CN109889918A - A kind of self-adapting regulation method of instructional video broadcasting speed - Google Patents

A kind of self-adapting regulation method of instructional video broadcasting speed Download PDF

Info

Publication number
CN109889918A
CN109889918A CN201910224284.5A CN201910224284A CN109889918A CN 109889918 A CN109889918 A CN 109889918A CN 201910224284 A CN201910224284 A CN 201910224284A CN 109889918 A CN109889918 A CN 109889918A
Authority
CN
China
Prior art keywords
speed
video
viewer
broadcasting speed
broadcasting
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
Application number
CN201910224284.5A
Other languages
Chinese (zh)
Other versions
CN109889918B (en
Inventor
于昊
袁博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Graduate School Tsinghua University
Original Assignee
Shenzhen Graduate School Tsinghua University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Graduate School Tsinghua University filed Critical Shenzhen Graduate School Tsinghua University
Priority to CN201910224284.5A priority Critical patent/CN109889918B/en
Publication of CN109889918A publication Critical patent/CN109889918A/en
Application granted granted Critical
Publication of CN109889918B publication Critical patent/CN109889918B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a kind of self-adapting regulation methods of instructional video broadcasting speed: utilizing T period of video and general information prime matrix, classification information prime matrix and the speed transfer parameter matrix of preset m broadcasting speed building video;The preview feedback of viewer is collected to sort out to viewer;Initial play speed is calculated according to viewer's type;According to the general information prime matrix and classification information prime matrix updated after speed transfer parameter matrix, the broadcasting speed of current slot and a upper viewer viewing in watching process, calculating broadcasting speed when current viewer watches subsequent time period becomes the probability of each speed in m speed;Current viewer is adjusted in the broadcasting speed of subsequent time period according to probability;The broadcasting speed path that current viewer watches video is generated after playing;It collects the feedback after class of viewer and basis is fed back after class and broadcasting speed path, update general information prime matrix and classification information prime matrix.

Description

A kind of self-adapting regulation method of instructional video broadcasting speed
Technical field
The present invention relates to a kind of self-adapting regulation methods of instructional video broadcasting speed, belong to computer application field.
Background technique
During by viewing video on-line study, the word speed for the person of giving lessons will affect understanding of the video viewers to material And learning enthusiasm.But the viewer with different Knowledge Base, different habits often has different need to the word speed for the person of giving lessons It asks.Moreover, course theme, teaching content type, Content Difficulty of the word speed of most preferably giving lessons also with corresponding section are closely bound up.
Existing video speed adjusting method majority needs viewer actively to play out speed adjustment in learning process. However in order to which the instruction word speed for the part for keeping Content Difficulty different is in suitable section always, speed is generally required repeatedly It adjusts, to be easy the study attention of dispersion viewer.Separately there are Part Methods to identify and monitor the word speed for the person of giving lessons, thus root According to the word speed adjust automatically broadcasting speed for the person of giving lessons, however this method has ignored difficulty or ease and the video viewers of course content Individual demand.
The disclosure of background above technology contents is only used for auxiliary and understands inventive concept and technical solution of the invention, not The prior art for necessarily belonging to present patent application shows above content in the applying date of present patent application in no tangible proof Before have disclosed in the case where, above-mentioned background technique should not be taken to evaluation the application novelty and creativeness.
Summary of the invention
It is a primary object of the present invention to be based on ant group algorithm, a kind of adaptive adjustment of instructional video broadcasting speed is proposed Method forms corresponding broadcasting speed path to every class viewer, to make to watch after classifying to video viewers Person dynamically adjusts video playout speed according to the broadcasting speed path corresponding to it during watching instructional video, real The adaptive adjustment of existing broadcasting speed is broadcast with needing viewer voluntarily to adjust when solving and watching online teaching video in the prior art The scheme of the problem of putting speed and influencing learning effect and the existing basis person of giving lessons word speed adjust automatically broadcasting speed is deposited Word speed can not adapt to different viewer's demands the problem of.
A kind of technical solution that the present invention is proposed for the above-mentioned purpose is as follows:
A kind of self-adapting regulation method of instructional video broadcasting speed, includes the following steps:
S1, the video is divided into T period, and presets m possible broadcasting speed v for each period1,v2, v3,…,vm
S2, using the m broadcasting speed of the T period and each period, construct the general information of the video Prime matrix M=(τt,j(n-1))T×m, classification information prime matrixAnd speed transfer parameter matrix MSpeedChange=(μij)m×m, the n-1 expression video, which has n-1 viewer, to be watched, n=1, style=1,2 when initial, 3 ..., k indicate the preset kind of viewer, i, j ∈ (v1,v2,v3,…,vm);Wherein: τt,j(n-1) indicate that the video has n- 1 viewer completes the general information element concentration that t-th of period broadcasting speed is j after watching;Indicate the view The classification information element concentration that t-th of period broadcasting speed is j after frequency has n-1 viewer to complete viewing;μijIndicate the view A possibility that broadcasting speed of frequency moves to j by the i factor;
S3, n-th of viewer is defined as current viewer, after collecting the pre-generated preview video of current viewer's viewing Preview feedback information, and current viewer is sorted out according to the preview feedback information, type is style (n);
S4, the type style (n) according to current viewer calculate current viewer and watch broadcasting for the 1st period video Put speedAnd make current viewer with speedStart to watch video;
S5, in watching process, according to speed transfer parameter matrix, current slot broadcasting speed and it is upper one viewing Person watches the general information prime matrix and classification information prime matrix updated after the video, and it is lower for the moment to calculate current viewer's viewing Between section video when broadcasting speed become the probability of each speed in the m broadcasting speed;
S6, current viewer is adjusted in the video playout speed of subsequent time period according to the probability;
S7, circulation step S5 and S6 generate the broadcasting speed path that current viewer watches the video after finishing playingWhereinT-th of period is watched for current viewer When broadcasting speed, t=1,2,3 ..., T;
S8, the feedback information after class for collecting current viewer, and according to the feedback information after class and its broadcasting speed road Diameter V (n) updates the general information prime matrix and the classification information prime matrix, and repeats step S3 to next viewer ~S8.
The self-adapting regulation method of instructional video broadcasting speed provided by above-mentioned technical proposal of the present invention can be automatically The characteristics of video viewers select suitable broadcasting speed path, have taken into account different type viewer and demand;In addition, also certain The problem of instruction word speed in the instructional video of part is not by design is compensated in degree, and there is practical application value.
Detailed description of the invention
Fig. 1 is the self-adapting regulation method flow chart of the instructional video broadcasting speed of one embodiment of the invention;
Fig. 2 is visual broadcasting speed path profile in one embodiment of the invention.
Specific embodiment
The invention will be further described with specific embodiment with reference to the accompanying drawing.
A specific embodiment of the invention provides a kind of self-adapting regulation method of instructional video broadcasting speed, with reference to figure 1, this method comprises the following steps:
Step S1, the video is divided into T period, and presets m possible broadcasting speeds for each period v1,v2,v3,…,vm.In T period, the preceding T-1 period is to divide equally, and duration is tspace, it is assumed that the total duration of video is ttotal, then have: T=[ttotal/tspace]+1;[] indicates to be rounded the number in bracket.For each period, all in advance If v1,v2,v3,…,vm, for example, possible broadcasting speed of each period be 0.75,0.8,0.85 ... ..., 1.3,1.35, 1.4,1.45,1.5 }, m=16 in the example.It should be understood that those skilled in the art can be according to specific scene and need It asks, sets different tspaceValue, and correspond to different tspaceValue, in broadcasting speed set between best between friction speed Every setting also different from.
Step S2, using the m broadcasting speed of the T period and each period, the general of the video is constructed Pheromone Matrix M=(τt,j(n-1))T×m, classification information prime matrixAnd speed transfer parameter Matrix MSpeedChange=(μij)m×m, the n-1 expression video, which has n-1 viewer, to be watched, n=1, style=when initial 1,2,3 ..., k indicate the preset kind of viewer, i, j ∈ (v1,v2,v3,…,vm);Wherein: τt,j(n-1) video is indicated The general information element concentration that t-th of period broadcasting speed is j after having n-1 viewer to complete viewing;Indicate institute Stating video has n-1 viewer to complete the classification information element concentration that t-th of period broadcasting speed is j after watching;μijIndicate institute State the factor a possibility that broadcasting speed of video moves to j by i.Step S2 is to general information prime matrix and classification information element The step of matrix is initialized, in initialization step S2, also non-someone watches the video, i.e. n=1, for arbitrary t, J, style, τt,j(0)=1,In addition, the speed transfer parameter matrix meets:
Wherein, b is speed mobility threshold.
The present invention is based on the concept principle of ant group algorithm, proposes the ant group algorithm of aforementioned improved, by the tune of speed Turn over turns to routing problem, constructs the general information prime matrix M=(τ for calculating speed transformation probabilityt,j(n- 1))T×m, classification information prime matrixAnd speed transfer parameter matrix MSpeedChange= (μij)m×m
Step S3, defining n-th of viewer is current viewer, collects the pre-generated preview view of current viewer's viewing Preview feedback information after frequency, and current viewer is sorted out according to the preview feedback information, obtained type is style(n).For an online teaching video, the present invention generates a shorter preview video to the video in advance, and And viewer can only watch the preview video with default speed, it is therefore an objective to which one for obtaining viewer to the video word speed is preliminary Feedback, to classify to the viewer.Preview feedback includes that broadcasting speed feedback, language difficulty feedback and Content Difficulty are anti- Feedback.In a kind of specific example, broadcasting speed feeds back SR=-1,0,1 (respectively corresponding " relatively slow ", " moderate ", " very fast ");Language It says difficulty DL=-1,0,1 (respectively corresponding " simple ", " medium ", " difficulty ");Content Difficulty DC=-1,0,1 (respectively corresponds " letter List ", " medium ", " more difficult ").Using this feedback system, the type style of video viewers can be defined, such as the following table 1 institute Show:
The illustrative viewer's type of table 1 and its class condition
Viewer's type style Condition
1 (needing very jogging speed) SR=1&DC+DL > 0
2 (needing slower speed) SR=1&DC+DL≤0, or SR=0&DC+DL=2
3 (needing moderate speed) SR=0&-2 < DC+DL < 2
4 (needing fast speed) SR=-1&DC+DL≤0, or SR=0&DC+DL=-2
5 (needing speed quickly) SR=-1&DC+DL < 0
So that the definition of five seed types and its class condition of viewer are given to above-mentioned example, for a viewer For, as long as submitting preview feedback after viewing preview video, can classify to the viewer.It should be understood that viewing Person's type and quantity are not limited to that the preview feedback of other dimensions can also be integrated cited by above-mentioned table 1, provide in above-mentioned table 1 Different types.
Step S4, according to the mode of step S3, it is determined that, can basis after type style (n) belonging to current viewer Style (n) calculates the broadcasting speed that current viewer watches the 1st period videoSpeed is initially watched, and Make current viewer with speedStart to watch video.It is the current of style (n) for type by taking above-mentioned table 1 as an example Viewer initially watches speedIt should be noted that initial velocity calculates public affairs herein Formula is not limited to that, can separately be set as the case may be, and the initial sight of all types of (style) viewers can also be directly specified See speed.
Step S5, it in watching process (in general, when some period of video will have been watched), is just moved according to speed Shifting parameter matrix, the broadcasting speed of current slot and a upper viewer watch the general information element square updated after the video Battle array and classification information prime matrix calculate the probability that subsequent time period is played with speed each in m broadcasting speed.Calculation formula is such as Under:
Wherein, α, β are weight parameter;q∈(v1,v2,v3,…,vm);Indicate subsequent time period (t+ 1 period) with the probability of speed q broadcasting;The broadcasting speed of current slot t
Step S6, the probability adjustment current viewer being calculated according to previous step is fast in the video playing of subsequent time period Degree carries out stochastic transformation according to the probability in the video playout speed of subsequent time period to current viewer.
Step S7, circulation step S5 and S6 generates the broadcasting speed that current viewer watches the video after finishing playing PathWhereinWhen being t-th of current viewer's viewing Between section when broadcasting speed, t=1,2,3 ..., T.
Step S8, after complete video of viewer's viewing, the feedback information after class of current viewer is collected, and according to The feedback information after class and its broadcasting speed path V (n) update the general information prime matrix and the classification information element square Battle array, and step S3~S8 is repeated to next viewer.Specific update method is as follows:
Firstly, obtaining current viewer to comprehensive marking Score (n) of the whole broadcasting speed of the video, and respectively Calculate whole viewer's average score Score until currentaveAnd the average score of all viewers of same typeThen Score is utilizedaveWithCalculate undated parameter δ (n) and δstyle(n)(n):
Then, above-mentioned undated parameter is recycled to update the general information prime matrix and the classification information prime matrix, is updated Formula are as follows:
Wherein:
Wherein, c0、c1The update constant of respectively described general information prime matrix and the classification information prime matrix;ρ0、ρ1Respectively For the attenuation rate of the general information prime matrix and the classification information prime matrix.That is, often there is viewer's viewing The complete video exactly completes an iteration, and every iteration is primary, the general information prime matrix and classification information prime matrix of the video It is updated.
As the viewer of video is continuously increased, each type of broadcasting speed path will restrain, at this time can be to various Broadcasting speed path corresponding to type is visualized, specifically, institute is visual for five seed types shown in the table 1 A kind of exemplary broadcasting speed path is as shown in Figure 2.The person of giving lessons of the subsequent video can be according to the visual broadcasting speed Path and the feedback after class of viewer etc., come transfer parameter matrix of regulating the speed, the m possible broadcasting speeds and described Speed mobility threshold etc..
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that Specific implementation of the invention is only limited to these instructions.For those skilled in the art to which the present invention belongs, it is not taking off Under the premise of from present inventive concept, several equivalent substitute or obvious modifications can also be made, and performance or use is identical, all answered When being considered as belonging to protection scope of the present invention.

Claims (10)

1. a kind of self-adapting regulation method of instructional video broadcasting speed, which comprises the steps of:
S1, the video is divided into T period, and presets m possible broadcasting speed v for each period1,v2, v3,…,vm
S2, using the m broadcasting speed of the T period and each period, construct the general information element square of the video Battle array M=(τt,j(n-1))T×m, classification information prime matrixAnd speed transfer parameter matrix MSpeedChange=(μij)m×m, the n-1 expression video, which has n-1 viewer, to be watched, n=1, style=1,2 when initial, 3 ..., k indicate the preset kind of viewer, i, j ∈ (v1,v2,v3,…,vm);Wherein: τt,j(n-1) indicate that the video has n- 1 viewer completes the general information element concentration that t-th of period broadcasting speed is j after watching;Indicate the view The classification information element concentration that t-th of period broadcasting speed is j after frequency has n-1 viewer to complete viewing;μijIndicate the view A possibility that broadcasting speed of frequency moves to j by the i factor;
S3, n-th of viewer is defined as current viewer, it is pre- after collecting the pre-generated preview video of current viewer's viewing It lookes at feedback information, and current viewer is sorted out according to the preview feedback information, type is style (n);
S4, the type style (n) according to current viewer calculate the broadcasting speed that current viewer watches the 1st period video DegreeAnd make current viewer with speedStart to watch video;
S5, in watching process, according to speed transfer parameter matrix, the broadcasting speed of current slot and a upper viewer see It sees the general information prime matrix and classification information prime matrix updated after the video, calculates current viewer and watch subsequent time period Broadcasting speed becomes the probability of each speed in the m broadcasting speed when video;
S6, current viewer is adjusted in the video playout speed of subsequent time period according to the probability;
S7, circulation step S5 and S6 generate the broadcasting speed path that current viewer watches the video after finishing playingWhereinT-th of period is watched for current viewer When broadcasting speed, t=1,2,3 ..., T;
S8, the feedback information after class for collecting current viewer, and according to the feedback information after class and its broadcasting speed path V (n), update the general information prime matrix and the classification information prime matrix, and to next viewer repeat step S3~ S8。
2. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S1 is specific It include: the total duration t for obtaining the videototalAnd be divided into T period, and preceding T-1 every section of the period when Length is tspace
Wherein, ttotal、T、tspaceThe relationship of three is T=[ttotal/tspace]+1。
3. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S2 is initial When change, for arbitrary t, j, style, τt,j(0)=1,
4. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that the speed is moved Shifting parameter matrix meets:
Wherein, b is speed mobility threshold.
5. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S3 is specific Include:
S31, the preview video for generating the video;
S32, collection current viewer watch the preview feedback information after the preview video, the preview feedback with default speed Information includes broadcasting speed feedback, language difficulty feedback and Content Difficulty feedback;
S33, current viewer is sorted out according to broadcasting speed feedback, language difficulty feedback and Content Difficulty feedback.
6. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S5 packet It includes:
If the broadcasting speed of current slot tSpeed is played when then current viewer watches subsequent time period video DegreeFor the probability of each speed in the m broadcasting speedAre as follows:
Wherein, α, β are weight parameter;q∈(v1,v2,v3,…,vm)。
7. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S8 packet It includes:
S81, current viewer is obtained to comprehensive marking Score (n) of the whole broadcasting speed of the video, and calculate separately and cut Whole viewer's average score Score until currentaveAnd the average score of all viewers of same type
S82, Score is utilizedaveWithCalculate undated parameter δ (n) and δstyle(n)(n):
S83, the undated parameter δ (n) and δ are utilizedstyle(n)(n) the general information prime matrix and classification information element are updated Matrix, more new formula are as follows:
τt,j(n)=ρ0·τt,j(n-1)+Δτt,j(n),
Wherein:
Wherein, c0、c1The respectively described general information The update constant of prime matrix and the classification information prime matrix;ρ0、ρ1The respectively described general information prime matrix and classification letter Cease the attenuation rate of prime matrix.
8. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that further include following Step:
S9, when increasing with viewer, when the convergence of broadcasting speed path corresponding to each type, to broadcasting speed path into Row visualization, obtains the broadcasting speed path curve figure of the different type viewer of the video.
9. the self-adapting regulation method of instructional video broadcasting speed as claimed in claim 4, which is characterized in that further include giving lessons Person's set-up procedure: after class feedback and the broadcasting speed path of the person of giving lessons of the video by comparison viewer, to institute It states speed transfer parameter matrix, the m possible broadcasting speeds and the speed mobility threshold is adjusted.
10. the self-adapting regulation method of instructional video broadcasting speed as described in claim 1, which is characterized in that step S6 tool Body includes: to carry out stochastic transformation according to the probability in the video playout speed of subsequent time period to current viewer.
CN201910224284.5A 2019-03-22 2019-03-22 Self-adaptive adjustment method for teaching video playing speed Active CN109889918B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910224284.5A CN109889918B (en) 2019-03-22 2019-03-22 Self-adaptive adjustment method for teaching video playing speed

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910224284.5A CN109889918B (en) 2019-03-22 2019-03-22 Self-adaptive adjustment method for teaching video playing speed

Publications (2)

Publication Number Publication Date
CN109889918A true CN109889918A (en) 2019-06-14
CN109889918B CN109889918B (en) 2020-12-29

Family

ID=66933825

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910224284.5A Active CN109889918B (en) 2019-03-22 2019-03-22 Self-adaptive adjustment method for teaching video playing speed

Country Status (1)

Country Link
CN (1) CN109889918B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113012506A (en) * 2021-03-01 2021-06-22 深圳市微幼科技有限公司 Interactive teaching system based on big data
WO2022134690A1 (en) * 2020-12-23 2022-06-30 上海哔哩哔哩科技有限公司 Playback control method and device
CN115119066A (en) * 2022-06-30 2022-09-27 武汉美和易思数字科技有限公司 Teaching video interaction method and system based on dynamic weight

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104811798A (en) * 2015-04-17 2015-07-29 广东欧珀移动通信有限公司 Method and device for regulating video playing speed
US20150333951A1 (en) * 2014-05-19 2015-11-19 Samsung Electronics Co., Ltd. Content playback method and electronic device implementing the same
CN107105314A (en) * 2017-05-12 2017-08-29 北京小米移动软件有限公司 Video broadcasting method and device
US20170347135A1 (en) * 2016-05-24 2017-11-30 Sonic Ip, Inc. Systems and Methods for Providing Variable Speeds in a Trick-Play Mode
CN107888948A (en) * 2017-11-07 2018-04-06 北京小米移动软件有限公司 Determine method and device, the electronic equipment of video file broadcasting speed
CN108966012A (en) * 2018-07-18 2018-12-07 北京奇艺世纪科技有限公司 A kind of video playing rate determination method, device and electronic equipment
CN109309880A (en) * 2018-10-08 2019-02-05 腾讯科技(深圳)有限公司 Video broadcasting method, device, computer equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150333951A1 (en) * 2014-05-19 2015-11-19 Samsung Electronics Co., Ltd. Content playback method and electronic device implementing the same
CN104811798A (en) * 2015-04-17 2015-07-29 广东欧珀移动通信有限公司 Method and device for regulating video playing speed
US20170347135A1 (en) * 2016-05-24 2017-11-30 Sonic Ip, Inc. Systems and Methods for Providing Variable Speeds in a Trick-Play Mode
CN107105314A (en) * 2017-05-12 2017-08-29 北京小米移动软件有限公司 Video broadcasting method and device
CN107888948A (en) * 2017-11-07 2018-04-06 北京小米移动软件有限公司 Determine method and device, the electronic equipment of video file broadcasting speed
CN108966012A (en) * 2018-07-18 2018-12-07 北京奇艺世纪科技有限公司 A kind of video playing rate determination method, device and electronic equipment
CN109309880A (en) * 2018-10-08 2019-02-05 腾讯科技(深圳)有限公司 Video broadcasting method, device, computer equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
K.A. PEKER;A. DIVAKARAN: "Adaptive fast playback-based video skimming using a compressed-domain visual complexity measure", 《2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)》 *
刘莉: "可视化技术在工程类课程教学中的可用性研究", 《万方学位论文》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022134690A1 (en) * 2020-12-23 2022-06-30 上海哔哩哔哩科技有限公司 Playback control method and device
CN113012506A (en) * 2021-03-01 2021-06-22 深圳市微幼科技有限公司 Interactive teaching system based on big data
CN115119066A (en) * 2022-06-30 2022-09-27 武汉美和易思数字科技有限公司 Teaching video interaction method and system based on dynamic weight
CN115119066B (en) * 2022-06-30 2024-03-29 武汉美和易思数字科技有限公司 Teaching video interaction method and system based on dynamic weights

Also Published As

Publication number Publication date
CN109889918B (en) 2020-12-29

Similar Documents

Publication Publication Date Title
CN109889918A (en) A kind of self-adapting regulation method of instructional video broadcasting speed
CN104462383B (en) A kind of film based on a variety of behavior feedbacks of user recommends method
CN104081429B (en) Video recommendations based on video co-occurrence statistics
CN105721899B (en) A kind of method and system of video quality score
CN105653683B (en) Personalized recommendation method and device
WO2004017178A2 (en) Statistical personalized recommendation system
CN105744370A (en) Radio and television system based on group viewing behaviors and personalized program recommendation method thereof
CN104053112B (en) A kind of audiphone tests method of completing the square certainly
CN109218744A (en) A kind of adaptive UAV Video of bit rate based on DRL spreads transmission method
JP2003526290A (en) Method and apparatus for displaying television program recommendations
CN1739106A (en) Individual recommender profile modification using profiles of others
CN110059221B (en) Video recommendation method, electronic device and computer readable storage medium
CN105975496A (en) Music recommendation method and device based on context sensing
CN109816438A (en) Information-pushing method and device
CN109977409A (en) A kind of intelligent expression recommended method and system based on user&#39;s chat habit
CN114595831A (en) Federal learning method integrating adaptive weight distribution and personalized differential privacy
CN109731291A (en) A kind of dynamic adjusting method and system of rehabilitation game
CN110030704A (en) Control method, device, storage medium and the air-conditioning of air-conditioning
CN110781377A (en) Article recommendation method and device
CN113132765A (en) Code rate decision model training method and device, electronic equipment and storage medium
JPWO2002061619A1 (en) Ad distribution system
CN107277580A (en) A kind of method that the TV programme to be played back are cached on mobile phone
CN110619447B (en) Anchor evaluation method, device, equipment and storage medium
CN112199611A (en) Intelligent scenic spot recommendation method based on AIoT and computer vision
CN112365447B (en) Multidimensional movie and television scoring method

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