CN110163673A - A kind of temperature prediction technique, device, equipment and storage medium based on machine learning - Google Patents
A kind of temperature prediction technique, device, equipment and storage medium based on machine learning Download PDFInfo
- Publication number
- CN110163673A CN110163673A CN201910403255.5A CN201910403255A CN110163673A CN 110163673 A CN110163673 A CN 110163673A CN 201910403255 A CN201910403255 A CN 201910403255A CN 110163673 A CN110163673 A CN 110163673A
- Authority
- CN
- China
- Prior art keywords
- information
- temperature
- user
- user behavior
- video
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000010801 machine learning Methods 0.000 title claims abstract description 40
- 238000003860 storage Methods 0.000 title claims description 28
- 230000006399 behavior Effects 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims description 27
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 12
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 14
- 241001071864 Lethrinus laticaudis Species 0.000 description 13
- 238000012545 processing Methods 0.000 description 8
- 239000003795 chemical substances by application Substances 0.000 description 6
- 238000013179 statistical model Methods 0.000 description 5
- 230000001154 acute effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000283973 Oryctolagus cuniculus Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of temperature prediction technique, equipment and system based on machine learning, comprising: the user behavior information generated when being played by obtaining target video；The interested object information of user in the target video is determined according to the user behavior information；Temperature prediction is carried out to the object information based on temperature prediction model, obtain the temperature object information in the target video, more accurately excavate video periphery commodity, fed back statistics are substituted by model prediction, the prediction timeliness to hot spot object in video can be greatly promoted, the production restocking process of commodity is shortened.
Description
Technical field
This disclosure relates to machine learning techniques field, and in particular to a kind of temperature prediction technique based on machine learning, dress
It sets, equipment and storage medium.
Background technique
Viewing Online Video has become a kind of universal daily entertainment mode, and what is occurred in popular movie and video programs is some
Stage property, clothing, accessory and other items are held in both hands with the heat that the hot broadcast of movie and video programs usually will receive consumer.Online Video service provider
The successively online online store service combined with movie and video programs, for selling week relevant to movie and television contents to video user
Side commodity.
Currently, relying primarily on rear feedback mechanism for the periphery commodity for excavating movie and television play program: passing through collection and movie and television play
The message such as relevant microblogging, wechat circle of friends, video comments are analyzed, and identify that user comments the video topic discussed warmly warmly, so
Periphery relevant to video hot topic commodity are produced afterwards.It but is to pass through in the existing scheme for excavating video dependent merchandise temperature
It collects the related news progress data mining analysis after movie and television play is broadcasted and obtains related much-sought-after item, cause to the pre- of much-sought-after item
The poor in timeliness of survey.
Summary of the invention
The present disclosure proposes a kind of temperature prediction technique, device, equipment and storage medium based on machine learning, Neng Gou great
The big prediction timeliness promoted to hot spot object in video.The disclosure is specifically to be realized with following technical solution:
On the one hand, the temperature prediction technique based on machine learning that present disclose provides a kind of, comprising:
Obtain the user behavior information generated when target video plays；
The interested object information of user in the target video is determined according to the user behavior information；
User's row that the user behavior information generated when being played based on training video and the training video are generated when playing
The temperature prediction model being trained for the corresponding temperature object information of information to default and its learning model is to described right
Image information carries out temperature prediction, obtains the temperature object information in the target video.
On the other hand, the temperature prediction meanss based on machine learning that present disclose provides a kind of, comprising:
First obtains module, for obtaining the user behavior information generated when target video plays；
First determining module, for determining that user is interested right in the target video according to the user behavior information
Image information；
When prediction module, the user behavior information generated when for being played based on training video and the training video are played
The corresponding temperature object information of the user behavior information of generation predicts the temperature that default and its learning model is trained
Model carries out temperature prediction to the object information, obtains the temperature object information in the target video.
On the other hand, present disclose provides a kind of pre- measurement equipment of the temperature based on machine learning, the equipment includes processing
Device and memory, are stored at least one instruction, at least a Duan Chengxu, code set or instruction set in the memory, it is described extremely
A few instruction, an at least Duan Chengxu, the code set or instruction set are loaded by the processor and are executed to realize such as
Temperature prediction technique above-mentioned based on machine learning.
On the other hand, it present disclose provides a kind of computer readable storage medium, is stored at least in the storage medium
One instruction, at least a Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, the generation
Code collection or instruction set are loaded by processor and are executed to realize the temperature prediction technique based on machine learning as the aforementioned.
Present disclose provides a kind of temperature prediction technique, device, equipment and storage medium based on machine learning, passes through receipts
Collect scene information when user watches video, interest-degree of the user to the corresponding object occurred in video is predicted, by same
Scene information analysis of the user of video when watching video, utilizes the user behavior information generated when playing based on training video
And the corresponding temperature object information of user behavior information that generates when playing of the training video to default and its learning model into
The temperature prediction model that row training obtains predicts the temperature of corresponding object in corresponding video.Utilize skill provided by the embodiments of the present application
Art scheme can more accurately excavate video periphery commodity, substitute fed back statistics by model prediction, can greatly promote to view
The prediction timeliness of hot spot object in frequency shortens the production restocking process of commodity.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology and advantage, below will be to implementation
Example or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, the accompanying drawings in the following description is only
It is only some embodiments of the present invention, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of system architecture signal of temperature prediction technique based on machine learning provided in an embodiment of the present invention
Figure；
Fig. 2 is that a kind of system architecture details of temperature prediction technique based on machine learning provided in an embodiment of the present invention is shown
It is intended to；
Fig. 3 is a kind of flow diagram of temperature prediction technique based on machine learning provided in an embodiment of the present invention；
Fig. 4 is a kind of flow diagram of the method for building up of temperature prediction model provided in an embodiment of the present invention；
Fig. 5 is a kind of process of temperature prediction technique of the statistical model provided in an embodiment of the present invention in conjunction with prediction model
Schematic diagram；
Fig. 6 is a kind of method of the interested object information of determining red user of target video provided in an embodiment of the present invention
Flow diagram；
Fig. 7 is another method for determining the interested object information of the red user of target video provided in an embodiment of the present invention
Flow diagram；
Fig. 8 is a kind of stream of method that target object is determined based on multiple temperature object informations provided in an embodiment of the present invention
Journey schematic diagram；
Fig. 9 is a kind of application scenarios signal that user behavior information is obtained when playing video provided in an embodiment of the present invention
Figure；
Figure 10 is a kind of structural schematic diagram of temperature prediction meanss based on machine learning provided in an embodiment of the present invention；
Figure 11 is a kind of hardware block diagram of the server of temperature prediction technique provided by the embodiments of the present application.
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, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art without making creative work it is obtained it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, system, product or server need not limit
In step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, produce
The other step or units of product or equipment inherently.
It is introduced below the present invention is based on the temperature prediction technique of machine learning, present description provides such as embodiments or process
The figure method operating procedure, but may include more or less operation step based on routine or without creative labor
Suddenly.The step of enumerating in embodiment sequence is only one of numerous step execution sequences mode, does not represent unique execution
Sequentially.When system or server product in practice executes, it can be held according to embodiment or method shown in the drawings sequence
Capable or parallel execution (such as environment of parallel processor or multiple threads).
Fig. 1 is a kind of system architecture signal of temperature prediction technique based on machine learning provided in an embodiment of the present invention
Figure, as shown in Figure 1, the scene includes: client 01, background server 02, big data server 03, Analytical Results Database 04
With production/operator 05.
Fig. 2 is that a kind of system architecture details of temperature prediction technique based on machine learning provided in an embodiment of the present invention is shown
It is intended to.
Specifically, the client 01 is common video playback apparatus, clothes are played for providing a user Online Video
The input signal of business and collecting and reporting user.The client 01 may include smart phone, desktop computer, tablet computer,
The entity device of the types such as laptop, digital assistants, intelligent wearable device, also may include running in entity device
Software, such as some service providers are supplied to the Webpage of user, or those service providers are supplied to answering for user
With.In the embodiment of this specification, the client 01 is needed comprising in video APP (application program), microphone, data
Report tetra- Agent (agency), voice Agent modules.Wherein video APP is mainly that user provides the broadcasting service of Online Video；
Microphone is used to receive near field and the far field voice signal of user；Data report Agent for collecting user in viewing video mistake
Related broadcast information data and manipulation behavioral data in journey, and it is sent to back-end services；Voice Agent is for receiving microphone
Collected audio data carries out code conversion (end-point detection, compression, fragment) and is convenient for audio transmission.
Specifically, the data that the 02 primary recipient client of background server uploads.Voice is carried out for voice data
Identification conversion and natural language processing.The broadcasting manipulation data and voice data for converging user are arranged simultaneously, are reported to bottom
Data warehouse is stored.The background server 02 may include an independently operated server or Distributed Services
Device, or the server cluster being made of multiple servers.Server 01 may include having network communication unit, processor and depositing
Reservoir etc..In this specification embodiment, background service includes ASR (automatic speech recognition) service, NLP (at natural language
Reason) service and data report service.Wherein ASR services the audio data reported for receiving client voice agent, to sound
Frequency evidence is decoded, language model, acoustic model and feature extraction are handled, and transfer is converted into normative text.NLP service
Text information after receiving ASR service processing, rule-based template matching and deep learning model understand the intention of user speech,
Identify voice messaging relevant to comment on commodity in video.Wherein, rule template is predefined text resolution rule, is based on
Rule template understands that being intended that for user speech is parsed by the text information to input according to predefined rule, extracts
The intention of text.Data report service to be used for the data and NLP service output that standardized customer end data reports agent to report
Voice remark information, carry out the extension (such as related acute acute name, performer's information) of relevant information, bottom after data are transmitted
It is stored.Wherein, input information may only be merely the local message watched in video, for subsequent data mining results
More precisely, it is desirable to provide richer comprehensive data information, and in order to save network bandwidth and reduce the complexity that reports of data,
Client report matchmaker's standing cease when, generally can only report main id information, such as the id of video, therefore, need herein into
Row information extension.
Specifically, the big data server 03 is responsible for the reported data of storage magnanimity and excavate to data to divide
Analysis, based on machine learning algorithm training commodity temperature prediction model.The big data server 03 may include an independent fortune
Capable server perhaps distributed server or the server cluster being made of multiple servers.Server 01 may include
There are network communication unit, processor and memory etc..Divide between bucket specifically, the server 01 can be used for carrying out user
Association training study.Big data server 03 described in this specification embodiment mainly includes three parts: data warehouse is mainly used
In mass data storage (such as the data warehouse built based on Hadoop (a kind of distributed system infrastructure))；Crawler service
It is mainly used for external data to crawl and (crawl the comment information etc. on external website about article in film), for further enriching
Related data；Data of the data analysis service based on acquisition, the temperature in conjunction with machine learning algorithm, to the commodity occurred in video
It is predicted, prediction result is output to Analytical Results Database.Wherein, the big data server 03 and the background server
02 function can be inherited in the same server.
Specifically, the analysis that the Analytical Results Database 04 is mainly used for storing the output of big data server 03 is pre-
It surveys as a result, and the analysis prediction result is reported to the production/operator 05.
Specifically, production/the operator 05 is used to receive the analysis prediction knot that the Analytical Results Database 04 reports
Fruit, and production/Management plan is determined based on the analysis prediction result.
Fig. 3 is a kind of flow diagram of temperature prediction technique based on machine learning provided in an embodiment of the present invention, such as
Shown in Fig. 3, the method is specifically included:
S301: the user behavior information generated when target video plays is obtained.
It is described to obtain the user behavior information generated when target video plays in this specification embodiment, it specifically includes:
Voice messaging, operation information.
Wherein, voice messaging refers to the acoustic information generated in video display process by client process at voice data
Information.Specifically, can be the voice messaging that user during watching video carries out acquisition when phonetic search, it is also possible to
User issues when client acquires good friend's voice-enabled chat in user and network speech information or user in the home environment with
The voice messaging generated after the speech information that relatives and friends generate when chatting.
Operation information refers to that user is to the operation information of video jukebox software in video display process.Specifically, can be with
It is the operation information for being broadcast slowly to video playing progress during watching video, reviewing, suspending etc., is also possible to watching
Shot operation during video is also possible to the operation informations such as transmission barrage during watching video.
S303: the interested object information of user in the target video is determined according to the user behavior information.
Specifically, object information can be the information of stage property, clothes, accessory and other items, it is also possible to the members such as image, symbol
The information of element.In view of user is when watching target video, if find oneself interested object in target video, often
Video jukebox software can be executed and the operation such as review or suspend, so that user more clearly sees oneself interested object clearly, because
This, can determine object interested to user according to the specific behavior that user generates when watching video.Likewise, for example with
Family when encountering the picture that interested object occurs, can usually discuss exchange when watching target video together with friend together
Therefore the object obtains the voice messaging generated during user's viewing video and is determined for the interested object of user
Information.
As shown in figure 4, providing a kind of flow diagram of the method for building up of temperature prediction model, specifically include:
S401: the user behavior information generated when training video plays is obtained.
S403: temperature object information corresponding with the user behavior information generated when training video broadcasting is obtained.
In this specification embodiment, user behavior information and its corresponding temperature object letter that training video generates when playing
Breath is used as training data, and source can be the database of major video applications software or video website, specifically can use system
Meter model obtains.Referring to Fig. 5, the process for providing a kind of temperature prediction technique of statistical model with prediction model in conjunction with is illustrated
Figure.
Specifically, in conjunction with user tag data, being concluded to the behavioral data of user by defining artificial experience rule
Statistics, comprehensively considers the factors such as the scene, the frequency, intensity of user behavior, and the behavior distribution of quantificational description user calculates user
For the key training of some object.Historical behavior and artificial experience of the statistical model based on user, the interest of identity user.
Specifically, artificial experience rule be according to operation experience, for the feature of data statistics result, the object that extracts
Temperature prediction scheme.Such as: there is front evaluation for some object and (occurs " beautiful " in the comment information by collecting user
Vocabulary such as " liking " " desired ") accounting reaches 40%, then it is denoted as liking.
Specifically, user tag data, that is, user's portrait (such as age of user, educational background, gender, address, consuming capacity, receipts
Enter the information such as grade).Generally, user likes interested object and user's portrait relationship ratio in the video and video of viewing
Relatively closely.For example, the higher user of many consuming capacities can be to luxury goods packet, clothes, the cosmetics etc. occurred in movie and television play
Interested, many ages are more keen to the cartoon elements in movie and television play in the consumer of twenties.
Specifically, the behavioral data of user is the user's operation that can be directly used for statistics, for example user's forward direction is commented on, is fast
Into, search etc. operation.
Specifically, for the determination method of specific object, on the one hand, comprising apparent product name in comment information,
Object can directly be extracted；On the other hand, video pictures when can be according to user comment, in conjunction with image analysis recognition caculation,
Extract specific object.
S405: default machine learning model is instructed based on the user behavior information and the temperature object information
Practice, obtains temperature prediction model.
On the basis of statistical model, introduce prediction model, based on the result of statistical model as training sample, in conjunction with
Family label data and video tab data (acute, terrible, the young label data of such as costume piece, city), the default prediction mould of training
Type obtains temperature prediction model, predicts that each user in video may interested object for user behavior data.
Wherein, prediction model can be the machine learning models such as support vector machines, k nearest neighbor.
When the user behavior information generated when the target video of acquisition plays is voice messaging, according to the user behavior
Information determines the interested object information of user in the target video, a kind of determining red user of target video provided such as Fig. 6
Shown in the flow diagram of the method for interested object information, specifically include:
S601: semantic analysis is carried out to the voice messaging, obtains information related with object in the voice messaging.
It will be appreciated by those skilled in the art that, non-structured voice can be believed by core technologies such as speech recognitions
Breath is converted to the index of structuring, to realize the excavation to special object in audio file and quick-searching, obtains voice letter
Information related with object in breath.
S603: the frequency of occurrence of the information related with object is counted.
Specifically, certain object frequency of occurrence is higher, illustrating that user is higher to its interest level, frequency of occurrence is lower,
User's interest level is lower.
S605: the interested object information of user in the target video is determined based on the frequency of occurrence.
When the user behavior information generated when the target video of acquisition plays is operation information, according to the user behavior
Information determines the interested object information of user in the target video, and the another kind provided such as Fig. 7 determines the red use of target video
Shown in the flow diagram of the method for the interested object information in family, specifically include:
S701: the type of the operation information is identified.
It will be appreciated by those skilled in the art that, to the operation of video according to type difference can be divided into hair barrage, review,
Slowly it broadcasts, screenshot etc..Client obtains user to the operation information of video software during user watches video, and then identifies
The type of different operation information out.
S703: according to the operation frequency of the different types of operation information of the type statistics of the operation information.
Wherein, operation information can be divided into according to the difference of mode of operation by different type, and counts different type respectively
Operation information the operation frequency.For example, sending out the operation information of barrage for user, counting user sends out the frequency of barrage；For
User plays back the operation information of video content, statistics playback frequency.
Specifically, certain object frequency of occurrence is higher, illustrating that user is higher to its interest level, frequency of occurrence is lower,
User's interest level is lower.
S705: determine that user is interested right in target video based on the operation frequency of the different types of operation information
Image information.
It should be understood that the frequency that user sends out barrage is higher, user is more possible in the video played within that time
There are interested objects, specifically, can further determine that user is interested right according to the semantics recognition to barrage content
Image information.
S305: temperature prediction is carried out to the object information based on temperature prediction model, is obtained in the target video
Temperature object information；The temperature prediction model is the user behavior information and the training generated when being played based on training video
The corresponding temperature object information of the user behavior information generated when video playing is trained to obtain to default machine learning model
's.
What is obtained by step S301-S305 is temperature object information when user watches target video, it is general and
Speech, the information of a user may be more inaccurate, or does not have very high reference value.Therefore, available multiple
The temperature object information of user, to improve the accuracy for determining temperature object in target video, as shown in figure 8, providing one kind
The flow diagram of the method for target object is determined based on multiple temperature object informations.
S801: when obtaining the target video and playing, the corresponding temperature object information of multiple user behavior information.
Temperature object information of the user in target video is obtained using such as step S301-S305, obtains multiple use
Multiple temperature object informations of the family in the target video.Wherein, multiple quantity is bigger more accurate to prediction result.
S803: temperature in the target video is determined based on the corresponding temperature object information of the multiple user behavior information
The temperature parameter of object information.
Specifically, the temperature parameter can be temperature object in the reflection target video in multiple users by joyous
The parameter information for meeting degree, can be particular number, be also possible to ratio.For example, getting heat when 3 users watch video
Object information is spent, is ABC, ACDE, AB respectively, then number 3 times that A occurs, the number that B, C occur is 2 times, what D, E occurred
Number is 1 time, then parameter temperature > B, C parameter temperature > D, E parameter temperature of A.
S805: the target object of the corresponding temperature object information of the temperature parameter is determined based on the temperature parameter.
Specifically, one or more temperature parameter thresholds can be set, pass through the ratio of temperature parameter and temperature parameter threshold
Compared with, it can be deduced that the target object of different temperatures (hot, hotter, secondary heat etc.).Further, the example taken a step in rapid S803,
When temperature parameter >=3 when, object A be hot object, when 3 > temperature parameter >=2 when, object B be compared with heat target.
When determining the target object of different temperatures, the target temperature object and its corresponding temperature information are sent to
Commodity production/operator is adapted so that commodity production/operator designs and produces according to the different temperatures of target temperature object
The commodity of quantity for selection by the user and are bought.
The embodiment of this specification is distributed after getting the article in the possible interested video of each user
Statistics obtains possible most popular article and improves forecasting accuracy as final prediction result.
The embodiment of the invention also provides a kind of when playing video obtains the application scenarios of user behavior information.User is just
Passing through certain video software playing animation piece " piggy and rabbit " in mobile terminal, as shown in figure 9, the cartoon total duration is
1 hour, when user sees bottom 36 minutes, there is the picture of rabbit and piggy.If at this point, user, which compares piggy, feels emerging
Interest, user may can't help giving a call ", like this piggy well ", then mobile terminal can carry out radio reception to it,
And voice messaging is sent to background server；User can also click on " pause " button or dragging progress bar is reviewed
Equal realizations have gone through picture existing for piggy again or repeatedly, these operations are captured by client, and after being sent to
Platform server；Similarly, when barrage is opened, user can also pass through input character " piggy is good lovely " (not shown) etc.
It can analyze to express oneself to the interested emotion of piggy in picture from the background by the semantics recognition to character in barrage
The interested object of user " piggy " out.
The interested object information of multiple users is joined by the temperature that big data server is predicted to obtain " piggy "
Number, such as be 40 to " piggy " interested user, then production/operator obtains the information in 100 sample of users
Afterwards, can have the commodity, such as T-shirt, money pot, toy etc. of piggy element according to the piggy design, and according to the quantity
In conjunction with the customized suitable commodity of production of practical crowd's quantity.To, when waiting the cartoon online, corresponding piggy element commodity
Restocking realizes the Accurate Prediction of much-sought-after item, improves user satisfaction.
The temperature prediction meanss based on machine learning that the embodiment of the invention also provides a kind of, as shown in Figure 10, the dress
It sets and includes:
First obtains module 1001, for obtaining the user behavior information generated when target video plays；
First determining module 1003, for determining that user is interested in the target video according to the user behavior information
Object information；
Prediction module 1005 carries out temperature prediction to the object information for temperature prediction model, obtains the target
Temperature object information in video；The temperature prediction model be when being played based on training video the user behavior information that generates and
The corresponding temperature object information of user behavior information that the training video generates when playing carries out default machine learning model
What training obtained.
Obtain the user behavior information generated when training video plays.
In some embodiments, the temperature prediction model in the prediction module is established in the following manner: acquisition and institute
State the corresponding temperature object information of user behavior information generated when training video plays；Based on the user behavior information and institute
It states temperature object information to be trained default machine learning model, obtains temperature prediction model.
In some embodiments, when the user behavior information is voice messaging, first determining module includes:
Semantic analysis unit, for the voice messaging carry out semantic analysis, obtain in the voice messaging with object
Related information；
First statistic unit, for counting the frequency of occurrence of the information related with object；
First determination unit, for determining that the interested object of user is believed in the target video based on the frequency of occurrence
Breath.
In some embodiments, when the user behavior information is operation information, first determining module includes:
Recognition unit, for identification type of the operation information；
Second statistic unit, the operation frequency for the different types of operation information of type statistics according to the operation information
It is secondary；
Second determination unit is used for being determined in target video based on the operation frequency of the different types of operation information
The interested object information in family.
In some embodiments, described device further include:
Second obtains module, when being played for obtaining the target video, the corresponding temperature pair of multiple user behavior information
Image information；
Second determining module, for determining the mesh based on the corresponding temperature object information of the multiple user behavior information
Mark the temperature parameter of temperature object information in video.
In some embodiments, described device further include:
Third determining module, for determining the corresponding temperature object information of the temperature parameter based on the temperature parameter
Target object.
Apparatus and method embodiment in the Installation practice is based on same inventive concept.
The present invention also provides a kind of pre- measurement equipments of the temperature based on machine learning, and the equipment includes processor and storage
Device is stored at least one instruction, at least a Duan Chengxu, code set or instruction set in the memory, and described at least one refers to
It enables, an at least Duan Chengxu, the code set or instruction set are loaded by the processor and executed to realize base as the aforementioned
In the temperature prediction technique of machine learning.
The present invention also provides a kind of computer readable storage medium, at least one finger is stored in the storage medium
Enable, at least a Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, the code set or
Instruction set is loaded by processor and is executed to realize the temperature prediction technique based on machine learning as the aforementioned.
Optionally, in the present embodiment, above-mentioned storage medium can be located in multiple network servers of computer network
At least one network server.Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, only
Read memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), movement
The various media that can store program code such as hard disk, magnetic or disk.
In this specification embodiment, the memory can be used for storing software program and module, and processor passes through operation
It is stored in the software program and module of memory, thereby executing various function application and data processing.Memory can be main
Including storing program area and storage data area, wherein storing program area can application program needed for storage program area, function
Deng；Storage data area, which can be stored, uses created data etc. according to the equipment.In addition, memory may include high speed with
Machine access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or its
His volatile solid-state part.Correspondingly, memory can also include Memory Controller, to provide processor to memory
Access.
Embodiment of the method provided by the embodiment of the present application can be in mobile terminal, terminal, server or class
As execute in arithmetic unit.For running on the server, Figure 11 is a kind of temperature prediction provided by the embodiments of the present application
The hardware block diagram of the server of method.As shown in figure 11, which can generate ratio because configuration or performance are different
Biggish difference may include one or more central processing units (Central Processing Units, CPU) 1110
(processing unit that processor 1110 can include but is not limited to Micro-processor MCV or programmable logic device FPGA etc.) is used for
The memory 1130 of storing data, the storage medium 1120 of one or more storage application programs 1123 or data 1122
(such as one or more mass memory units).Wherein, memory 1130 and storage medium 1120 can be of short duration storage
Or persistent storage.The program for being stored in storage medium 1120 may include one or more modules, and each module can wrap
It includes to the series of instructions operation in server.Further, central processing unit 1110 can be set to and storage medium
1120 communications execute the series of instructions operation in storage medium 1120 on server 1100.Server 1100 can also wrap
One or more power supplys 1160 are included, one or more wired or wireless network interfaces 1150, one or more
Input/output interface 1140, and/or, one or more operating systems 1121, such as Windows Server TM, Mac
OS XTM, Unix TM, Linux TM, Free BSD TM etc..
Input/output interface 1140 can be used for that data are received or sent via a network.Above-mentioned network is specifically real
Example may include the wireless network that the communication providers of server 1100 provide.In an example, input/output interface 1140 wraps
A network adapter (Network Interface Controller, NIC) is included, base station and other network equipments can be passed through
It is connected so as to be communicated with internet.In an example, input/output interface 1140 can be radio frequency (Radio
Frequency, RF) module, it is used to wirelessly be communicated with internet.
It will appreciated by the skilled person that structure shown in Figure 11 is only to illustrate, above-mentioned electronics is not filled
The structure set causes to limit.For example, server 1100 may also include more perhaps less component or tool than shown in Figure 11
There is the configuration different from shown in Figure 11.
The reality of the temperature prediction technique based on machine learning, device, equipment and the storage medium that are provided by aforementioned present invention
Example is applied as it can be seen that the video dependent merchandise temperature prediction that this specification embodiment is realized based on user video viewing scene information analysis
System and scheme, by collect user watch video when scene information (voice messaging, operation information etc.), in conjunction with engineering
Algorithm and big data digging technology are practised, predicts interest-degree of the user to the respective articles occurred in video, to predict corresponding shadow
Depending on the temperature of acute respective articles.In this way, video periphery commodity can be more accurately excavated, are substituted by model prediction
Fed back statistics greatly shorten the production restocking process of commodity, can preferably combine the temperature of video, promote corresponding periphery commodity
Attention rate.
In addition, the accuracy for excavating commodity depends on corresponding topic temperature to be difficult to excavate corresponding for the collection of drama of minority
Periphery commodity.Temperature prediction technique provided by the invention based on machine learning also can carry out week to the movie and television play works of detumescence
The prediction of side commodity temperature, meets the shopping need of minority group.
It should be understood that embodiments of the present invention sequencing is for illustration only, do not represent the advantages or disadvantages of the embodiments.
And above-mentioned this specification specific embodiment is described.Other embodiments are within the scope of the appended claims.One
In a little situations, the movement recorded in detail in the claims or step can be executed according to the sequence being different from embodiment and
Still desired result may be implemented.In addition, process depicted in the drawing not necessarily requires the particular order shown or company
Continuous sequence is just able to achieve desired result.In some embodiments, multitasking and parallel processing it is also possible or
It may be advantageous.
All the embodiments in this specification are described in a progressive manner, 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 system and server example, since it is substantially similar to the method embodiment, so being described relatively simple, related place
Illustrate referring to the part of embodiment of the method.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of temperature prediction technique based on machine learning, which is characterized in that the described method includes:
Obtain the user behavior information generated when target video plays；
The interested object information of user in the target video is determined according to the user behavior information；
Temperature prediction is carried out to the object information based on temperature prediction model, obtains the temperature object letter in the target video
Breath；When the temperature prediction model is the user behavior information generated when being played based on training video and training video broadcasting
The corresponding temperature object information of the user behavior information of generation is trained default machine learning model.
2. the method according to claim 1, wherein when the user behavior information be voice messaging when, it is described
Determine that the interested object information of user includes: in the target video according to the user behavior information
Semantic analysis is carried out to the voice messaging, obtains information related with object in the voice messaging；
Count the frequency of occurrence of the information related with object；
The interested object information of user in the target video is determined based on the frequency of occurrence.
3. the method according to claim 1, wherein when the user behavior information be operation information when, it is described
Determine that the interested object information of user includes: in the target video according to the user behavior information
Identify the type of the operation information；
According to the operation frequency of the different types of operation information of the type statistics of the operation information；
The interested object information of user in target video is determined based on the operation frequency of the different types of operation information.
4. the method according to claim 1, wherein in the temperature prediction model that is based on to the object information
Temperature prediction is carried out, after obtaining the temperature object information in the target video, the method also includes:
When obtaining the target video and playing, the corresponding temperature object information of multiple user behavior information；
Temperature object information in the target video is determined based on the corresponding temperature object information of the multiple user behavior information
Temperature parameter.
5. according to the method described in claim 4, it is characterized in that, described corresponding based on the multiple user behavior information
After temperature object information determines the temperature parameter of temperature object information in the target video, the method also includes:
The target object of the corresponding temperature object information of the temperature parameter is determined based on the temperature parameter.
6. a kind of temperature prediction meanss based on machine learning, which is characterized in that described device includes:
First obtains module, for obtaining the user behavior information generated when target video plays；
First determining module, for determining that the interested object of user is believed in the target video according to the user behavior information
Breath；
Prediction module carries out temperature prediction to the object information for temperature prediction model, obtains in the target video
Temperature object information；The temperature prediction model is the user behavior information and the training generated when being played based on training video
The corresponding temperature object information of the user behavior information generated when video playing is trained to obtain to default machine learning model
's.
7. device according to claim 6, which is characterized in that described when the user behavior information is voice messaging
First determining module includes:
Semantic analysis unit obtains related with object in the voice messaging for carrying out semantic analysis to the voice messaging
Information；
First statistic unit, for counting the frequency of occurrence of the information related with object；
First determination unit, for determining the interested object information of user in the target video based on the frequency of occurrence.
8. device according to claim 6, which is characterized in that described when the user behavior information is operation information
First determining module includes:
Recognition unit, for identification type of the operation information；
Second statistic unit, the operation frequency for the different types of operation information of type statistics according to the operation information；
Second determination unit, for determining that user feels in target video based on the operation frequency of the different types of operation information
The object information of interest.
9. device according to claim 6, which is characterized in that described device further include:
Second obtains module, when being played for obtaining the target video, the corresponding temperature object letter of multiple user behavior information
Breath；
Second determining module, for determining that the target regards based on the corresponding temperature object information of the multiple user behavior information
The temperature parameter of temperature object information in frequency.
10. device according to claim 9, which is characterized in that described device further include:
Third determining module, for determining the target of the corresponding temperature object information of the temperature parameter based on the temperature parameter
Object.
11. a kind of pre- measurement equipment of temperature based on machine learning, which is characterized in that the equipment includes processor and memory,
It is stored at least one instruction, at least a Duan Chengxu, code set or instruction set in the memory, at least one instruction,
An at least Duan Chengxu, the code set or instruction set are loaded by the processor and are executed to realize such as claim 1 to 5
Temperature prediction technique described in middle any claim based on machine learning.
12. a kind of computer readable storage medium, which is characterized in that be stored at least one instruction, extremely in the storage medium
A few Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, the code set or instruction
Collection is loaded as processor and is executed to realize the heat based on machine learning as described in any claim in claim 1 to 5
Spend prediction technique.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910403255.5A CN110163673A (en) | 2019-05-15 | 2019-05-15 | A kind of temperature prediction technique, device, equipment and storage medium based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910403255.5A CN110163673A (en) | 2019-05-15 | 2019-05-15 | A kind of temperature prediction technique, device, equipment and storage medium based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110163673A true CN110163673A (en) | 2019-08-23 |
Family
ID=67634562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910403255.5A Pending CN110163673A (en) | 2019-05-15 | 2019-05-15 | A kind of temperature prediction technique, device, equipment and storage medium based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110163673A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050193A (en) * | 2019-11-12 | 2020-04-21 | 汉口北进出口服务有限公司 | User portrait construction method and device, computer equipment and storage medium |
| CN111275514A (en) * | 2020-01-07 | 2020-06-12 | 载信软件(上海)有限公司 | Intelligent purchasing method and system, storage medium and electronic device |
| CN111339404A (en) * | 2020-02-14 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Content popularity prediction method and device based on artificial intelligence and computer equipment |
| CN112702632A (en) * | 2019-10-22 | 2021-04-23 | 中国移动通信集团吉林有限公司 | Live program injection method, device, system, storage medium and computer equipment |
| CN115443663A (en) * | 2020-05-19 | 2022-12-06 | 国际商业机器公司 | Automatically generating enhancements to AV content |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102487456A (en) * | 2009-11-30 | 2012-06-06 | 国际商业机器公司 | Method for providing visit rate of online video and device thereof |
| US20130176415A1 (en) * | 2012-01-06 | 2013-07-11 | Lg Electronics Inc. | Apparatus for processing a service and method thereof |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
| CN104951563A (en) * | 2015-07-08 | 2015-09-30 | 北京理工大学 | Method and device for determining to-be-recommended objects |
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| CN107105320A (en) * | 2017-03-07 | 2017-08-29 | 上海交通大学 | A kind of Online Video temperature Forecasting Methodology and system based on user emotion |
| CN107484030A (en) * | 2017-07-29 | 2017-12-15 | 安徽博威康信息技术有限公司 | Merchandise news obtains system in a kind of viewing video based on spectators' operation |
| CN109033180A (en) * | 2018-06-26 | 2018-12-18 | 深圳市爱的网络科技有限公司 | A kind of information-pushing method, device, computer installation and computer readable storage medium |
| CN109672939A (en) * | 2019-01-07 | 2019-04-23 | 北京奇艺世纪科技有限公司 | A kind of method and device of marking video content temperature |
-
2019
- 2019-05-15 CN CN201910403255.5A patent/CN110163673A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102487456A (en) * | 2009-11-30 | 2012-06-06 | 国际商业机器公司 | Method for providing visit rate of online video and device thereof |
| US20130176415A1 (en) * | 2012-01-06 | 2013-07-11 | Lg Electronics Inc. | Apparatus for processing a service and method thereof |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
| CN104951563A (en) * | 2015-07-08 | 2015-09-30 | 北京理工大学 | Method and device for determining to-be-recommended objects |
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| CN107105320A (en) * | 2017-03-07 | 2017-08-29 | 上海交通大学 | A kind of Online Video temperature Forecasting Methodology and system based on user emotion |
| CN107484030A (en) * | 2017-07-29 | 2017-12-15 | 安徽博威康信息技术有限公司 | Merchandise news obtains system in a kind of viewing video based on spectators' operation |
| CN109033180A (en) * | 2018-06-26 | 2018-12-18 | 深圳市爱的网络科技有限公司 | A kind of information-pushing method, device, computer installation and computer readable storage medium |
| CN109672939A (en) * | 2019-01-07 | 2019-04-23 | 北京奇艺世纪科技有限公司 | A kind of method and device of marking video content temperature |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112702632A (en) * | 2019-10-22 | 2021-04-23 | 中国移动通信集团吉林有限公司 | Live program injection method, device, system, storage medium and computer equipment |
| CN112702632B (en) * | 2019-10-22 | 2022-12-30 | 中国移动通信集团吉林有限公司 | Live program injection method, device, system, storage medium and computer equipment |
| CN111050193A (en) * | 2019-11-12 | 2020-04-21 | 汉口北进出口服务有限公司 | User portrait construction method and device, computer equipment and storage medium |
| CN111050193B (en) * | 2019-11-12 | 2022-06-10 | 汉口北进出口服务有限公司 | User portrait construction method and device, computer equipment and storage medium |
| CN111275514A (en) * | 2020-01-07 | 2020-06-12 | 载信软件(上海)有限公司 | Intelligent purchasing method and system, storage medium and electronic device |
| CN111339404A (en) * | 2020-02-14 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Content popularity prediction method and device based on artificial intelligence and computer equipment |
| CN115443663A (en) * | 2020-05-19 | 2022-12-06 | 国际商业机器公司 | Automatically generating enhancements to AV content |
| CN115443663B (en) * | 2020-05-19 | 2024-04-09 | 国际商业机器公司 | Automatically generating enhancements to AV content |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163673A (en) | A kind of temperature prediction technique, device, equipment and storage medium based on machine learning | |
| CN111711828B (en) | Information processing method and device and electronic equipment | |
| CN103718166B (en) | Messaging device, information processing method | |
| KR101816113B1 (en) | Estimating and displaying social interest in time-based media | |
| WO2017193897A1 (en) | Data recommendation method and device therefor, and storage medium | |
| CN107463698B (en) | Method and device for pushing information based on artificial intelligence | |
| US9524487B1 (en) | System and methods for detecting temporal music trends from online services | |
| CN108563753A (en) | Message pushes generation method, device and the computer readable storage medium of official documents and correspondence | |
| CN111708901A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN109165302A (en) | Multimedia file recommendation method and device | |
| CN110364146A (en) | Audio recognition method, device, speech recognition apparatus and storage medium | |
| CN104780093A (en) | Method and device for processing expression information in instant messaging process | |
| CN108848393B (en) | Method, device and equipment for showing entrance and storage medium | |
| CN109783539A (en) | Usage mining and its model building method, device and computer equipment | |
| WO2022042157A1 (en) | Method and apparatus for manufacturing video data, and computer device and storage medium | |
| CN107465739B (en) | The method and device of entity channel user drainage | |
| CN113111264B (en) | Interface content display method and device, electronic equipment and storage medium | |
| CN107810638A (en) | By the transmission for skipping redundancy fragment optimization order content | |
| WO2021097721A1 (en) | Information pushing method and apparatus, electronic device, and computer-readable medium | |
| KR102676791B1 (en) | Method and system for providing multiple profiles | |
| CN113742567A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN111555966A (en) | Message processing method, device, system, storage medium and computer equipment | |
| CN109313649A (en) | Voice-based knowledge sharing application for chat robots | |
| CN113626624B (en) | Resource identification method and related device | |
| CN112784103A (en) | Information pushing method and device |
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 |