CN110096613A - A kind of video recommendation method, device, electronic equipment and storage medium - Google Patents
A kind of video recommendation method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110096613A CN110096613A CN201910293787.8A CN201910293787A CN110096613A CN 110096613 A CN110096613 A CN 110096613A CN 201910293787 A CN201910293787 A CN 201910293787A CN 110096613 A CN110096613 A CN 110096613A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- ranking results
- label
- mood
- 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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention provides a kind of video recommendation method, device, electronic equipment and storage mediums, wherein, video recommendation method includes: the mood label for obtaining each video, wherein, mood label is reflecting video on the label of influence caused by user emotion, and the principle of the first preset times is not more than by the number that identical mood label continuously occurs, the video is ranked up, the first video ranking results that user emotion can be caused to change are obtained, according to the first video ranking results, recommend video.Video is recommended to client using technical solution provided in an embodiment of the present invention, it is possible to reduce user is continuously in the phenomenon in extreme emotion, concentrates the attention of user more, to increase the duration that user uses Video Applications.
Description
Technical field
The present invention relates to Internet technical fields, more particularly to a kind of video recommendation method, device, electronic equipment and deposit
Storage media.
Background technique
As mobile terminal is more more and more universal, all kinds of Video Applications become more and more popular in the terminal.Video Applications
Server can recommend a series of video to the client of Video Applications, after user opens Video Applications in the client,
Each video of server recommendation can successively be watched.For example, user can pass through after being mounted with short Video Applications in terminal
Each short-sighted frequency that the server of short Video Applications is recommended to the client of short Video Applications is successively watched in the operations such as sliding.
In the prior art, Video Applications are to make user's stay longer in this application, it will usually which recommending to user should
User is possible to interested video.
However, inventor has found in the implementation of the present invention, at least there are the following problems for the prior art: when for a long time
When continuing video interested to user recommended user, it is easy to so that user extreme emotion occurs and (keeps excited shape as lasting
State), thus easily lead to it is absent minded, generate it is tired, it is easy to so that user is closed the application so that user using view
The duration of frequency application shortens.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of video recommendation method, device, electronic equipment and storage medium, with
Increase the duration that user uses Video Applications.Specific technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of video recommendation methods, which comprises
Obtain the mood label of each video, wherein the mood label is reflecting video to shadow caused by user emotion
Loud label；
It is not more than the principle of the first preset times by the number that identical mood label continuously occurs, the video is arranged
Sequence obtains the first video ranking results that user emotion can be caused to change；
According to the first video ranking results, recommend video.
Optionally, before described the step of being ranked up the video, the method also includes:
Obtain the broadcasting record that user plays the video；
It is recorded according to the broadcasting, determines that the user likes degree to the video；
Correspondingly, the number continuously occurred by identical mood label is not more than the principle of the first preset times, by institute
It states video to be ranked up, obtains the first video ranking results that user emotion can be caused to change, comprising:
Degree is liked to the video according to the user, the number continuously occurred based on identical mood label is not more than
The principle of first preset times is ranked up the video, obtains the first video ranking results.
Optionally, described that degree is liked to the video according to the user, continuously occurred based on identical mood label
Number be not more than the first preset times principle, the video is ranked up, the first video ranking results are obtained, comprising:
The sequence of degree from high to low is liked to the video according to the user, the video is ranked up, is obtained
To the second video ranking results；
The number continuously occurred based on identical mood label is not more than the principle of the first preset times, carries out to target video
Sequence adjustment, obtains the first video ranking results, wherein the target video are as follows: the company in the second video ranking results
The video of continuous arrangement and the user to the difference for liking degree of corresponding video within a preset range.
Optionally, the type of the mood label includes: the type and expression for indicating video and user's attention being caused to be concentrated
Video causes the scatterbrained type of user；
The number continuously occurred by identical mood label be not more than the first preset times principle, by the video into
Row sequence, obtains the first video ranking results that user emotion can be caused to change, comprising:
Obtain the queueing discipline of all types of mood labels, wherein the mood label of same type connects in the queueing discipline
The continuous number occurred is not more than the second preset times；
According to the queueing discipline of all types of mood labels, and it is little based on the number that identical mood label continuously occurs
In the principle of the first preset times, the video is ranked up, obtains the first video ranking results.
Optionally, described according to the first video ranking results, after recommending video, the method also includes:
Obtain the user experience information that user watches recommended video；
According to the user experience information, judge whether to adjust the first video ranking results；
If it is, adjustment the first video ranking results, and press the first video ranking results adjusted, Xiang Suoshu
User recommends video, and the step of executing the user experience information for obtaining the recommended video of user's viewing.
Second aspect, the embodiment of the invention also provides a kind of video recommendations device, described device includes:
Label acquiring unit, for obtaining the mood label of each video, wherein the mood label be reflecting video to
The label influenced caused by the mood of family；
Video sequencing unit, the number for continuously occurring by identical mood label are not more than the original of the first preset times
Then, the video is ranked up, obtains the first video ranking results that user emotion can be caused to change；
Video recommendations unit, for recommending video according to the first video ranking results.
Optionally, described device further include:
Acquiring unit is recorded, the broadcasting record of the video is played for obtaining user；
Like extent determination unit, for recording according to the broadcasting, determines that the user likes journey to the video
Degree；
Correspondingly, the video sequencing unit, is specifically used for: according to the user to the degree of liking of the video, base
It is not more than the principle of the first preset times in the number that identical mood label continuously occurs, the video is ranked up, is obtained
First video ranking results.
Optionally, the video sequencing unit, comprising:
First video sorting subunit, for liking degree from high to low suitable to the video according to the user
Sequence is ranked up the video, obtains the second video ranking results；
Video adjusts subelement, and the number for continuously being occurred based on identical mood label is no more than the first preset times
Principle is ranked up adjustment to target video, obtains the first video ranking results, wherein the target video are as follows: described second
Continuous arrangement and the user in video ranking results to the difference for liking degree of corresponding video within a preset range
Video.
Optionally, the type of the mood label includes: the type and expression for indicating video and user's attention being caused to be concentrated
Video causes the scatterbrained type of user；
The video sequencing unit, comprising:
Rule obtains subelement, for obtaining the queueing discipline of all types of mood labels, wherein phase in the queueing discipline
The number that the mood label of same type continuously occurs is not more than the second preset times；
Second video sorting subunit for the queueing discipline according to all types of mood labels, and is based on mutually sympathizing with
The number that thread label continuously occurs is not more than the principle of the first preset times, is ranked up to the video, obtains the first video
Ranking results.
Optionally, described device further include:
Experience information acquiring unit is pushed away for after the video recommendations unit recommends video, obtaining user's viewing
The user experience information for the video recommended；
Judging unit is adjusted, adjusts the first video sequence knot for judging whether according to the user experience information
Fruit；
Rule adjustment unit, for adjusting first video when the judging result of the adjustment judging unit is to be
Ranking results, and the first video ranking results adjusted are pressed, Xiang Suoshu user recommends video, and executes the acquisition user
The step of watching the user experience information of recommended video.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, including processor, communication interface, memory and
Communication bus, wherein the processor, the communication interface, the memory complete mutual communication by the bus；
The memory, for storing computer program；The processor, it is real for executing the program stored on the memory
The existing any method and step of first aspect.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, storage in the storage medium
There is computer program, first aspect any step is realized when the computer program is executed by processor.
5th aspect, the embodiment of the invention provides a kind of computer program products comprising instruction, when it is in computer
When upper operation, so that computer executes any method and step of first aspect.
In video recommendations scheme provided in an embodiment of the present invention, electronic equipment is continuously gone out each video by identical mood label
Existing number is ranked up no more than the principle of the first preset times, obtains the first video that user emotion can be caused to change sequence
As a result, recommend video according still further to the first video ranking results, since the first video ranking results can cause user emotion to change,
Avoid user from being in same mood for a long time and generate it is tired, in this way, by each video in the first video ranking results
The each video of sort recommendations, so that it may influence the emotional change of user by the video played, reduce user and persistently locate
Phenomenon in extreme emotion increases the possibility that user stops longer duration.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described.
Fig. 1 is the first flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 2 is second of flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 3 is the third flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of video recommendations device provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of electronic equipment provided in an embodiment of the present invention；
Graph of relation of the Fig. 6 between irritation level and user's attention；
Fig. 7 is video playing position and the graph of relation to user's irritation level.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description.
Persistently there is the phenomenon that extreme emotion to reduce user, the attention intensity of user is improved, to increase
User uses the duration of Video Applications, and the embodiment of the invention provides a kind of video recommendation method, device, electronic equipment and storages
Medium.
Video recommendation method is provided for the embodiments of the invention first below to be introduced.
It should be noted that video recommendation method provided by the embodiment of the present invention can be, but not limited to answer applied to video
In.
The executing subject of video recommendation method provided in an embodiment of the present invention can be electronic equipment, and the electronic equipment is for example
It can be, but not limited to be server, as shown in Figure 1, method includes the following steps:
S110: the mood label of each video is obtained.
Video in step S110 both can be all videos stored in server, can also be all in server
Video to be recommended.
Above-mentioned mood label is reflecting video on the label of influence produced by the mood of user.If there are multiple feelings in video
Thread label then stores the period of the corresponding video clip of difference mood label in the video.
In one embodiment of the present of invention, above-mentioned mood label can be the mood of first dimension such as glad, sad, terrified
Label, above-mentioned mood label may be the mood label of fierce second dimension such as releive, and can also be the mood of other dimensions
Label.For example, the mood that family usually can be used in the video is more releived, and view is worked as when the mood label of video is " releiving "
When the mood label of frequency is " fierceness ", the mood which usually can be used family is more fierce.
In one embodiment, the mood label of each video can be obtained in the following manner: the video of each video is believed
Breath input label trained in advance determines in model, determines mood label, obtains the mood label of each video；Wherein, above-mentioned mark
It signs and determines that model is, according to the video information of the mark mood label of Sample video, Sample video, what training obtained is used for as view
Frequency determines the model of label.Determine model by label to obtain the mood label of video, can it is more convenient, be quickly obtained it is each
The mood label of video.In another embodiment, also it is available manually determine each video mood label.
Above-mentioned video information may include at least one of following: the music information of video, the hue information of video, video
Plot information.Above-mentioned video information can also include the other information of video, and the embodiment of the present invention does not limit specifically.
In a specific embodiment, it can train in the following way and obtain above-mentioned label and determine model: by sample
The video information of video is inputted to training pattern, obtains the output mood label of Sample video；With the mark mood of Sample video
On the basis of label, according to the difference between the output mood label of Sample video and the mark mood label of Sample video, adjustment
To the model parameter of training pattern, the training for treating training pattern is realized, and will be true as label to training pattern after training
Cover half type.
S120: it is not more than the principle of the first preset times by the number that identical mood label continuously occurs, by above-mentioned video
It is ranked up, obtains the first video ranking results that user emotion can be caused to change.
Above-mentioned first preset times are time for being not easy to cause user's dispersion attention, user emotion can be caused to change
Number.First preset times are also possible to be become according to the mood of user's sets itself either the empirical value that technical staff sets
The setting of change degree.
Wherein, the first preset times are positively correlated with the easy degree for causing user emotion to change, in order to cause user emotion
Variation, the value of the first preset times can take lesser value.For example, above-mentioned first preset times for example can be in 1~5
Any number, is also possible to other numbers for being not easy to cause user's dispersion attention, and the embodiment of the present invention does not limit specifically.?
In the embodiment of the present invention, when the first preset times are smaller, more hold according to the first video ranking results video recommended to the user
Easily cause the emotional change of user.For example, the first preset times can be 2, at this point, the number that identical mood label continuously occurs
No more than 2 times.
For example, when the mood label of each video include it is fierce, releive, when the first preset times are 2, can according to releive,
It releives, is fierce, releive, releive, fierce ... sequence, each video is ranked up, it, can be with when the first preset times are 3
According to releive, releive, releive, it is fierce, fierce, releive, releive, releive, fierce, fierce ... sequence, each video is carried out
Sequence, when plaing in order each video according to above-mentioned ranking results, can make the mood of user it is gentle with it is nervous between replace change
Change.
In one embodiment, each video can be pressed feelings according to preset mood tagging arrangements rule by electronic equipment
Thread label is ranked up, wherein the number that identical mood label continuously occurs in preset mood tagging arrangements rule is little
In the first preset times, according to video corresponding to tactic mood label as defined in preset mood tagging arrangements rule
It can cause the emotional change of user.For example, preset mood tagging arrangements rule can for it is glad, common, sad, glad,
Commonly, in terror, it is glad, common, sad, glad, common, terrified ....
S130: according to above-mentioned first video ranking results, recommend each video.
In video recommendation method provided in an embodiment of the present invention, electronic equipment is continuously gone out each video by identical mood label
Existing number is ranked up no more than the principle of the first preset times, obtains the first video that user emotion can be caused to change sequence
As a result, recommend video according still further to the first video ranking results, since the first video ranking results can cause user emotion to change,
Avoid user from being in same mood for a long time and generate it is tired, in this way, by each video in the first video ranking results
The each video of sort recommendations, so that it may influence the emotional change of user by the video played, reduce user and persistently locate
Phenomenon in extreme emotion increases the possibility that user stops longer duration.
In one embodiment, as shown in Fig. 2, before step S120, above-mentioned video recommendation method can also include
Following steps S140~S150:
S140: the broadcasting record that user plays above-mentioned video is obtained.
Include in above-mentioned broadcasting record: user played the mark information of video, the mark information of each played video
It is: the information that the watched video is added in the operation that played video progress according to user.User when watching video,
Some operations may be carried out to the video of viewing, for example, skipping the behaviour such as video, collection video, comment video in watching process
Make, whether user, which likes the video, usually may determine that these operations of video from user.When user carries out video
After operation, corresponding mark information can be added to the video.According to the operation that user carries out video, mark information can be use
Whether whether the scoring at family played duration ratio, collected, by user by least one of user comment；Wherein, above-mentioned
Duration ratio is the duration that video is played and the ratio between the total duration of the video.
S150: it is recorded according to above-mentioned broadcasting, determines that user likes degree to above-mentioned video.
Electronic equipment can determine that user likes journey to all types of videos according to the mark information of each played video
Degree, likes degree to each video according to the user, determines that the user likes degree to each video.It is above-mentioned like degree can be with
It is indicated in the form of scoring, for example, user is 7 points, likes degree to modern class video to the degree of liking of ancient costume class video
For 4 points, the degree of liking of suspense class video is 8 points, is 3 points, to economy class video to the degree of liking of love class video
Liking degree is 5 points, then, if video belongs to ancient costume class and love class, the degree of liking of the video is 10 points, if video category
In modern class, suspense class and economy class, then the scoring of the video is 17 points.
Again alternatively, mark information can be the mark that user likes or do not like the video, the type is regarded according to user
The label of frequency liked or do not liked, determination like degree to such video.
Correspondingly, step S120, can be realized with S121 according to the following steps:
S121: degree is liked to above-mentioned video according to user, the number continuously occurred based on identical mood label is little
In the principle of the first preset times, above-mentioned video is ranked up, obtains the first video ranking results.
In above embodiment, what is obtained due to electronic equipment is that user emotion can be caused to change and by liking degree
The the first video ranking results to sort from high to low, in this way, successively being broadcast by the sequence of each video in the first video ranking results
Each video is put, the mood of user can be not only influenced with the video played, increases the duration that user uses Video Applications,
User can also be made successively to watch video according to from the sequence for liking not liking, make that user first watches is that oneself is liked
Video improves the quantity of the video of user's viewing, further increases the duration that user uses Video Applications.
In one implementation, step S121 can be realized according to the following steps:
The sequence of degree from high to low is liked to above-mentioned video according to user, above-mentioned video is ranked up, obtains
Two video ranking results；
The number continuously occurred based on identical mood label is not more than the principle of the first preset times, carries out to target video
Sequence adjustment, obtains the first video ranking results, wherein the target video are as follows: the continuous row in the second video ranking results
The video of column and user to the difference for liking degree of corresponding video within a preset range.
When it is above-mentioned to like degree be the scoring to video when, the above-mentioned difference for liking degree can be within a preset range to be commented
The difference divided is in preset fraction, for example, it may be the difference of scoring is also possible to other ranges in 2 points, 1 point or 0 point
Interior, the embodiment of the present invention does not limit specifically.
For example, being ranked up according to like degree sequence from high to low of the user to each video to each video, obtain
Second video ranking results are as follows: video 1 (fierceness, 9 points), video 2 (fierceness, 9 points), video 3 (fierceness, 8 points), video 4 (relax
It is slow, 8 points), video 5 (releiving, 8 points), video 6 (fierce, 7 points), if liking the difference of degree in 1 point, target video letter
Breath is 1~video of video 5, the first video ranking results obtained after adjustment is ranked up to target video information are as follows: video 1
(fierceness, 9 points), video 4 (releiving, 8 points), video 2 (fierceness, 9 points), video 5 (releiving, 8 points), video 3 (fierceness, 8 points), view
Frequently 6 (fierceness, 7 points).
It, can be in each video of played in order by each video in the first video ranking results by above embodiment
The close each video of degree of liking of user is playd in order into each video by the sequence that user emotion can be caused to change, in this way may be used
To be further reduced the phenomenon that video for making user extreme emotion occur continuously plays, further increases user and answered using video
Duration.
In one embodiment, the type of above-mentioned mood label may include: to indicate that video causes user's attention collection
In type and indicate video cause the scatterbrained type of user；
Above-mentioned steps S120 can be realized with S122~S123 according to the following steps:
S122: the queueing discipline of all types of mood labels is obtained, wherein the mood mark of same type in above-mentioned queueing discipline
The number continuously occurred is signed no more than the second preset times；
S123: according to the queueing discipline of all types of mood labels, and the number continuously occurred based on identical mood label is not
Greater than the principle of the first preset times, above-mentioned video is ranked up, obtains the first video ranking results.
Second preset times are also the number that user emotion can be caused to change.Similarly, the second preset times both can be with
It is the empirical value of technical staff's setting, is also possible to according to the setting of the emotional change degree of user's sets itself.
Wherein, the second preset times are positively correlated with the easy degree for causing user emotion to change, in order to cause user emotion
Variation, the value of the second preset times can take lesser value.Second preset times can be equal with the first preset times, can also
To differ with the first preset times, the embodiment of the present invention is not limited specifically, for example, the second preset times for example can be in 1~5
Any number, be also possible to other can cause user emotion change number.In embodiments of the present invention, when second is default
Number gets over hour, and the emotional change of user is more easily caused according to the first video ranking results video recommended to the user.For example,
Second preset times can be 2, at this point, the number that same type mood label continuously occurs is no more than 2 times.
In the present embodiment, indicate that the mood label for the type that video causes user's attention to be concentrated can be expression view
Frequency makes user not allow the mood label for being also easy to produce extreme emotion, such as the moods label such as may is that and releive, is glad, is common；It indicates
Video, which causes the mood label of the scatterbrained type of user can be, indicates that video makes user be easy to produce extreme emotion
Mood label, such as may is that the moods labels such as fierce, terrified, sadness.Other tools also can be set in those skilled in the art
The mood label of body, the embodiment of the present invention do not limit specifically.
The queueing discipline of all types of mood labels may include: all types of mood labels put in order and arrangement pitch.
For example, indicating the mood label for the type that video causes user's attention to be concentrated are as follows: it is common, glad, indicate that video causes user
The mood label of scatterbrained type are as follows: terrified, sad, arrangement pitch are as follows: every two indicates that video causes user to infuse
Two, interval causes the mood label of the scatterbrained type of user, arrangement between the mood label for the type that meaning power is concentrated
Sequentially are as follows: indicate the mood label for the type that video causes user's attention to be concentrated causes user's attention not followed by one
The mood label of the type of concentration, then queueing discipline can be with are as follows: common, terrified, sad, glad, terrified, sad, common, frightened
Probably, sad, glad, terrified, sad ..., those skilled in the art can also according to the actual situation, according to the feelings of same type
The number that thread label continuously occurs is not more than the principle of the second preset times, sets other arrangement rule of all types of mood labels
Then, the embodiment of the present invention does not limit specifically.
In a specific embodiment, step S123 can be realized according to the following steps: according to all types of mood labels
Queueing discipline is ranked up above-mentioned video, obtains third video ranking results；Time continuously occurred based on identical mood label
Number is not more than the principle of the first preset times, is ranked up adjustment to each video in the first video ranking results.
Each video is ranked up by mood label according to the queueing discipline of all types of mood labels of acquisition, it can be faster
Speed is easily ranked up each video, keeps video sequence efficiency higher, to keep video recommendations more efficient, while may be used also
So that different types of intervals of video plays, it is further reduced the phenomenon that user is continuously in extreme emotion, makes user's
Attention is more concentrated, to increase the duration that user uses Video Applications.
In one embodiment, as shown in figure 3, after step s 130, the method can also include the following steps
S160~S180:
S160: the user experience information that user watches recommended video is obtained；
S170: according to above-mentioned user experience information, judge whether to adjust above-mentioned first video ranking results；
S180: if the judging result of step S170 be it is yes, adjust above-mentioned first video ranking results, and by adjustment after
The first video ranking results, to user recommend video, and execute step S160 performed by step.
Above-mentioned user experience information, characterization user watch the letter of the experience of video according to above-mentioned first video ranking results
Breath.In the present embodiment, user experience information can be with are as follows: user's viewing is recommended to regard according to above-mentioned first video ranking results
When frequency, the quantity for the video that the duration of user's first use Video Applications or user are once watched.
If user experience information are as follows: when user watches video recommended according to above-mentioned first video ranking results, Yong Huyi
The secondary duration using Video Applications, then in step S170, whether electronic equipment can be greater than preset duration according to above-mentioned duration, sentence
Disconnected whether to need to adjust above-mentioned first video ranking results, if being not more than preset duration, judgement needs to adjust above-mentioned first
Video ranking results then determine not needing to adjust above-mentioned first video ranking results if it is greater than preset duration.
Electronic equipment adjusts above-mentioned first video ranking results, can be the arrangement pitch for changing each mood label and/or
It puts in order.Specifically, the available user's history of electronic equipment plays record, broadcasting in record is played according to the history of acquisition
Sequence is put forward to adjust the first video ranking results, so that suitable according to the corresponding video playing of the first video ranking results adjusted
When sequence plays video, user experience can be improved.
If what the user experience information obtained was reflected is the poor information of user experience, at this point, adjustment arrangement rule
Then, until the available user of queueing discipline adjusted preferably experiences, in this way, can be according to the arrangement of better user experience
Rule is ranked up each video, to further increase the duration that user uses Video Applications.Herein either with
Machine adjusts queueing discipline, is also possible to successively select from preset queueing discipline.
In one embodiment, the type of above-mentioned mood label may include: the first kind and Second Type；The first kind
Type are as follows: indicate the type that video causes user's attention to be concentrated, Second Type are as follows: indicate that video causes user absent minded
Type；
Above-mentioned steps S120 can be realized according to the following steps:
Obtain the queueing discipline of all types of mood labels, wherein the mood label of Second Type connects in above-mentioned queueing discipline
The continuous number occurred is not more than third preset times；
It is not more than the original of the first preset times according to above-mentioned queueing discipline and by the number that identical mood label continuously occurs
Then each video is ranked up, obtains the first video ranking results.
Since the attention of user is usually related to the irritation level that user is subject to, as shown in fig. 6, the stimulation that user is subject to
It is horizontal too high or too low, it easily causes that user is absent minded, when the irritation level that user is subject to is medium, is easy to make
User's attention is more concentrated.Therefore, the corresponding mood label of the above-mentioned first kind specifically may is that indicate video make user by
The mood label of medium stimulation, the corresponding mood label of above-mentioned Second Type specifically may is that indicate video make user by
The mood label of high and too low stimulation.It may is that user for example by the mood label of excessively high and too low stimulation wild with joy, emerging
Put forth energy, in terror, it is sad, lose heart, flat etc., may is that user for example by the mood label of medium stimulation glad, happy, pleased
Happy, open-minded etc..
Above-mentioned third preset times are the number for being not easy to cause user's dispersion attention.In order to collect user's attention more
In, the value of third preset times can take lesser value.Above-mentioned third preset times for example can be any time in 1~3
Number, is also possible to other numbers for being not easy to cause user's dispersion attention.In embodiments of the present invention, when third preset times
More hour is less susceptible to cause user's dispersion attention according to the first video ranking results video recommended to the user.For example, the
Two preset times can be 2, at this point, the number that Second Type mood label continuously occurs is no more than 2 times.
Time that present embodiment will indicate that video causes the mood label of the scatterbrained type of user continuously to occur
Number limits smaller, and the attention that family can be used more is concentrated.
In video display process, when same video playing to different location, the irritation level of user is also different,
As shown in fig. 7, minimum to the irritation level of user, therefore, video is broadcast when video playing to transition location and coda position
When putting to transition location and coda position, it is easy to cause user absent minded.In one embodiment, in step
In S130, each video can be recommended to user according to the following steps: recommend principle to recommend each video to user by first, described first
Recommend principle are as follows: in currently played video playing to transition location or coda position, recommend next video to user.
The attention that family can be further used so is more concentrated.
Corresponding with above-mentioned video recommendation method, the embodiment of the invention also provides a kind of video recommendations devices, such as Fig. 4 institute
Show, which includes:
Label acquiring unit 410, for obtaining the mood label of each video, wherein the mood label is reflecting video
On the label of influence caused by user emotion；
Video sequencing unit 420, the number for continuously occurring by identical mood label is no more than the first preset times
The video is ranked up by principle, obtains the first video ranking results that user emotion can be caused to change；
Video recommendations unit 430, for recommending video according to the first video ranking results.
In video recommendations device provided in an embodiment of the present invention, electronic equipment is continuously gone out each video by identical mood label
Existing number is ranked up no more than the principle of the first preset times, obtains the first video that user emotion can be caused to change sequence
As a result, recommend video according still further to the first video ranking results, since the first video ranking results can cause user emotion to change,
Avoid user from being in same mood for a long time and generate it is tired, in this way, by each video in the first video ranking results
The each video of sort recommendations, so that it may influence the emotional change of user by the video played, reduce user and persistently locate
Phenomenon in extreme emotion increases the possibility that user stops longer duration.
In one embodiment, described device can also include:
Acquiring unit is recorded, the broadcasting record of the video is played for obtaining user；
Like extent determination unit, for recording according to the broadcasting, determines that the user likes journey to the video
Degree；
Correspondingly, the video sequencing unit 420, is specifically used for: degree is liked to the video according to the user,
The number continuously occurred based on identical mood label is not more than the principle of the first preset times, is ranked up, obtains to the video
To the first video ranking results.
In one embodiment, the video sequencing unit 420 may include:
First video sorting subunit, for liking degree from high to low suitable to the video according to the user
Sequence is ranked up the video, obtains the second video ranking results；
Video adjusts subelement, and the number for continuously being occurred based on identical mood label is no more than the first preset times
Principle is ranked up adjustment to target video, obtains the first video ranking results, wherein the target video are as follows: described second
Continuous arrangement and the user in video ranking results to the difference for liking degree of corresponding video within a preset range
Video.
In one embodiment, the type of the mood label may include: to indicate that video causes user's attention collection
In type and indicate video cause the scatterbrained type of user；
The video sequencing unit 420, comprising:
Rule obtains subelement, for obtaining the queueing discipline of all types of mood labels, wherein phase in the queueing discipline
The number that the mood label of same type continuously occurs is not more than the second preset times；
Second video sorting subunit for the queueing discipline according to all types of mood labels, and is based on mutually sympathizing with
The number that thread label continuously occurs is not more than the principle of the first preset times, is ranked up to the video, obtains the first video
Ranking results.
In one embodiment, described device can also include:
Experience information acquiring unit, for after the video recommendations unit recommends video, obtaining user's viewing institute
The user experience information of the video of recommendation；
Judging unit is adjusted, adjusts the first video sequence knot for judging whether according to the user experience information
Fruit；
Rule adjustment unit, for adjusting first video when the judging result of the adjustment judging unit is to be
Ranking results, and the first video ranking results adjusted are pressed, Xiang Suoshu user recommends video, and executes the acquisition user
The step of watching the user experience information of recommended video.
The embodiment of the invention also provides a kind of electronic equipment, as shown in figure 5, include processor 501, communication interface 502,
Memory 503 and communication bus 504, wherein processor 501, communication interface 502, memory 503 are complete by communication bus 504
At mutual communication,
Memory 503, for storing computer program；
Processor 501 when for executing the program stored on memory 503, realizes following steps:
Obtain the mood label of each video, wherein the mood label is reflecting video to shadow caused by user emotion
Loud label；
It is not more than the principle of the first preset times by the number that identical mood label continuously occurs, the video is arranged
Sequence obtains the first video ranking results that user emotion can be caused to change；
According to the first video ranking results, recommend video.
Each video is not more than by electronic equipment provided in an embodiment of the present invention by the number that identical mood label continuously occurs
The principle of first preset times is ranked up, the first video ranking results for obtaining capable of causing user emotion to change, according still further to the
One video ranking results recommend video, since the first video ranking results can cause user emotion to change, avoid user for a long time
Generated in same mood it is tired, in this way, each by the sort recommendations of each video in the first video ranking results
Video, so that it may influence the emotional change of user by the video played, reduce user and be continuously in extreme emotion
Phenomenon increases the possibility that user stops longer duration.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal
Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
In another embodiment provided by the invention, a kind of computer readable storage medium is additionally provided, which can
It reads to be stored with instruction in storage medium, when run on a computer, so that computer executes any institute in above-described embodiment
The video recommendation method stated.
In another embodiment provided by the invention, a kind of computer program product comprising instruction is additionally provided, when it
When running on computers, so that computer executes any video recommendation method in above-described embodiment.
For device/electronic equipment/storage medium/program product embodiment, since it is substantially similar to method reality
Example is applied, so being described relatively simple, the relevent part can refer to the partial explaination of embodiments of method.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device/
For electronic equipment/storage medium embodiment, since it is substantially similar to the method embodiment, so being described relatively simple, phase
Place is closed to illustrate referring to the part of embodiment of the method.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (12)
1. a kind of video recommendation method, which is characterized in that the described method includes:
Obtain the mood label of each video, wherein the mood label is reflecting video on influence caused by user emotion
Label；
It is not more than the principle of the first preset times by the number that identical mood label continuously occurs, the video is ranked up,
Obtain the first video ranking results that user emotion can be caused to change；
According to the first video ranking results, recommend video.
2. the method according to claim 1, wherein before described the step of being ranked up the video,
The method also includes:
Obtain the broadcasting record that user plays the video；
It is recorded according to the broadcasting, determines that the user likes degree to the video；
Correspondingly, the number continuously occurred by identical mood label is not more than the principle of the first preset times, by the view
Frequency is ranked up, and obtains the first video ranking results that user emotion can be caused to change, comprising:
Degree is liked to the video according to the user, the number continuously occurred based on identical mood label is not more than first
The principle of preset times is ranked up the video, obtains the first video ranking results.
3. according to the method described in claim 2, it is characterized in that, described like journey to the video according to the user
Degree, the number continuously occurred based on identical mood label are not more than the principle of the first preset times, are ranked up to the video,
Obtain the first video ranking results, comprising:
The sequence of degree from high to low is liked to the video according to the user, the video is ranked up, obtains
Two video ranking results；
The number continuously occurred based on identical mood label is not more than the principle of the first preset times, is ranked up to target video
Adjustment, obtains the first video ranking results, wherein the target video are as follows: the continuous row in the second video ranking results
The video of column and the user to the difference for liking degree of corresponding video within a preset range.
4. the method according to claim 1, wherein the type of the mood label includes: to indicate that video causes
The type and indicate that video causes the scatterbrained type of user that user's attention is concentrated；
The number continuously occurred by identical mood label is not more than the principle of the first preset times, and the video is arranged
Sequence obtains the first video ranking results that user emotion can be caused to change, comprising:
Obtain the queueing discipline of all types of mood labels, wherein the mood label of same type continuously goes out in the queueing discipline
Existing number is not more than the second preset times；
According to the queueing discipline of all types of mood labels, and the number continuously occurred based on identical mood label is no more than the
The principle of one preset times is ranked up the video, obtains the first video ranking results.
5. method according to claim 1 to 4, which is characterized in that tied in described sort according to first video
Fruit, after recommending video, the method also includes:
Obtain the user experience information that user watches recommended video；
According to the user experience information, judge whether to adjust the first video ranking results；
If it is, adjustment the first video ranking results, and press the first video ranking results adjusted, Xiang Suoshu user
Recommend video, and the step of executing the user experience information for obtaining the recommended video of user's viewing.
6. a kind of video recommendations device, which is characterized in that described device includes:
Label acquiring unit, for obtaining the mood label of each video, wherein the mood label is reflecting video to user's feelings
The label influenced caused by thread；
Video sequencing unit, the number for continuously occurring by identical mood label are not more than the principle of the first preset times, will
The video is ranked up, and obtains the first video ranking results that user emotion can be caused to change；
Video recommendations unit, for recommending video according to the first video ranking results.
7. device according to claim 6, which is characterized in that described device further include:
Acquiring unit is recorded, the broadcasting record of the video is played for obtaining user；
Like extent determination unit, for recording according to the broadcasting, determines that the user likes degree to the video；
Correspondingly, the video sequencing unit, is specifically used for: liking degree to the video according to the user, be based on phase
The number continuously occurred with mood label is not more than the principle of the first preset times, is ranked up to the video, obtains first
Video ranking results.
8. device according to claim 7, which is characterized in that the video sequencing unit, comprising:
First video sorting subunit is right for liking the sequence of degree from high to low to the video according to the user
The video is ranked up, and obtains the second video ranking results；
Video adjusts subelement, and the number for continuously being occurred based on identical mood label is not more than the original of the first preset times
Then, adjustment is ranked up to target video, obtains the first video ranking results, wherein the target video are as follows: second view
The view of continuous arrangement and the user in frequency ranking results to the difference for liking degree of corresponding video within a preset range
Frequently.
9. device according to claim 6, which is characterized in that the type of the mood label includes: to indicate that video causes
The type and indicate that video causes the scatterbrained type of user that user's attention is concentrated；
The video sequencing unit, comprising:
Rule obtains subelement, for obtaining the queueing discipline of all types of mood labels, wherein mutually similar in the queueing discipline
The number that the mood label of type continuously occurs is not more than the second preset times；
Second video sorting subunit for the queueing discipline according to all types of mood labels, and is based on identical mood mark
The principle that the number continuously occurred is not more than the first preset times is signed, the video is ranked up, obtains the sequence of the first video
As a result.
10. according to the described in any item devices of claim 6 to 9, which is characterized in that described device further include:
Experience information acquiring unit, for after the video recommendations unit recommends video, acquisition user's viewing to be recommended
The user experience information of video；
Judging unit is adjusted, for judging whether to adjust the first video ranking results according to the user experience information；
Rule adjustment unit, for adjusting the first video sequence when the judging result of the adjustment judging unit is to be
As a result, and pressing the first video ranking results adjusted, Xiang Suoshu user's recommendation video, and the execution acquisition user viewing
The step of user experience information for the video recommended.
11. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein described
Processor, the communication interface, the memory complete mutual communication by the bus；
The memory, for storing computer program；
The processor realizes any method of claim 1-5 for executing the program stored on the memory
Step.
12. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program realizes claim 1-5 any method and step when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910293787.8A CN110096613B (en) | 2019-04-12 | 2019-04-12 | Video recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910293787.8A CN110096613B (en) | 2019-04-12 | 2019-04-12 | Video recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110096613A true CN110096613A (en) | 2019-08-06 |
| CN110096613B CN110096613B (en) | 2021-07-20 |
Family
ID=67444765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910293787.8A Active CN110096613B (en) | 2019-04-12 | 2019-04-12 | Video recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096613B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517085A (en) * | 2019-08-27 | 2019-11-29 | 新华网股份有限公司 | It generates and shows method for reporting, electronic equipment and computer readable storage medium |
| CN111107438A (en) * | 2019-12-30 | 2020-05-05 | 北京奇艺世纪科技有限公司 | Video loading method and device and electronic equipment |
| CN111274381A (en) * | 2020-01-22 | 2020-06-12 | 上海工艺美术职业学院 | Recommendation method and system for electronic book, electronic equipment and computer storage medium |
| CN112423134A (en) * | 2020-07-06 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Video content recommendation method and device and computer equipment |
| CN112464025A (en) * | 2020-12-17 | 2021-03-09 | 当趣网络科技(杭州)有限公司 | Video recommendation method and device, electronic equipment and medium |
| CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102495873A (en) * | 2011-11-30 | 2012-06-13 | 北京航空航天大学 | Video recommending method based on video affective characteristics and conversation models |
| CN103714130A (en) * | 2013-12-12 | 2014-04-09 | 深圳先进技术研究院 | Video recommendation system and method thereof |
| US20140298364A1 (en) * | 2013-03-26 | 2014-10-02 | Rawllin International Inc. | Recommendations for media content based on emotion |
| CN104216960A (en) * | 2014-08-21 | 2014-12-17 | 北京奇艺世纪科技有限公司 | Method and device for recommending video |
| CN104731950A (en) * | 2015-03-31 | 2015-06-24 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| US20150178304A1 (en) * | 2006-09-22 | 2015-06-25 | The John Nicholas and Kristin Gross Trust U/A/D April 13, 2010 | Topic Based Recommender System & Method |
| CN104951479A (en) * | 2014-03-31 | 2015-09-30 | 小米科技有限责任公司 | Video content detecting method and device |
| CN105787069A (en) * | 2016-03-01 | 2016-07-20 | 中山大学深圳研究院 | Personalized music recommendation method |
| CN105893443A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and apparatus, and server |
| CN106611028A (en) * | 2015-10-27 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Personalized music recommendation method and system |
| CN108170868A (en) * | 2018-02-09 | 2018-06-15 | 宁夏灵智科技有限公司 | Video recommendation method and device |
-
2019
- 2019-04-12 CN CN201910293787.8A patent/CN110096613B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150178304A1 (en) * | 2006-09-22 | 2015-06-25 | The John Nicholas and Kristin Gross Trust U/A/D April 13, 2010 | Topic Based Recommender System & Method |
| CN102495873A (en) * | 2011-11-30 | 2012-06-13 | 北京航空航天大学 | Video recommending method based on video affective characteristics and conversation models |
| US20140298364A1 (en) * | 2013-03-26 | 2014-10-02 | Rawllin International Inc. | Recommendations for media content based on emotion |
| CN103714130A (en) * | 2013-12-12 | 2014-04-09 | 深圳先进技术研究院 | Video recommendation system and method thereof |
| CN104951479A (en) * | 2014-03-31 | 2015-09-30 | 小米科技有限责任公司 | Video content detecting method and device |
| CN104216960A (en) * | 2014-08-21 | 2014-12-17 | 北京奇艺世纪科技有限公司 | Method and device for recommending video |
| CN104731950A (en) * | 2015-03-31 | 2015-06-24 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN106611028A (en) * | 2015-10-27 | 2017-05-03 | 中国科学院深圳先进技术研究院 | Personalized music recommendation method and system |
| CN105893443A (en) * | 2015-12-15 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Video recommendation method and apparatus, and server |
| CN105787069A (en) * | 2016-03-01 | 2016-07-20 | 中山大学深圳研究院 | Personalized music recommendation method |
| CN108170868A (en) * | 2018-02-09 | 2018-06-15 | 宁夏灵智科技有限公司 | Video recommendation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 邓文兵: "基于SVD++与上下文感知的个性化音乐推荐系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑（月刊 ）》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517085A (en) * | 2019-08-27 | 2019-11-29 | 新华网股份有限公司 | It generates and shows method for reporting, electronic equipment and computer readable storage medium |
| CN111107438A (en) * | 2019-12-30 | 2020-05-05 | 北京奇艺世纪科技有限公司 | Video loading method and device and electronic equipment |
| CN111107438B (en) * | 2019-12-30 | 2022-04-22 | 北京奇艺世纪科技有限公司 | Video loading method and device and electronic equipment |
| CN111274381A (en) * | 2020-01-22 | 2020-06-12 | 上海工艺美术职业学院 | Recommendation method and system for electronic book, electronic equipment and computer storage medium |
| CN112423134A (en) * | 2020-07-06 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Video content recommendation method and device and computer equipment |
| WO2022007626A1 (en) * | 2020-07-06 | 2022-01-13 | 上海哔哩哔哩科技有限公司 | Video content recommendation method and apparatus, and computer device |
| CN112423134B (en) * | 2020-07-06 | 2022-03-29 | 上海哔哩哔哩科技有限公司 | Video content recommendation method and device, computer equipment and storage medium |
| CN112464025A (en) * | 2020-12-17 | 2021-03-09 | 当趣网络科技(杭州)有限公司 | Video recommendation method and device, electronic equipment and medium |
| CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110096613B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096613A (en) | A kind of video recommendation method, device, electronic equipment and storage medium | |
| CN104090990B (en) | News push method and system | |
| US20130024813A1 (en) | Method, system, and means for expressing relative sentiments towards subjects and objects in an online environment | |
| CN108647293A (en) | Video recommendation method, device, storage medium and server | |
| US20140330825A1 (en) | Recommendation engine | |
| Nagy | The impact of country of origin in mobile phone choice of generation Y and Z | |
| JP6784499B2 (en) | Decision device, decision method and decision program | |
| Yu et al. | To stream or not to stream? Exploring factors influencing impulsive consumption through gastronomy livestreaming | |
| US20080096174A1 (en) | Tutorial generation unit, multimedia management system, portable apparatus, method of explanation of multimedia management behavior, computer program product | |
| CN105243105B (en) | Content ordering method and device | |
| CN106302471B (en) | Method and device for recommending virtual gift | |
| CN109996122A (en) | A kind of video recommendation method, device, server and storage medium | |
| Tacon et al. | Fantasy sport: A systematic review and new research directions | |
| CN108280124A (en) | Product classification method and device, ranking list generation method and device, electronic equipment | |
| CN109151488A (en) | According to the method and system of user behavior real-time recommendation direct broadcasting room | |
| CN110287306A (en) | Recipe recommendation method and equipment | |
| Zhang et al. | A visual interface for critiquing-based recommender systems | |
| Nobarany et al. | The design space of opinion measurement interfaces: exploring recall support for rating and ranking | |
| US20100332426A1 (en) | Method of identifying like-minded users accessing the internet | |
| CN107707940A (en) | Video sequencing method, device, server and system | |
| Willermark et al. | Subjectively experienced time and user satisfaction: An experimental study of progress indicator design in mobile application | |
| CN108170868A (en) | Video recommendation method and device | |
| CN106021302A (en) | Intelligent recommendation technique based wireless music recommendation method and system | |
| CN107483391A (en) | The method for pushing and device of multimedia file | |
| CN112565902A (en) | Video recommendation method and device and electronic equipment |
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 |