X2、X3It is independent variable.
5. method for ordering television channels as claimed in claim 4, which is characterized in that the channel sequencing request further includes described
Regional belonging to television set, second viewing information includes viewing duration, switching times and viewing population ages' distribution;
The server calculates the corresponding frequency of each channel designation according to channel sequencing request and the weight order function
The step of road weighted value includes:
According to area belonging to the television set, corresponding channel weight subfunction is selected from the weight order function;
The second viewing information in being asked according to the channel sequencing and the selected channel weight subfunction, calculate each frequency
The corresponding channel weight value of road title.
6. a kind of server, which is characterized in that the server includes the first transceiver module, the first generation module, the second transmitting-receiving
Module, computing module and the second generation module, wherein:
First transceiver module, the channel information for receiving multiple television sets, the channel information include channel number, frequency
Number corresponding first viewing information in road;First viewing information includes more than two viewing parameters;
First generation module, for according to the channel number and corresponding first viewing information of the channel number, adopting
With multiple linear regression model, and multiple linear regression model coefficient is trained, generates weight order function;
Second transceiver module, the channel sequencing request for receiving television set transmission, the channel sequencing request includes frequency
Corresponding second viewing information of road title, channel designation, second viewing information include more than two viewing parameters;
The computing module, for according to channel sequencing request and the weight order function, calculating each channel designation
Corresponding channel weight value;
Second generation module is used for according to the corresponding channel weight value of each channel, to each channel according to channel weight
Value is ranked up from big to small, generates new channel list;
Second transceiver module is additionally operable to the new channel list returning to television set, for the television set according to
The local channel list of new channel list update television set.
7. server as claimed in claim 6, which is characterized in that first transceiver module is additionally operable to receive multiple TVs
The channel information that machine is reported when networking with the server triggers.
8. server as claimed in claims 6 or 7, which is characterized in that first viewing information includes viewing duration, switching
Number, viewing population ages distribution and viewing area;
First generation module is additionally operable to the server according to the channel number, viewing duration, switching times, viewing
Population ages are distributed and viewing area, are trained using multiple linear regression model, and to multiple linear regression model coefficient,
Generate weight order function;The multiple linear regression model is:H=A1+B1*X1+C1*X2+D1*X3+E1*X4, wherein A1、B1、
C1、D1、E1It is constant, X1、X2、X3、X4It is independent variable.
9. server as claimed in claims 6 or 7, which is characterized in that first viewing information include viewing duration,
Switching times, viewing population ages distribution and viewing area;The weight order function includes multiple channel weight subfunctions;
First generation module is additionally operable to according to the channel number, viewing duration, switching times, viewing population ages point
Cloth and viewing area, are trained using multiple linear regression model, and to multiple linear regression model coefficient, are generated eachly
The corresponding channel weight subfunction in area;The multiple linear regression model is:H=A2+B2*X1+C2*X2+D2*X3, wherein A2、
B2、C2、D2It is constant, X1、X2、X3It is independent variable.
10. server as claimed in claim 9, which is characterized in that the channel sequencing request further includes the television set institute
Possession area, second viewing information include viewing duration, switching times and viewing population ages' distribution;
The computing module includes:
Searching unit, for according to area belonging to the television set, corresponding channel being selected to weigh from the weight order function
Baryon function;
Computing unit, for the second viewing information and the sub- letter of the selected channel weight in being asked according to the channel sequencing
Number, calculates the corresponding channel weight value of each channel designation.
11. a kind of sorting television channels system, which is characterized in that the system comprises as described in claim any one of 6-10
Server, and multiple television sets for being connect with the server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510810947.3A CN105472413B (en) | 2015-11-19 | 2015-11-19 | Method for ordering television channels, system and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510810947.3A CN105472413B (en) | 2015-11-19 | 2015-11-19 | Method for ordering television channels, system and server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105472413A CN105472413A (en) | 2016-04-06 |
CN105472413B true CN105472413B (en) | 2018-09-04 |
Family
ID=55609627
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510810947.3A Active CN105472413B (en) | 2015-11-19 | 2015-11-19 | Method for ordering television channels, system and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105472413B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106354371A (en) * | 2016-09-06 | 2017-01-25 | 深圳市金立通信设备有限公司 | Application sorting method and terminal |
CN106534909A (en) * | 2016-12-05 | 2017-03-22 | 合网络技术(北京)有限公司 | Channel catalogue display method and device |
CN106791901B (en) * | 2016-12-15 | 2020-09-22 | Tcl科技集团股份有限公司 | Live broadcast channel ordering method and device |
CN113473230B (en) * | 2021-07-02 | 2022-08-26 | 海信视像科技股份有限公司 | Method for realizing channel switching by using third-party application and display equipment |
WO2022121380A1 (en) | 2020-12-07 | 2022-06-16 | 海信视像科技股份有限公司 | Channel switching method for display device, and display device |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9015156B2 (en) * | 2012-03-30 | 2015-04-21 | Percolate Industries, Inc. | Interactive computing recommendation facility with learning based on user feedback and interaction |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5758257A (en) * | 1994-11-29 | 1998-05-26 | Herz; Frederick | System and method for scheduling broadcast of and access to video programs and other data using customer profiles |
CN100534130C (en) * | 2007-11-20 | 2009-08-26 | 腾讯科技(深圳)有限公司 | Method, system and equipment to recommend program to television users |
CN101739417A (en) * | 2008-11-04 | 2010-06-16 | 未序网络科技(上海)有限公司 | System for sequencing multi-index comprehensive weight audio-video album |
IN2014DN07244A (en) * | 2012-02-21 | 2015-04-24 | Ooyala Inc | |
CN104216960A (en) * | 2014-08-21 | 2014-12-17 | 北京奇艺世纪科技有限公司 | Method and device for recommending video |
CN104462293A (en) * | 2014-11-27 | 2015-03-25 | 百度在线网络技术(北京)有限公司 | Search processing method and method and device for generating search result ranking model |
-
2015
- 2015-11-19 CN CN201510810947.3A patent/CN105472413B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9015156B2 (en) * | 2012-03-30 | 2015-04-21 | Percolate Industries, Inc. | Interactive computing recommendation facility with learning based on user feedback and interaction |
Also Published As
Publication number | Publication date |
---|---|
CN105472413A (en) | 2016-04-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105472413B (en) | Method for ordering television channels, system and server | |
CN104572889B (en) | A kind of search word recommends methods, devices and systems | |
CN105912697A (en) | Optimization method and device of dialog system knowledge base | |
CN101355686B (en) | Method and system for statistic of audience rating | |
CN104657372B (en) | page operation data processing method and device | |
CN104834657B (en) | User behavior analysis method and server | |
CN107705005A (en) | A kind of movie and television contents Valuation Method | |
CN108764505A (en) | A kind of reservation management method and system of open laboratory | |
CN107659627B (en) | Fitness data synchronization method, device, terminal, equipment, server and storage medium | |
CN104239499A (en) | Method and device for college entrance will intelligent recommendation based on big data | |
CN106375369A (en) | Mobile Web service recommendation method and collaborative recommendation system based on user behavior analysis | |
CN110413748A (en) | Based on big data robot service knowledge base entry recommender system | |
CN105207821A (en) | Network comprehensive performance evaluation method oriented to service | |
CN105376649B (en) | Realize the blind operating method of the set-top box of accurate combined recommendation and system | |
CN104811810A (en) | Real-time regional audience rating and audience share statistical system based on intelligent television and method thereof | |
CN102891916A (en) | Method and mobile terminal for predicating user operation | |
CN106326297A (en) | Application recommendation method and device | |
CN106303591B (en) | A kind of video recommendation method and device | |
CN109270848A (en) | Recommended method, server, household appliance and the storage medium of contextual model | |
CN109688217A (en) | A kind of information push method, device and electronic equipment | |
CN110288443A (en) | Information pushing method and device, electronic equipment and computer readable storage medium | |
CN110503463A (en) | A kind of shops's Site planning method based on chain industry situation | |
CN110245207A (en) | A kind of exam pool construction method, exam pool construction device and electronic equipment | |
CN109583932A (en) | A kind of method, apparatus and electronic equipment of generation activity crowd | |
CN107193829B (en) | Application program recommendation method and device |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210712 Address after: Room 821, No. 333, jiufo Jianshe Road, Zhongxin Guangzhou Knowledge City, Huangpu District, Guangzhou, Guangdong 510000 Patentee after: Skyworth Group Intelligent Technology Co., Ltd Address before: No.99, Kaida Road, Guangzhou Economic and technological development science and Technology City, Guangzhou, Guangdong 510000 Patentee before: GUANGZHOU SKYWORTH FLAT DISPLAY TECHNOLOGY Co.,Ltd. |
|
TR01 | Transfer of patent right |