CN108363730A - A kind of content recommendation method, system and terminal device - Google Patents
A kind of content recommendation method, system and terminal device Download PDFInfo
- Publication number
- CN108363730A CN108363730A CN201810032233.8A CN201810032233A CN108363730A CN 108363730 A CN108363730 A CN 108363730A CN 201810032233 A CN201810032233 A CN 201810032233A CN 108363730 A CN108363730 A CN 108363730A
- Authority
- CN
- China
- Prior art keywords
- program
- timesharing
- label
- recommendation
- default
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention is suitable for technical field of information processing, provides a kind of content recommendation method, system and terminal device, including:Obtain the history rating record of user;It is recorded according to history rating, obtains preset period of time and the corresponding timesharing minute mark label weight of default label;It is recorded according to history rating, obtains the default corresponding bonus point factor of label and decay factor;It obtains and presets the corresponding program recommendation list of label, and assignment is carried out to the program in program recommendation list, obtain recommending assignment;According to timesharing minute mark label weight, the bonus point factor, decay factor and recommend assignment, obtains recommendation.The interested program of user that the embodiment of the present invention passes through consideration preset period of time, interest level of the user in preset period of time to default label is calculated, and calculate the recommendation that user is pushed in preset period of time, to more accurately be pushed to the specific recommendation of user, user experience is optimized.
Description
Technical field
The invention belongs to a kind of technical field of information processing more particularly to content recommendation method, system and terminal devices.
Background technology
With the development of Internet technology, user more applies intelligent terminal to watch movie and video programs, and usual user searches
The method of program includes searching the program that user likes by recommendation, or directly search known program and watched.
Currently, including being based on content Collaborative Filtering Recommendation Algorithm by the method that recommendation searches the program that user likes
With the Collaborative Filtering Recommendation Algorithm based on user behavior, wherein the recommendation results based on content Collaborative Filtering Recommendation Algorithm fix,
Recommendation results are easy unalterable;The recommendation results of Collaborative Filtering Recommendation Algorithm based on user behavior are according to close with user
User's program do and recommend, recommendation results can update often, but computationally intensive.
Invention content
In view of this, an embodiment of the present invention provides a kind of content recommendation method, system and terminal device, it is existing to solve
Unalterable, the computationally intensive problem of recommendation results present in technology.
The first aspect of the embodiment of the present invention provides a kind of content recommendation method, including:
Obtain the history rating record of user;
It is recorded according to history rating, obtains preset period of time and the corresponding timesharing minute mark label weight of default label;
It is recorded according to history rating, obtains the default corresponding bonus point factor of label and decay factor;
It obtains and presets the corresponding program recommendation list of label, and assignment is carried out to the program in program recommendation list, obtain
Recommend assignment;
According to timesharing minute mark label weight, the bonus point factor, decay factor and recommend assignment, obtains recommendation.
The second aspect of the embodiment of the present invention provides a kind of content recommendation system, including:
History rating records acquisition module, and the history rating for obtaining user records;
Timesharing minute mark label Weight Acquisition module obtains preset period of time and default label for being recorded according to history rating
Corresponding timesharing minute mark label weight;
Impact factor acquisition module, for being recorded, obtaining the default corresponding bonus point factor of label and being declined according to history rating
Subtracting coefficient;
Recommend program assignment module, for obtaining the corresponding program recommendation list of default label, and to program recommendation list
In program carry out assignment, obtain recommend assignment;
Recommendation acquisition module is used for according to timesharing minute mark label weight, the bonus point factor, decay factor and recommends assignment,
Obtain recommendation.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
The step of realizing content recommendation method as described above.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, the computer program to realize the step of content recommendation method as described above when being executed by processor
Suddenly.
Existing advantageous effect is the embodiment of the present invention compared with prior art:By the history rating note for obtaining user
Record;It is recorded according to history rating, obtains preset period of time and the corresponding timesharing minute mark label weight of default label;According to history rating
Record obtains the default corresponding bonus point factor of label and decay factor;It obtains and presets the corresponding program recommendation list of label, and is right
Program in program recommendation list carries out assignment, obtains recommending assignment;According to timesharing minute mark label weight, the bonus point factor, decaying because
Son and recommendation assignment, obtain recommendation.The embodiment of the present invention is calculated by the interested program of user of consideration preset period of time
It obtains interest level of the user in preset period of time to default label, and calculates and be pushed in the recommendation of user in preset period of time
Hold, to more accurately be pushed to the specific recommendation of user, optimizes user experience.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram of content recommendation method provided in an embodiment of the present invention;
Fig. 2 is the implementation process schematic diagram of step S102 in Fig. 1 provided in an embodiment of the present invention;
Fig. 3 is the implementation process schematic diagram of step S103 in Fig. 1 provided in an embodiment of the present invention;
Fig. 4 is the implementation process schematic diagram of step S303 in Fig. 3 provided in an embodiment of the present invention;
Fig. 5 is the implementation process schematic diagram of step S306 in Fig. 3 provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of content recommendation system provided in an embodiment of the present invention;
Fig. 7 is the structural schematic diagram of timesharing minute mark label Weight Acquisition module in Fig. 6 provided in an embodiment of the present invention;
Fig. 8 is the structural schematic diagram of impact factor acquisition module in Fig. 6 provided in an embodiment of the present invention;
Fig. 9 is the structural schematic diagram of full-time impact factor acquiring unit in Fig. 8 provided in an embodiment of the present invention;
Figure 10 is the structural schematic diagram of timesharing impact factor acquiring unit in Fig. 8 provided in an embodiment of the present invention;
Figure 11 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific implementation mode
In being described below, for illustration and not for limitation, it is proposed that such as tool of particular system structure, technology etc
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
Term " comprising " in description and claims of this specification and above-mentioned attached drawing and their any deformations, meaning
Figure, which is to cover, non-exclusive includes.Such as process, method or system comprising series of steps or unit, product or equipment do not have
It is defined in the step of having listed or unit, but further includes the steps that optionally not listing or unit, or optionally also wrap
It includes for the intrinsic other steps of these processes, method, product or equipment or unit.In addition, term " first ", " second " and
" third " etc. is for distinguishing different objects, not for description particular order.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Embodiment 1:
Fig. 1 shows a kind of implementation process for content recommendation method that one embodiment of the present of invention provides, the present embodiment
Flow executive agent can be terminal device, details are as follows for process:
In step S101, the history rating record of user is obtained.
In the present embodiment, the history rating record of user preset time span is obtained, is wrapped in the history rating record
Contain multiple programs arranged according to time tandem.
In step s 102, it is recorded according to history rating, obtains preset period of time and the corresponding timesharing minute mark of default label
Sign weight.
In the present embodiment, the preset period of time can be the period in morning (00:00~6:00), morning (6:00~11:
00), noon (11:00~13:00), afternoon (13:00~17:00), the dusk (17:00~19:00), the prime time in night (19:
00~22:00), night just before going to bed (22:00~24:00).
In the present embodiment, each program in history rating record carries at least one default label.It is described pre-
Bidding label may include ancient costume, city, fantasy, love, war, action etc..
In step s 103, it is recorded according to history rating, obtains the default corresponding bonus point factor of label and decay factor.
In step S104, obtains and preset the corresponding program recommendation list of label, and to the program in program recommendation list
Assignment is carried out, obtains recommending assignment.
In step S105, according to timesharing minute mark label weight, the bonus point factor, decay factor and recommends assignment, recommended
Content.
From above-described embodiment it is found that being recorded by the history rating for obtaining user;It is recorded, is preset according to history rating
Period and the corresponding timesharing minute mark label weight of default label;It is recorded according to history rating, obtains the corresponding bonus point of default label
The factor and decay factor;It obtains and presets the corresponding program recommendation list of label, and the program in program recommendation list is assigned
Value obtains recommending assignment;According to timesharing minute mark label weight, the bonus point factor, decay factor and recommend assignment, obtains recommendation.
User is calculated in preset period of time to being marked in advance by the interested program of user of consideration preset period of time in the embodiment of the present invention
The interest level of label, and the recommendation that user is pushed in preset period of time is calculated, to more accurately be pushed to use
The specific recommendation in family, optimizes user experience.
As shown in Fig. 2, in one embodiment of the invention, Fig. 2 shows the specific implementation streams of step S102 in Fig. 1
Journey, details are as follows:
In step s 201, the corresponding program of extraction preset period of time from history rating record, obtains timesharing rating sequence.
In the present embodiment, the program in history rating record includes viewing time, according to the viewing time and is preset
Period extracts the timesharing rating sequence.According to above-mentioned preset period of time, history rating record can be divided into be received for morning timesharing
Depending on sequence, daystart timesharing rating sequence, noon timesharing rating sequence, timesharing in afternoon rating sequence, dusk timesharing rating sequence, evening
Between gold timesharing rating sequence, night timesharing rating sequence just before going to bed.
In step S202, is extracted from timesharing rating sequence and preset the corresponding program of label, obtained timesharing minute mark and sign for
Depending on sequence.
In the present embodiment, when obtaining the timesharing rating sequence, timesharing minute mark is obtained according to default label and signs for regarding
Sequence, each label correspond to a timesharing minute mark and sign for regarding sequence.
By taking a specific application scenarios as an example:
In history rating record, the default label of program " Mekong action " is action, crime, viewing time 8:
00;The default label of program " the long old song form in beautiful rivers and mountains " is love, ancient costume, viewing time 14:00, ten inner peach of three lives three generations
Colored default label is ancient costume, fantasy, love, viewing time 15:00, the default label of warwolf 2 is war, action, viewing
Time is 16:30.
It is afternoon to take preset period of time, and obtained timesharing rating sequence is the long old song form in beautiful rivers and mountains, ten inner peach of three lives three generations
Flower, warwolf 2.
According to the timesharing rating sequence, it is love to take default label, then timesharing minute mark sign for regarding sequence as:Beautiful rivers and mountains
A long old song form, ten inner peach blossom of three lives three generations.
In step S203, timesharing minute mark is signed for regard the program total quantity in sequence divided by the section in timesharing rating sequence
Mesh total quantity obtains timesharing minute mark label weight.
In the present embodiment, if default label is i, preset period of time t, then timesharing minute mark signs for the program sum regarding sequence
Amount is Num (nt,i), the program total quantity in timesharing rating sequence is Num (nt), then timesharing minute mark label weight Wt,iForWt,iIndicate the corresponding timesharing minute mark label weights of default label i at preset period of time t.
As shown in figure 3, in one embodiment of the invention, Fig. 3 shows the implementation process of step S103 in Fig. 1, in detail
It states as follows;
In step S301, it is the program assignment in history rating record according to the first preset rules, obtains each section
The corresponding program score value of mesh.
In the present embodiment, it is described according to the first preset rules be the history rating record in program assignment include press
Sequence according to time order and function is that the program in history rating record is incremented by assignment with pre-set tolerance.Such as come history rating
The program score value for recording first position is 1, and the program score value for coming the second position is 2, in this way, being passed successively for pre-set tolerance with 1
Increase to the program assignment in history rating record.
In step s 302, it is extracted from history rating record and presets the corresponding program of label, obtained minute mark and sign for regarding sequence
Row.
In step S303, is signed for regarding sequence according to program score value and minute mark, it is corresponding full-time that default label is calculated
The bonus point factor and full-time decay factor.
In step s 304, the corresponding program of extraction preset period of time from history rating record, obtains timesharing rating sequence.
In step S305, is extracted from timesharing rating sequence and preset the corresponding program of label, obtained timesharing minute mark and sign for
Depending on sequence.
In step S306, is signed for regarding sequence according to program score value, timesharing rating sequence and timesharing minute mark, be calculated pre-
Bidding signs the corresponding timesharing bonus point factor and timesharing decay factor.
As shown in figure 4, in one embodiment of the invention, Fig. 4 shows the implementation process of step S303 in Fig. 3, in detail
It states as follows:
In step S401, the summation that minute mark signs for regarding the corresponding program score value of program in sequence is calculated, minute mark is obtained
Sign program score value summation.
In step S402, it is based on the first default computation rule, is signed for regarding sequence according to minute mark label program score value summation, minute mark
Program total quantity in row, the program total quantity in history rating record and the first default attenuation coefficient, are calculated pre- bidding
Sign corresponding full-time decay factor.
In the present embodiment, the first default computation rule is:
ai=1+d1*(nL*Num(ni)-Sum(ni))
Wherein, aiTo preset the corresponding full-time decay factors of label i;d1For the first default attenuation coefficient;nLFor history rating
Program total quantity in record, in the present embodiment, nLIt can be with value for 10, for indicating that user closely likes watching for a period of time
Program;Num(ni) it is that minute mark is signed for regarding the program total quantity in sequence;Sum(ni) it is minute mark label program score value summation.
By the above-mentioned first default computation rule, to obtain the corresponding full-time decay factor of default label.
In step S403, when default label all same corresponding in the presence of continuously N number of program in history rating record, obtain
Take N values, N >=2.
In the present embodiment, when the program of continuous N number of position in history rating record includes same default label,
Show there is a continuous rating at this time, it is interested that user presets this label, so obtaining N values, calculates the default label and corresponds to
The full-time bonus point factor.
In step s 404, by N values and the first default bonus point multiplication, obtain the default corresponding full-time bonus point of label because
Son.
In the present embodiment, the calculation formula of the full-time bonus point factor is:bi=a1* N, wherein a1For the first default bonus point system
Number;biFor the corresponding full-time bonus point factors of the default label i.
As shown in figure 5, in one embodiment of the invention, Fig. 5 is the implementation process of step S306 in Fig. 3, is described in detail such as
Under:
In step S501, the summation that timesharing minute mark signs for regarding the corresponding program score value of program in sequence is calculated, is obtained
Timesharing minute mark label program score value summation.
In step S502, it is based on the second default computation rule, according to timesharing minute mark label program score value summation, timesharing minute mark
It signs for regarding the program total quantity in sequence, the program total quantity in history rating record and the second default attenuation coefficient, calculates
To the corresponding timesharing decay factor of default label.
In the present embodiment, the second default computation rule is:
at,i=1+d2*(nL*Num(nt,i)-Sum(nt,i));
Wherein, d2For the second default attenuation coefficient;Num(nt,i) it is that timesharing minute mark is signed for regarding the program total quantity in sequence;
Sum(nt,i) it is timesharing minute mark label program score value summation.By the above-mentioned second default computation rule, timesharing decay factor a is obtainedt,i
In step S503, when default label all same corresponding there are continuous N program in timesharing rating sequence, obtain
Take M values, M >=2.
In the present embodiment, when the program of continuous N position in the timesharing rating sequence includes same default label,
Showing this preset period of time has a continuous rating, and it is interested that user in this preset period of time presets this label, so M values are obtained,
Calculate the timesharing bonus point factor of the default label.
In step S504, by M values and the second default bonus point multiplication, obtain the default corresponding timesharing bonus point of label because
Son.
In the present embodiment, step S504 includes:bt,i=a2* M, wherein a2For the second default bonus point coefficient, bt,iIt is default
The corresponding timesharing bonus point factors of label i.
In the present embodiment, in Fig. 1 step S104 detailed process, including:
In step s 601, public program recommendation list is obtained.
In the present embodiment, server pushes public program recommendation list to terminal device, and server includes internal referral
The preset algorithm of system, internal referral system includes the Collaborative Filtering Recommendation Algorithm based on content, the collaboration based on user behavior
Filtering recommendation algorithms, popular broadcasting proposed algorithm, popular search proposed algorithm.
In the present embodiment, public program recommendation list further includes the rendition list obtained based on external data source, such as beans
Valve program ranking list, Baidu's film rating index recommend list etc..
In the present embodiment, according to the difference of preset algorithm, obtained public program recommendation list is also different, if pre- imputation
Method is multiple, then the public recommendation list got is also multiple.
Step S602:All corresponding programs of default label are extracted from public program recommendation list, obtain each
The corresponding program recommendation list of default label.
In the present embodiment, it by extracting all corresponding programs of default label, obtains each default label and corresponds to
Program recommendation list.
Step S603:Assignment is carried out according to the second preset rules to the program in program recommendation list, obtains public program
The corresponding recommendation assignment of each program in recommendation list.
In the present embodiment, step S603 includes:The arrangement that puts in order according to program in public program recommendation list is every
Program in the corresponding program recommendation list of one default label, and successively decreased with pre-set tolerance for the program in program recommendation list
Assignment.Such as, it is pre-set tolerance with 1, for the program assignment of first position in all corresponding program recommendation lists of default label
It is 100, the program of the second position is assigned a value of 99, and so on, obtain the recommendation of all programs in public program recommendation list
Assignment.
In one embodiment of the invention, in Fig. 1 step S105 specific implementation flow, including:
Step S701:Computation rule is preset based on third, to minute mark label weight, the bonus point factor, decay factor and recommends to assign
Value carries out integral operation, obtains the recommendation score of program in public program recommendation list.
In one embodiment of the invention, the content recommendation method further includes:
Obtain the quantity of each program occurs in all public recommendation lists number and default label.
In the present embodiment, since preset algorithm is there are multiple, corresponding obtained public program recommendation list also have it is multiple,
Obtain the number that each program occurs in all public recommendation lists.
In the present embodiment, by taking a program p in public program recommendation list as an example, the recommendation of the program p is calculated
Scoring, specifically includes:
Third presets computation rule:
Wherein, npIndicate the number that program p occurs in all public recommendation lists;nx,pIndicate the default label of program p
Quantity;I indicates to preset label i;T indicates preset period of time t;at,iIt indicates to preset the corresponding timesharing decay factors of label i;aiIt indicates
Preset the corresponding full-time decay factors of label i;bt,iIt indicates to preset the corresponding timesharing bonus point factors of label i;biIt indicates to preset label
The corresponding full-time bonus point factors of i;C indicates to preset bonus point item;wt,iIndicate timesharing minute mark label weight;Dx,i,pIt indicates using pre- imputation
Recommendation assignment of the program p that method x is screened in the default corresponding program recommendation lists of label i.
In the present embodiment, the default bonus point item c includes the first default bonus point value and the second default bonus point value, described pre-
If the acquisition process of the numerical value of bonus point item c includes:
1) in the corresponding default label of program p and history rating record the program of first position it is corresponding one it is pre-
When bidding label are identical, c is the first default bonus point value.
2) when the corresponding default labels of program p all pre- biddings corresponding with the program of first position in history rating record
When label are different, c is the second default bonus point value.
In the present embodiment, the first default bonus point value could be provided as 0.02, and the second default bonus point value is set as 0.Pass through
Bonus point item numerical value is obtained, it can be to the default label bonus point of user's current interest, to make the content of recommendation more cater to use
The current interest in family.
Computation rule is preset according to above-mentioned third, the recommendation of all programs in the public program recommendation list is calculated
Scoring.
Step S702:The section arranged in the public program recommendation list is corresponded to according to the sequence of recommendation score from high to low
Mesh obtains recommendation.
In the present embodiment, the sequence for the program in the public program recommendation list according to recommendation score from high to low
Sequence, and the program of default recommended amount is obtained down as recommendation since the highest program of recommendation score.
In one embodiment of the invention, when the program in the recommendation got includes in history rating record
When program, the program identical with the program in history rating record is removed, and selected from the remaining program of public recommendation list
It takes the highest program of recommendation score to be put into recommendation, comes the rearmost position of recommendation, and so on, until recommendation
In there is no user history rating record in program until.To ensure that recommendation has not been seen and may have been felt for user
The content of interest.
From above-described embodiment it is found that by obtaining minute mark label weight, the bonus point factor and decay factor, realize continuous to user
The default label watched carries out bonus point, bonus point is carried out to the label of user's current interest, to make the recommendation for recommending user
Content more caters to the current interest of user, and according to preset period of time, is recorded to the history rating of user's difference preset period of time
It is divided, so as to obtain the interested recommendation of different periods user, user is avoided to miss interested content,
Meanwhile this commending contents algorithm calculates simply, it is only necessary to which simple addition subtraction multiplication and division calculating can be completed, and calculation amount is smaller, shortens
Operation time, operation efficiency is improved, user experience is optimized.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment 2:
As shown in fig. 6, the content recommendation system 1000 that one embodiment of the present of invention provides, for executing corresponding to Fig. 1
Embodiment in method and step comprising:
History rating records acquisition module 1100, and the history rating for obtaining user records;
Timesharing minute mark label Weight Acquisition module 1200, for being recorded, obtaining preset period of time and being preset according to history rating
The corresponding timesharing minute mark label weight of label;
Impact factor acquisition module 1300 obtains the corresponding bonus point factor of default label for being recorded according to history rating
And decay factor;
Recommend program assignment module 1400, recommends for obtaining the corresponding program recommendation list of default label, and to program
Program in list carries out assignment, obtains recommending assignment;
Recommendation acquisition module 1500, for being assigned according to timesharing minute mark label weight, the bonus point factor, decay factor and recommendation
Value, obtains recommendation.
From above-described embodiment it is found that being recorded by the history rating for obtaining user;It is recorded, is preset according to history rating
Period and the corresponding timesharing minute mark label weight of default label;It is recorded according to history rating, obtains the corresponding bonus point of default label
The factor and decay factor;It obtains and presets the corresponding program recommendation list of label, and the program in program recommendation list is assigned
Value obtains recommending assignment;According to timesharing minute mark label weight, the bonus point factor, decay factor and recommend assignment, obtains recommendation.
User is calculated in preset period of time to being marked in advance by the interested program of user of consideration preset period of time in the embodiment of the present invention
The interest level of label, and the recommendation that user is pushed in preset period of time is calculated, to more accurately be pushed to use
The specific recommendation in family, optimizes user experience.
As shown in Figure 7 in one embodiment of the invention, the timesharing in the embodiment corresponding to Fig. 6 shown in Fig. 7 point
Label Weight Acquisition module 1200 further includes the structure for executing the method and step in the embodiment corresponding to Fig. 2 comprising:
Timesharing rating retrieval unit 1210 is corresponded to for extracting the preset period of time from history rating record
Program, obtain timesharing rating sequence;
Timesharing minute mark is signed for regarding retrieval unit 1220, for extracting the pre- bidding from the timesharing rating sequence
Corresponding program is signed, timesharing minute mark is obtained and signs for regarding sequence;
Timesharing minute mark label Weight Acquisition unit 1230, for by timesharing minute mark sign for regard sequence in program total quantity divided by
Program total quantity in timesharing rating sequence obtains timesharing minute mark label weight.
As shown in Figure 8 in one embodiment of the invention, Fig. 8 output Fig. 6 corresponding to embodiment in influence because
Sub-acquisition module 1300 is additionally operable to execute the structure of the method and step in the embodiment corresponding to Fig. 3, including:
Program score value acquiring unit 1310, for being the program assignment in history rating record according to the first preset rules,
Obtain the corresponding program score value of each program;
Minute mark is signed for regarding retrieval unit 1320, and the corresponding section of label is preset for being extracted from history rating record
Mesh obtains minute mark and signs for regarding sequence;
Full-time impact factor acquiring unit 1330 regards sequence for being signed for according to program score value and minute mark, is calculated pre-
Bidding signs the corresponding full-time bonus point factor and full-time decay factor;
Timesharing rating retrieval unit 1340, for extracting the corresponding program of preset period of time from history rating record,
Obtain timesharing rating sequence;
Timesharing minute mark is signed for regarding retrieval unit 1350, corresponding for extracting default label from timesharing rating sequence
Program obtains timesharing minute mark and signs for regarding sequence;
Timesharing impact factor acquiring unit 1360, for according to the program score value, timesharing rating sequence and timesharing minute mark
It signs for regarding sequence, the corresponding timesharing bonus point factor of default label and timesharing decay factor is calculated.
As shown in figure 9, in one embodiment of the invention, the full-time impact factor in Fig. 8 shown in Fig. 9 obtains single
Member 1330 is additionally operable to execute the structure of the method and step in the embodiment corresponding to Fig. 4, including:
Minute mark label program score value summation computation subunit 1331, it is corresponding for calculating the program that minute mark is signed for regarding in sequence
The summation of program score value obtains minute mark label program score value summation;
Full-time decay factor computation subunit 1332, for being based on the first default computation rule, according to minute mark label program point
Value summation, minute mark sign for regarding the program total quantity in sequence, the program total quantity in history rating record and the first default decaying
The corresponding full-time decay factor of default label is calculated in coefficient;
N values obtain subelement 1333, for equal when there is the corresponding default label of continuous N number of program in history rating record
When identical, the N values, N >=2 are obtained;
The full-time bonus point factor obtains subelement 1334, for by N values and the first default bonus point multiplication, obtaining pre- bidding
Sign the corresponding full-time bonus point factor.
As shown in Figure 10, in one embodiment of the invention, timesharing impact factor acquiring unit in Fig. 8 shown in Figure 10
1360 are additionally operable to execute the structure of the method and step in the embodiment corresponding to Fig. 5, including:
Timesharing minute mark label program score value summation obtains subelement 1361, signs for regarding the section in sequence for calculating timesharing minute mark
The summation of the corresponding program score value of mesh obtains timesharing minute mark label program score value summation;
Timesharing decay factor computation subunit 1362, for being based on the second default computation rule, according to timesharing minute mark label section
Mesh score value summation, timesharing minute mark sign for regarding the program total quantity in sequence, the program total quantity and second in history rating record
Default attenuation coefficient, is calculated the corresponding timesharing decay factor of default label;
M values obtain subelement 1363, and for working as, there are the corresponding default label of continuous N program is equal in timesharing rating sequence
When identical, the M values, M >=2 are obtained;
The timesharing bonus point factor obtains subelement 1364, for by M values and the second default bonus point multiplication, obtaining pre- bidding
Sign the corresponding timesharing bonus point factor.
In one embodiment of the invention, the recommendation program assignment module 1400 in Fig. 6 includes:
Public program recommendation list acquiring unit, for obtaining public program recommendation list;
Program recommendation list acquiring unit, for extracting all default labels pair from public program recommendation list
The program answered obtains each corresponding program recommendation list of default label;
Recommend assignment acquiring unit, for carrying out assignment according to the second preset rules to the program in program recommendation list,
Obtain the corresponding recommendation assignment of each program in public program recommendation list.
In one embodiment of the invention, the recommendation acquisition module 1500 in Fig. 6 further includes:
Recommendation score computing unit weighs the quantity of preset algorithm, minute mark label for presetting computation rule based on third
Weight, the bonus point factor, decay factor and recommendation assignment carry out integral operation, and the recommendation for obtaining program in public program recommendation list is commented
Point;
Recommendation acquiring unit is pushed away for corresponding to the arrangement public program according to the sequence of recommendation score from high to low
The program in list is recommended, recommendation is obtained.
From above-described embodiment it is found that by obtaining minute mark label weight, the bonus point factor and decay factor, realize continuous to user
The default label watched carries out bonus point, bonus point is carried out to the label of user's current interest, to make the recommendation for recommending user
Content more caters to the current interest of user, and according to preset period of time, is recorded to the history rating of user's difference preset period of time
It is divided, so as to obtain the interested recommendation of different periods user, user is avoided to miss interested content,
Meanwhile this commending contents algorithm calculates simply, it is only necessary to which simple addition subtraction multiplication and division calculating can be completed, and calculation amount is smaller, shortens
Operation time, operation efficiency is improved, user experience is optimized.
Embodiment 3:
The embodiment of the present invention additionally provides a kind of terminal device 11, including memory 111, processor 110 and is stored in
In memory 111 and the computer program 112 that can be run on processor 110, the processor 110 execute the computer journey
The step in each embodiment as described in example 1 above, such as step S101 shown in FIG. 1 to step S105 are realized when sequence 112.
Alternatively, the processor 110 is realized when executing the computer program 112 in each device embodiment as described in example 2 above
Each module function, such as module 1100 to 1500 shown in fig. 6 function.
The terminal device 11 can be that the calculating such as desktop PC, notebook, palm PC and cloud server are set
It is standby.The terminal device 11 may include, but be not limited only to, processor, memory.Such as the terminal device 11 can also include
Input-output equipment, network access equipment, bus etc..
Alleged processor 110 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 111 can be the internal storage unit of the terminal device 11, such as the hard disk of terminal device 11
Or memory.The memory 111 can also be on the External memory equipment of the terminal device 11, such as the terminal device 11
The plug-in type hard disk of outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD)
Card, flash card (Flash Card) etc..Further, the memory 11 can also both include the storage inside of terminal device 11
Unit also includes External memory equipment.The memory 111 is for storing the computer program 112 and the terminal device
Other programs needed for 11 and data.The memory 111, which can be also used for temporarily storing, have been exported or will export
Data.
Embodiment 4:
The embodiment of the present invention additionally provides a kind of computer readable storage medium, and computer-readable recording medium storage has meter
Calculation machine program 112 realizes the step in each embodiment as described in example 1 above, example when computer program is executed by processor
Step S101 to step S105 as shown in Figure 1.Alternatively, realizing such as embodiment 2 when the computer program is executed by processor
Described in each device embodiment in each module function, such as module 1100 to 1500 shown in fig. 6 function.
The computer program 112 can be stored in a computer readable storage medium, and the computer program 112 is in quilt
When processor 110 executes, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program 112 includes calculating
Machine program code, the computer program code can be source code form, object identification code form, executable file or it is certain in
Between form etc..The computer-readable medium may include:Any entity or dress of the computer program code can be carried
Set, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software
Distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according to making laws in jurisdiction
Requirement with patent practice carries out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, computer
Readable medium is including being not electric carrier signal and telecommunication signal.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.
Module or unit in system of the embodiment of the present invention can be combined, divided and deleted according to actual needs.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement etc., should all be included in the protection scope of the present invention made by within refreshing and principle.
Claims (10)
1. a kind of content recommendation method, which is characterized in that including:
Obtain the history rating record of user;
It is recorded according to the history rating, obtains preset period of time and the corresponding timesharing minute mark label weight of default label;
It is recorded according to the history rating, obtains the corresponding bonus point factor of the default label and decay factor;
The corresponding program recommendation list of the default label is obtained, and assignment is carried out to the program in the program recommendation list,
It obtains recommending assignment;
According to the timesharing minute mark label weight, the bonus point factor, the decay factor and the recommendation assignment, obtain in recommendation
Hold.
2. a kind of content recommendation method as described in claim 1, which is characterized in that it is described to be recorded according to the history rating,
Preset period of time and the corresponding timesharing minute mark label weight of default label are obtained, including:
The corresponding program of the preset period of time is extracted from history rating record, obtains timesharing rating sequence;
The corresponding program of the default label is extracted from the timesharing rating sequence, is obtained timesharing minute mark and is signed for regarding sequence;
The timesharing minute mark is signed for regard the program total quantity in sequence divided by the program total quantity in the timesharing rating sequence,
Obtain the timesharing minute mark label weight.
3. a kind of content recommendation method as described in claim 1, the bonus point factor includes that the full-time bonus point factor and timesharing add
Molecular group, the decay factor include full-time decay factor and timesharing decay factor;
It is described to be recorded according to the history rating, the corresponding bonus point factor of the default label and decay factor are obtained, including:
It is the program assignment in history rating record according to the first preset rules, obtains the corresponding program point of each program
Value;
The corresponding program of the default label is extracted from history rating record, minute mark is obtained and signs for regarding sequence;
It is signed for regarding sequence according to the program score value and the minute mark, corresponding described full-time of the default label is calculated
The bonus point factor and the full-time decay factor;
The corresponding program of the preset period of time is extracted from history rating record, obtains timesharing rating sequence;
The corresponding program of the default label is extracted from the timesharing rating sequence, is obtained timesharing minute mark and is signed for regarding sequence;
It is signed for regarding sequence according to the program score value, the timesharing rating sequence and the timesharing minute mark, be calculated described pre-
Bidding signs the corresponding timesharing bonus point factor and the timesharing decay factor.
4. a kind of content recommendation method as claimed in claim 3, which is characterized in that
It is described to be signed for regarding sequence according to the program score value and the minute mark, be calculated the full-time bonus point of the default label because
The full-time decay factor of the sub and described default label, including:
The summation that the minute mark signs for regarding the corresponding program score value of program in sequence is calculated, it is total to obtain minute mark label program score value
With;
Based on the first default computation rule, signed for regarding the section in sequence according to the minute mark label program score value summation, the minute mark
Mesh total quantity, the program total quantity in history rating record and the first default attenuation coefficient, are calculated the pre- bidding
Sign corresponding full-time decay factor;
When the default label all same corresponding in the presence of continuously N number of program in history rating record, the N is obtained
Value, N >=2;
By the N values and the first default bonus point multiplication, the corresponding full-time bonus point factor of the default label is obtained.
5. a kind of content recommendation method as claimed in claim 3, which is characterized in that
It is described to be signed for regarding sequence according to the program score value, the timesharing rating sequence and the timesharing minute mark, institute is calculated
The timesharing bonus point factor and the timesharing decay factor are stated, including:
The summation that the timesharing minute mark signs for regarding the corresponding program score value of program in sequence is calculated, timesharing minute mark label program is obtained
Score value summation;
Based on the second default computation rule, signed for regarding sequence according to the timesharing minute mark label program score value summation, the timesharing minute mark
Program total quantity in row, the program total quantity in history rating record and the second default attenuation coefficient, are calculated institute
State the corresponding timesharing decay factor of default label;
When the default label all same corresponding there are continuous N program in the timesharing rating sequence, the M is obtained
Value, M >=2;
By the M values and the described second default bonus point multiplication, the corresponding timesharing bonus point factor of the default label is obtained.
6. a kind of content recommendation method as described in claim 1, which is characterized in that the acquisition default label is corresponding
Program recommendation list, and assignment is carried out to the program in the program recommendation list, it obtains recommending assignment, including:
Obtain public program recommendation list;
The corresponding program of all default labels is extracted from the public program recommendation list, and it is described pre- to obtain each
Bidding signs the corresponding program recommendation list;
Assignment is carried out according to the second preset rules to the program in the program recommendation list, the public program is obtained and recommends row
The corresponding recommendation assignment of each program in table.
7. a kind of content recommendation method as claimed in claim 6, which is characterized in that described to be weighed according to the timesharing minute mark label
Weight, the bonus point factor, the decay factor and the recommendation assignment, obtain recommendation, including:
Computation rule is preset based on third, is assigned according to the timesharing minute mark label weight, the bonus point factor, decay factor and the recommendation
Value, is calculated the recommendation score of program in the public program recommendation list;
The program arranged in the public program recommendation list is corresponded to according to the sequence of recommendation score from high to low, is obtained in recommendation
Hold.
8. a kind of content recommendation system, which is characterized in that including:
History rating records acquisition module, and the history rating for obtaining user records;
Timesharing minute mark label Weight Acquisition module obtains preset period of time and default label for being recorded according to the history rating
Corresponding timesharing minute mark label weight;
Impact factor acquisition module obtains the corresponding bonus point factor of the default label for being recorded according to the history rating
And decay factor;
Recommend program assignment module, recommends for obtaining the corresponding program recommendation list of the default label, and to the program
Program in list carries out assignment, obtains recommending assignment;
Recommendation acquisition module, for according to the timesharing minute mark label weight, the bonus point factor, the decay factor and institute
Recommendation assignment is stated, recommendation is obtained.
9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 7 when executing the computer program
The step of any one content recommendation method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In the step of realization content recommendation method as described in any one of claim 1 to 7 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810032233.8A CN108363730B (en) | 2018-01-12 | 2018-01-12 | Content recommendation method, system and terminal equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810032233.8A CN108363730B (en) | 2018-01-12 | 2018-01-12 | Content recommendation method, system and terminal equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108363730A true CN108363730A (en) | 2018-08-03 |
CN108363730B CN108363730B (en) | 2020-11-06 |
Family
ID=63006105
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810032233.8A Active CN108363730B (en) | 2018-01-12 | 2018-01-12 | Content recommendation method, system and terminal equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108363730B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110309358A (en) * | 2018-03-27 | 2019-10-08 | 京东方科技集团股份有限公司 | A kind of resource recommendation method and system |
CN110598047A (en) * | 2019-08-22 | 2019-12-20 | 优地网络有限公司 | Movie and television information recommendation method and device, electronic equipment and storage medium |
CN111177562A (en) * | 2019-12-31 | 2020-05-19 | 中国银行股份有限公司 | Recommendation and sorting processing method and device for target objects and server |
CN111737561A (en) * | 2019-06-20 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Information pushing method and pushing system |
CN112052378A (en) * | 2019-10-15 | 2020-12-08 | 河南紫联物联网技术有限公司 | Intelligent terminal, and recommendation method and system for intelligent home application |
CN114302182A (en) * | 2021-12-28 | 2022-04-08 | 未来电视有限公司 | Television program pushing method, device, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090210907A1 (en) * | 2008-02-14 | 2009-08-20 | At&T Knowledge Ventures, L.P. | Method and system for recommending multimedia content |
US20100042608A1 (en) * | 2008-08-12 | 2010-02-18 | Kane Jr Francis J | System for obtaining recommendations from multiple recommenders |
CN102957969A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending program to IPTV (Internet protocol television) terminal user |
CN104102648A (en) * | 2013-04-07 | 2014-10-15 | 腾讯科技(深圳)有限公司 | User behavior data based interest recommending method and device |
CN104216885A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津)科技有限公司 | Recommending system and method with static and dynamic recommending reasons automatically combined |
CN105898421A (en) * | 2015-01-16 | 2016-08-24 | 何湘 | Network film and television program intelligent recommendation method and system |
-
2018
- 2018-01-12 CN CN201810032233.8A patent/CN108363730B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090210907A1 (en) * | 2008-02-14 | 2009-08-20 | At&T Knowledge Ventures, L.P. | Method and system for recommending multimedia content |
US20100042608A1 (en) * | 2008-08-12 | 2010-02-18 | Kane Jr Francis J | System for obtaining recommendations from multiple recommenders |
CN102957969A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending program to IPTV (Internet protocol television) terminal user |
CN104102648A (en) * | 2013-04-07 | 2014-10-15 | 腾讯科技(深圳)有限公司 | User behavior data based interest recommending method and device |
CN104216885A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津)科技有限公司 | Recommending system and method with static and dynamic recommending reasons automatically combined |
CN105898421A (en) * | 2015-01-16 | 2016-08-24 | 何湘 | Network film and television program intelligent recommendation method and system |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110309358A (en) * | 2018-03-27 | 2019-10-08 | 京东方科技集团股份有限公司 | A kind of resource recommendation method and system |
CN111737561A (en) * | 2019-06-20 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Information pushing method and pushing system |
CN110598047A (en) * | 2019-08-22 | 2019-12-20 | 优地网络有限公司 | Movie and television information recommendation method and device, electronic equipment and storage medium |
CN112052378A (en) * | 2019-10-15 | 2020-12-08 | 河南紫联物联网技术有限公司 | Intelligent terminal, and recommendation method and system for intelligent home application |
CN112052378B (en) * | 2019-10-15 | 2021-09-21 | 河南紫联物联网技术有限公司 | Intelligent terminal, and recommendation method and system for intelligent home application |
CN111177562A (en) * | 2019-12-31 | 2020-05-19 | 中国银行股份有限公司 | Recommendation and sorting processing method and device for target objects and server |
CN111177562B (en) * | 2019-12-31 | 2024-04-19 | 中国银行股份有限公司 | Recommendation ordering processing method and device for target object and server |
CN114302182A (en) * | 2021-12-28 | 2022-04-08 | 未来电视有限公司 | Television program pushing method, device, equipment and storage medium |
CN114302182B (en) * | 2021-12-28 | 2023-10-20 | 未来电视有限公司 | Push method, device, equipment and storage medium for television programs |
Also Published As
Publication number | Publication date |
---|---|
CN108363730B (en) | 2020-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108363730A (en) | A kind of content recommendation method, system and terminal device | |
CN110413877A (en) | A kind of resource recommendation method, device and electronic equipment | |
CN110418200A (en) | A kind of video recommendation method, device and terminal device | |
CN106604051A (en) | Live channel recommending method and device | |
CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
CN109829108B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
CN108536694A (en) | Estimation method, device and the terminal device of user preference | |
CN101162470A (en) | Video frequency advertisement recognition method based on layered matching | |
CN107360246A (en) | A kind of information push method and device, a kind of terminal and storage medium | |
CN106326391A (en) | Method and device for recommending multimedia resources | |
CN109511015A (en) | Multimedia resource recommended method, device, storage medium and equipment | |
CN110020149A (en) | Labeling processing method, device, terminal device and the medium of user information | |
CN110515904B (en) | Quality prediction model training method, quality prediction method and device for media file | |
CN109670848A (en) | Customer segmentation method, user equipment, storage medium and device based on big data | |
KR20090017268A (en) | Method for updating interest keyword of user and system for executing the method | |
CN107862532A (en) | A kind of user characteristics extracting method and relevant apparatus | |
CN109460519A (en) | Browse object recommendation method and device, storage medium, server | |
CN108629054A (en) | Community method for pushing, device, computer installation and computer readable storage medium | |
CN111104599A (en) | Method and apparatus for outputting information | |
CN106446149A (en) | Filtering method and device for notification message | |
CN110110206B (en) | Method, device, computing equipment and storage medium for mining and recommending relationships among articles | |
CN106980666A (en) | A kind of method and apparatus of recommendation video | |
CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
CN108804491A (en) | item recommendation method, device, computing device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |