CN108650531A - The method and system of video content Rapid matching product - Google Patents
The method and system of video content Rapid matching product Download PDFInfo
- Publication number
- CN108650531A CN108650531A CN201810785715.0A CN201810785715A CN108650531A CN 108650531 A CN108650531 A CN 108650531A CN 201810785715 A CN201810785715 A CN 201810785715A CN 108650531 A CN108650531 A CN 108650531A
- Authority
- CN
- China
- Prior art keywords
- live video
- buyer
- time point
- guide
- commodity
- 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 37
- 238000012545 processing Methods 0.000 claims description 35
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 229910002056 binary alloy Inorganic materials 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
-
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention provides a kind of method and system of video content Rapid matching product, the method includes：Recording includes the live video of multiple buyer's guides；Determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video；The live video is divided into the multiple video clips for respectively including each buyer's guide according to the beginning and the end time point；And it is the multiple video clip is associated with the corresponding commodity in Online Store respectively.
Description
Technical field
The present invention relates to e-commerce fields, and in particular to a kind of method and system of video content Rapid matching product.
Background technology
With the rapid proliferation and audio and video real-time Transmission of the terminal devices such as the fast development of e-commerce, smart mobile phone
Etc. technologies it is increasingly mature, live streaming sells goods as a trend becoming more and more popular at present.It refers to quotient that live streaming, which is sold goods,
Family employs live streaming personnel (main broadcaster) to use smart mobile phone or other live streaming equipment by internet in real time and interactively to client
The marketing behavior of group's promotion commodity has the characteristics that true lively, immediate interactive, largely simulates customer in quotient
Shopping guide's behavior of the true shopping experience and businessman of field, has been greatly facilitated the selling operation of businessman.
However, during live streaming, main broadcaster usually requires to introduce multiple commodity.In this way, after live streaming, live video conduct
One entirety, can not be corresponding with particular commodity, therefore can not offer convenience to two time selling.And artificial editing video content
Mode is time-consuming and laborious, cannot be satisfied the needs that shop on line quickly updates merchandise news.
As it can be seen that there is a need in the art for a kind of technical solutions that can make live video content Rapid matching particular commodity.
Invention content
In one aspect of the invention, a kind of method of video content Rapid matching product is provided, including：Recording includes
The live video of multiple buyer's guides；Determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video；
The live video is divided into the multiple video clips for respectively including each buyer's guide according to the beginning and the end time point；And
The multiple video clip is associated with the corresponding commodity in Online Store respectively.
In another aspect of the present invention, a kind of system of video content Rapid matching product is provided, including：Live streaming regards
Frequency record device is configured as the live video that recording includes multiple buyer's guides；Processing unit is configured as：It determines
The beginning and the end time point of each buyer's guide is corresponded respectively in the live video；According to the beginning and the end time point by the live streaming
Video is divided into the multiple video clips for respectively including each buyer's guide；And by the multiple video clip respectively on the net
Corresponding commodity in shop is associated.
In an additional aspect of the present invention, a kind of machine readable storage medium is additionally provided, it is executable to be stored with machine
Code command, the machine executable code instruction is when executed by a machine so that the machine executes according to the present invention any one
The method of the video content Rapid matching product of a embodiment.
In another aspect of the invention, a kind of computing device is additionally provided comprising processor and be connected with processor
The memory connect, have program stored therein in the memory instruction, and the processor is configured as by loading and executing described deposit
Program instruction in reservoir and the method for executing the video content Rapid matching product of any one embodiment according to the present invention.
The technical solution of video content Rapid matching product according to an embodiment of the invention can be regarded what commodity were broadcast live
Frequency content is automatic and is promptly trimmed into the video clip with commodity association, is provided for the application such as two time selling of Online Store
It is convenient.
Description of the drawings
Fig. 1 shows the schematic block diagram of the system of video content Rapid matching product according to an embodiment of the invention；
Fig. 2 shows the flow charts of the method for video content Rapid matching product according to an embodiment of the invention；
Fig. 3 A show the determination in the method for video content Rapid matching product according to some embodiments of the present invention
The embodiment for the step of the beginning and the end time point of each buyer's guide is corresponded respectively in live video；And
Fig. 3 B are shown in the method for the video content Rapid matching product of other embodiments according to the present invention really
The embodiment for the step of determining to correspond respectively to the beginning and the end time point of each buyer's guide in live video.
Specific implementation mode
The embodiment of the present invention is described with reference to the accompanying drawings.In the following description, numerous specific details are set forth so as to
Person of ordinary skill in the field is set to be appreciated more fully and realize the present invention.But to those of skill in the art
Member is it is evident that the present invention's realizes some that can not have in these details.However, it should be understood that of the invention
It is not limited to introduced specific embodiment.On the contrary, it may be considered that with the arbitrary combination of features described below and element come
Implement the present invention, regardless of whether they are related to different embodiments.Therefore, aspect, feature, embodiment and advantage below is only
It is illustrative, and it is not to be taken as element or the restriction of claim, unless clearly proposing in the claims.
Referring now to Fig. 1, it illustrates the systems of video content Rapid matching product according to some embodiments of the present invention
Schematic block diagram.
As shown in fig. 1, the system 100 of video content Rapid matching product according to some embodiments of the present invention is wrapped
It includes：
Live video record device 101 is configured as the live video that recording includes multiple buyer's guides；
Processing unit 102, is configured as：
Determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video；
The live video is divided into the multiple videos for respectively including each buyer's guide according to the beginning and the end time point
Segment；And
The multiple video clip is associated with the corresponding commodity in Online Store 120 respectively.
In some embodiments, the live video record device 101 and the processing unit 102 can be set by a terminal
Standby 110 realize that the terminal device 110 for example can be smart mobile phone, personal digital assistant, tablet computer, laptop
Equal mobile terminal devices.The mobile terminal device for example may include processor, memory, display, camera, Mai Kejian,
The hardware componenies such as loud speaker, wireless communication unit and the software stored in memory for defining system and application function
Program.The processor can be by loading and executing software program stored in memory and by means of corresponding hardware component
To execute corresponding function.For example, specifically, the live video record device 101 can be loaded and held by the processor
Recording function in row net cast application program stored in memory is realized；The processing unit 102 can be by institute
It states processor load and executes processing routine of the storage in memory with respective handling function to realize.
In further embodiments, the terminal device 110 for example can be live streaming terminal device.The live streaming terminal is set
The standby hardware device such as may include processing equipment, one or more cameras and headset.The processing equipment may include locating
Reason device, memory, display, the hardware componenies such as wireless communication unit and stored in memory define system and application
The software program of function.One or more of cameras and headset etc. can be connected to the place by wired or wireless way
Equipment is managed, in order to execute net cast application.The processor can be by loading and executing software stored in memory
Program simultaneously executes corresponding function by means of corresponding hardware component and equipment.For example, specifically, the live video is recorded
Device 101 can load and execute the recording function in net cast application program stored in memory by the processor
To realize；The processing unit 102 can load and execute corresponding processing program stored in memory by the processor
To realize.
According to an embodiment of the invention, pass through mobile terminal device or live streaming terminal device promotion Online Store in main broadcaster
During the live streaming of 120 multiple commodity, the live video record device 101 can record live video simultaneously, with record
The process of main broadcaster's promotion commodity.It is regarded after live video record device 101 records live video completion, or recording live streaming
During frequency, the processing unit 102 can determine the beginning and the end time point of each buyer's guide in live video, and according to institute
Stating the beginning and the end time point is divided into the live video video clip corresponding to each buyer's guide.The video clip can be with
It is stored or be sent to other equipment and be used.For example, the video clip corresponding to each buyer's guide can be by
The item detail page for sending the commodity in Online Store 120, so that customer is obtained by watching the video clip to the quotient
The more detailed understanding of product.In this way, just by the way that video content to be trimmed into the video clip with commodity association automatically and promptly,
It provides convenience for the two time selling etc. of Online Store 120.
In some embodiments, described be configured to determine that in the live video corresponds respectively to each buyer's guide
The processing unit 102 at the beginning and the end time point is configured to：By detecting the repeating frame in the live video to determine
State the beginning and the end time point that each buyer's guide is corresponded respectively in live video.
The repeating frame can be two or more similar picture frames in live video, such as mutual similar
Degree is more than two or more picture frames of certain threshold value (or diversity factor is less than certain threshold value).In general, including multiple commodity
During the live streaming of introduction, the picture (background and commodity) when the same commodity are broadcast live is relatively fixed, when different commodity are broadcast live
Picture changes greatly, therefore can judge this two figures by the way that whether two picture frames in detection live video are repeating frame
As whether frame is related to the same commodity.In addition, in some embodiments, main broadcaster can be required to put commodity when introducing commodity
It sets in fixed position, in this way, the effect for judging the different commodity periods by repeating frame detection can be further increased.In sequence
In the case of being detected to the live video, each picture frame can be compared with previous picture frame, work as detection
When to repeating frame, it may be determined that be the starting point of some buyer's guide；When detecting repeating frame again, it may be determined that be next quotient
The end of the starting point of product introduction and some buyer's guide settled point, and so on.It is even in live video further to eliminate
The interference of the continuous similar picture so occurred further certain number (such as 10 times) or a timing can occur in detection repeating frame
Between (such as 0.5 second) after, just it is determined as the starting point of buyer's guide or whole settled point.
In some embodiments, it is described be configured as determining by detecting the repeating frame in the live video it is described straight
The processing unit 102 for broadcasting the beginning and the end time point that each buyer's guide is corresponded respectively in video is configured to：
Obtain multiple key frames in the live video；
Successively for each key frame in the multiple key frame, following operation is executed：
The key frame is converted into gray scale picture；
Limb recognition is carried out to the gray scale picture, at edge picture；
The edge picture is normalized, edge picture is normalized to generate；
The normalization edge picture of the normalization edge picture and the previous adjacent key frame of the key frame is carried out
Binary system compares, to judge the similarity or diversity factor of the two；
Be more than predetermined threshold or diversity factor in response to the similarity both determined and be less than threshold value, judge the key frame with it is described
Adjacent key frame is repeating frame；And
In response to determining that pre-determined number or predetermined time continuously occurs in repeating frame, determine that the live video reaches a quotient
The start time point of product introduction, or reach the settled time point at end of previous buyer's guide and the settled time at end of a buyer's guide
Point.
As known to persons skilled in the art, key frame refers to rising for any smooth picture transition defined in video
The frame of initial point.Define the important frame of the main picture in video.Since the quantity of the whole frame in live video is very big, because
This in some embodiments of the invention, the processing unit 102 extracts key frame from the live video, and only in key
Detection repeating frame is compared between frame.The processing unit 102 can be carried using any key frame known in the art
Method is taken to extract key frame from live video.
After being extracted all keys from the live video, the processing unit 102 can use this respectively
Each key frame is converted to gray scale by known gradation conversion method, method for identification of edge and method for normalizing successively in field
Picture carries out limb recognition to generate edge picture to the gray scale picture, and the edge picture is normalized
Edge picture is normalized to generate.Then, the processing unit 102 can by the normalization edge picture of each key frame with
The normalization edge picture of previous adjacent key frame carries out binary system and relatively obtains similarity between the two, and in the two
Between similarity be more than a predetermined similarity threshold when, determine both be repeating frame；Alternatively, obtaining difference between the two
Degree, and diversity factor therebetween be less than a predetermined difference degree threshold value when, determine both be repeating frame.
The predetermined similarity threshold or predetermined difference degree threshold value can be arranged according to actual needs, you can be set
Can key frame when starting some buyer's guide to be correctly judged as repeating frame, so as to correctly judge that commodity are situated between
The starting point to continue.In some embodiments, the predetermined similarity threshold or predetermined difference degree threshold value can by system default, and
It can be adjusted according to practical application scene by user, for example, the application scenarios changed greatly for live streaming picture are (such as main
Broadcast the scene walked about), can the predetermined similarity threshold be arranged smaller, or the predetermined difference degree threshold value is arranged
It is larger；On the contrary, changing smaller application scenarios for live streaming picture, can the predetermined similarity threshold be arranged larger,
Or the predetermined difference degree threshold value is arranged smaller.
After repeating frame is determined from the adjacent key frame of the live video successively, the processing unit 102 can be into
One step determines the number or time that repeating frame continuously occurs, and works as the number that repeating frame continuously occurs and reach pre-determined number, or
When the time that repeating frame continuously occurs reaches the predetermined time, it can be determined that the live video reaches the starting of new buyer's guide
Time point, and (for other commodity except first commodity in the live video) previous buyer's guide end
Settled time point.This is done to eliminate the interference of the continuous similar picture accidentally occurred in live video, so as to more accurately
Determine that live video starts some buyer's guide.
In this way, being detected using repeating frame according to some embodiments of the present invention, it can not only effectively determine live streaming and regard
The origin and destination of each buyer's guide in frequency, and this realization method is without using complicated algorithm, without time-consuming training
Process, therefore be a kind of realization method of simple low cost.
In further embodiments, described be configured to determine that in the live video corresponds respectively to each buyer's guide
The processing unit 102 at the beginning and the end time point be configured to：Described in the identification of artificial intelligence image recognition technology
Each commodity in live video determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video.
The artificial intelligence image recognition technology such as can be based on artificial neural network such as convolutional neural networks
Image identification system.Described image identifying system can be trained with standard merchandise picture in advance, so as to described
Each commodity in live video are identified, and identify in turn in the live video correspond to each buyer's guide the beginning and the end when
Between point.By using artificial intelligence image recognition technology, each commodity in live video and each quotient can be efficiently identified
The beginning and the end time point of product introduction, to which live video to be effectively divided into the video clip corresponding to each commodity.
The processing unit 102 is additionally configured in yet other embodiments,：
While recording the live video, difference the multiple commodity of restocking；
Wherein, described to be configured to determine that the beginning and the end time point that each buyer's guide is corresponded respectively in the live video
Processing unit 102 be configured to：Using the time of the restocking commodity as corresponding to the commodity in the live video
The start time point of introduction, or as settled time point at end and the correspondence for corresponding to previous buyer's guide in the live video
In the start time point of the buyer's guide.
In such embodiments, main broadcaster can use barcode scanning, image recognition while carrying out the live streaming of multiple commodity
Etc. the commodity restocking that quick restocking method will be broadcast live by the processing unit 102, i.e., (such as by the relevant information of the commodity
The information such as category, title, brand, specification, the price of the commodity) it typing and uploads in Online Store 120 so that customer can
It accesses.For example, main broadcaster may use pattern of going window-shopping to carry out commodity live streaming, i.e. main broadcaster " with " customer goes to go window-shopping, and is going window-shopping
The commodity encountered to customer place of matchmakers in journey.If customer is interested in some commodity and requires main broadcaster's restocking commodity, lead
Broadcasting can the restocking commodity.In this way, the processing unit 102 can be using the shelf life of each commodity as the live streaming
The start time point of the buyer's guide in video, and (for other commodity in addition to first commodity) by the commodity
End settled time point of the shelf life as previous buyer's guide in the net cast.In such embodiments, described
Processing unit 102 is integrated with the function of restocking commodity.It is such in the application scenarios of restocking commodity when carrying out commodity live streaming
Embodiment provides a kind of mode for the starting point simply and effectively determining each buyer's guide in live video, so as to
Live video is divided into the video clip corresponding to each commodity.
In some further embodiments, described be configured to determine that in the live video corresponds respectively at least one
The processing unit 102 at least a pair of of the beginning and the end time point of a particular commodity introduction is additionally configured to：It is regarded by detecting the live streaming
Repeating frame in frequency corresponds respectively at least the one of at least one particular commodity introduction to further determine that in the live video
To the beginning and the end time point.
That is, while carry out commodity live streaming while restocking commodity application scenarios in, in addition to can be by commodity restocking when
Between the beginning and the end time point as the corresponding commodity introduction in live video, weight as described above can also be further advanced by
Multi-frame detection method determines the beginning and the end time point of each buyer's guide in live video.In this way, can successfully manage for example main
Situations such as forgetting restocking commodity is broadcast, so as to more accurately determine the beginning and the end time point of each buyer's guide in live video.
In some embodiments, it is described be configured as by the multiple video clip respectively with the phase in Online Store 120
The associated processing unit of commodity 102 is answered to be configured to：The multiple video clip is individually positioned in described online
The page of the corresponding commodity in shop 120.
Namely, live video is divided into comprising each quotient according to the beginning and the end time point of identified each commodity
After the video clip of product introduction, each video clip can be placed on the commodity in Online Store 120 by the processing unit 102
The page, such as be placed on item detail page and corresponding video play button be provided, in this way, accessing the use of the commodity page
Family can watch the playback of the video clip by clicking on, to obtain to the more detailed of the commodity and vividly
Solution, thus promote the two time selling of the commodity.
Certainly, in other embodiments, the processing unit 102 can also store each video clip of division
Or it is sent to other equipment, to be used in other times or scene.
In some embodiments, the sequence of each buyer's guide is pre-determined in commodity live streaming, and correspondingly live streaming regards
The sequence of each buyer's guide in frequency is also pre-determined, in this way, the processing unit 102 can be correct according to the sequence
Ground will be associated by dividing each video clip that live video obtains with corresponding commodity.Or, it is also possible by means auxiliary
Artificial means each video clip of division is associated with corresponding commodity.Or artificial intelligence image can also be passed through
Identification technology identifies the commodity in each video clip, and each video clip is associated with corresponding commodity.
The system 100 of video content Rapid matching product according to an embodiment of the invention is described above by reference to attached drawing,
It should be pointed out that above description is merely illustrative, rather than limiting the invention.In other embodiments of the invention, described
System 100 can have more, less or different module, and connection between each module, include and the relationships such as function can be with
Described and diagram difference.For example, although in the embodiment shown in fig. 1, the live video record device 102 and processing
Device 102 is respectively positioned in terminal device 110, in other embodiments, the live video record device 102 and processing unit
102 can also be located in different equipment, such as the live video record device 102 can be located in terminal device 110, and institute
Stating processing unit 102 can be located in an individual computing device, and the computing device can be with any wired or wireless way and institute
State the communication connection of terminal device 110.It is all these to change within all in the spirit and scope of the present invention.
Referring now to Fig. 2, it illustrates a kind of methods of video content Rapid matching product according to an embodiment of the invention
Flow chart.Each step of this method can correspond to a kind of above-mentioned video content Rapid matching according to an embodiment of the invention
The operation of each device in the system 100 of product.For simplicity, the portion repeated with above description is omitted in the following description
Divide details, therefore, can refer to more detailed understanding of the above description acquisition to this method.
As shown in Fig. 2, the method for video content Rapid matching commodity according to an embodiment of the invention includes the following steps：
In step 210, recording includes the live video of multiple buyer's guides；
In step 220, the beginning and the end time point that each buyer's guide is corresponded respectively in the live video is determined；
In step 230, the live video is divided into according to the beginning and the end time point and respectively includes each buyer's guide
Multiple video clips；And
It is in step 240, the multiple video clip is associated with the corresponding commodity in Online Store respectively.
Referring now to Fig. 3 A, it illustrates the embodiments of the step 220 according to some embodiments of the present invention.Such as figure
Shown in 3A, step 220 packet at the beginning and the end time point of each buyer's guide is corresponded respectively in the determination live video
Include following sub-step：
It is right respectively in the live video to determine by detecting the repeating frame in the live video in sub-step 221
It should be in the beginning and the end time point of each buyer's guide.
In some embodiments, described to be determined in the live video by detecting the repeating frame in the live video
The sub-step 221 for corresponding respectively to the beginning and the end time point of each buyer's guide includes：
Obtain multiple key frames in the live video；
Successively for each key frame in the multiple key frame, following operation is executed：
The key frame is converted into gray scale picture；
Limb recognition is carried out to the gray scale picture, to generate edge picture；
The edge picture is normalized, edge picture is normalized to generate；
The normalization edge picture of the normalization edge picture and the previous adjacent key frame of the key frame is carried out
Binary system compares, to judge the similarity or diversity factor of the two；
In response to determining that the similarity of the two is more than predetermined similarity threshold or diversity factor is less than predetermined difference degree threshold value,
Judge the key frame with the previous adjacent key frame for repeating frame；And
In response to determining that pre-determined number or predetermined time continuously occurs in repeating frame, determine that the live video reaches a quotient
The start time point of product introduction, or reach the initial time at the end settled time point and a buyer's guide of previous buyer's guide
Point.
In some embodiments, the beginning and the end time of each buyer's guide is corresponded respectively in the determination live video
The step 220 of point includes following sub-step：
It is described straight to determine to identify each commodity in the live video by using artificial intelligence image recognition technology
Broadcast the beginning and the end time point that each buyer's guide is corresponded respectively in video.
Referring now to Fig. 3 B, it illustrates the embodiments of the step 220 of other embodiments according to the present invention.Such as
Shown in Fig. 3 B, the method is further comprising the steps of：While recording the live video, difference the multiple quotient of restocking
Product (not shown)；Wherein, the step at the beginning and the end time point of each buyer's guide is corresponded respectively in the determination live video
Rapid 220 include following sub-step：
In sub-step 222, using the time of the restocking commodity as corresponding to rising for the buyer's guide in the live video
Begin time point, or as the settled time point at end for corresponding to previous buyer's guide in the live video and corresponds to the commodity
The start time point of introduction.
In some further embodiments, each buyer's guide is corresponded respectively in the determination live video
The step 220 at the beginning and the end time point further includes following optional sub-step：
In sub-step 223, further determined that in the live video by detecting the repeating frame in the live video
Correspond respectively to the beginning and the end time point of each buyer's guide.
In some embodiments, described that the multiple video clip is associated with the corresponding commodity in Online Store respectively
Step 240 include following sub-step：
The multiple video clip is individually positioned in the page of the corresponding commodity in the Online Store.
Above by reference to the method that attached drawing describes video content Rapid matching commodity according to an embodiment of the invention, should refer to
Go out, above description is merely illustrative, rather than limiting the invention.In other embodiments of the invention, this method can
Sequence with more, less or different step, and between each step includes and the relationships such as function can be with described and figure
The difference shown.For example, multiple functions that a usual step is completed can also be executed by multiple independent steps；Execute difference
The step of multiple steps of function can be merged into a bigger for executing these functions；It can be in any order between some steps
Execute or execute parallel, etc..It is all these to change within all in the spirit and scope of the present invention.
In another aspect of the present invention, a kind of machine readable storage medium is additionally provided, it is executable to be stored with machine
Code command, the machine executable code instruction is when executed by a machine so that the machine executes according to the present invention any one
The method of the video content Rapid matching commodity of a embodiment.
In an additional aspect of the present invention, a kind of computing device is additionally provided comprising processor and be connected with processor
The memory connect, have program stored therein in the memory instruction, and the processor is configured as by loading and executing described deposit
Program instruction in reservoir and execute video content Rapid matching commodity described in any one embodiment according to the present invention
Method.As understood by the skilled person in the art, which can also include other component, such as various input and output
Component, communication component etc. are repeated no more since these components can be the component in existing computer system.
The technical solution of video content Rapid matching product according to an embodiment of the invention can be regarded what commodity were broadcast live
Frequency content is automatic and is promptly trimmed into the video clip with commodity association, is provided for the application such as two time selling of Online Store
It is convenient.
The system of video content Rapid matching commodity according to the ... of the embodiment of the present invention according to an embodiment of the invention and side
Method can be realized by hardware, software, firmware or its arbitrary combination.Video content Rapid matching according to an embodiment of the invention
The system and method for commodity can be realized in a single computer system in a concentrated manner, or realize in a distributed fashion, at this
In kind distribution mode, different component distributions is in the computer system of several interconnection.A kind of group of typical hardware and software
It can be the general-purpose computing system with computer program to close, and the code modules in the computer program correspond to basis
Each module in the system of the video content Rapid matching commodity of the embodiment of the present invention, and be loaded when the computer program and
When execution, the computer system is controlled and make that it executes video content Rapid matching commodity according to an embodiment of the invention is
The operation of each module in system and function.
The foregoing description to the embodiment of the present invention has been provided for the purpose of illustration and description, there is illustrated permitted
The example of more details, such as particular elements and step, to provide a thorough understanding of embodiments of the present invention, purpose is not
It is exhausted or the limitation present invention.The each element or feature of specific embodiment is typically not limited to the specific embodiment, but
It is interchangeable under applicable circumstances and can uses in other embodiments, even if is not shown or described in detail.This
The variation of sample is not to be regarded as a departure from the disclosure, and all such modifications are intended to be included within the scope of this invention.
In some example embodiments, it is not described in well known component, structure and well known technology.
Term used herein is only used for the purpose of description specific example embodiments, and is not intended to be restrictive.This Shen
Please in each component title be only for sake of convenience depending on, rather than limiting the invention.As it is used herein, on unless
It explicitly points out additionally below, otherwise singulative " one ", "one" and "the" can also be intended to include plural form.Word " packet
Include ", " comprising ", "comprising" and " having " they are inclusives, therefore specify the feature, step, operation, component and/or device
Presence, but do not exclude the presence of or other one or more features, step, operation, component and/or device and combinations thereof add
Add.Step, process and operation described herein is not interpreted that them is necessarily required to hold with the particular order for discussing or showing
Row executes sequence unless specifically specified.Herein, the use that word " product " and " commodity " can be interchanged.
When component is referred to as or is illustrated as in another component "upper", " being connected to " or " being coupled to " another component,
It can be directly on, be connected or coupled to other component, or may exist intermediate member.As used herein, " connection ",
" connected " or similar word and corresponding diagram can refer to mechanical connection, be electrically connected in the case where no other clearly limit
Any one or more of connect, communicate to connect.In addition, as it is used herein, word "and/or", " and/or " include
Any and all combinations of one or more correlation Listed Items.
It is understood that the principle that is intended to be merely illustrative of the present of the above various embodiments of the present invention and showing for using
Example property embodiment, the present invention is not limited thereto.For those skilled in the art, do not departing from the present invention's
In the case of spirit and essence, various changes and modifications can be made therein, these variations and modifications are also considered as the guarantor in the present invention
Within the scope of shield.Protection scope of the present invention is only limited by the meaning and its equivalents of the language expression of the appended claims
It is fixed.
Claims (10)
1. a kind of method of video content Rapid matching product, including：
Recording includes the live video of multiple buyer's guides；
Determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video；
The live video is divided into the multiple video clips for respectively including each buyer's guide according to the beginning and the end time point；
And
The multiple video clip is associated with the corresponding commodity in Online Store respectively.
2. according to the method described in claim 1, wherein, each commodity being corresponded respectively in the determination live video and are situated between
The beginning and the end time point to continue includes：
Each buyer's guide is corresponded respectively in the live video to determine by detecting the repeating frame in the live video
The beginning and the end time point.
3. according to the method described in claim 2, wherein, the repeating frame in the live video by detection is to determine
It states and corresponds respectively to the beginning and the end time point of each buyer's guide in live video and include：
Obtain multiple key frames in the live video；
Successively for each key frame in the multiple key frame, following operation is executed：
The key frame is converted into gray scale picture；
Limb recognition is carried out to the gray scale picture, to generate edge picture；
The edge picture is normalized, edge picture is normalized to generate；
By the normalization edge picture of the previous adjacent key frame of normalization edge picture and the key frame carry out two into
System compares, to judge the similarity or diversity factor of the two；
In response to determining that the similarity of the two is more than predetermined similarity threshold or diversity factor is less than predetermined difference degree threshold value, judge
The key frame is repeating frame with the previous adjacent key frame；And
In response to determining that pre-determined number or predetermined time continuously occurs in repeating frame, determine that the live video reaches a commodity and is situated between
The start time point to continue, or reach the start time point at the end settled time point and a buyer's guide of previous buyer's guide.
4. according to the method described in claim 1, wherein, each commodity being corresponded respectively in the determination live video and are situated between
The beginning and the end time point to continue includes：
Each commodity in the live video are identified by using artificial intelligence image recognition technology to determine that the live streaming regards
The beginning and the end time point of each buyer's guide is corresponded respectively in frequency.
5. according to the method described in claim 1, further including：
While recording the live video, difference the multiple commodity of restocking；
Wherein, the beginning and the end time point for each buyer's guide being corresponded respectively in the determination live video includes：
Using the time of the restocking commodity as start time point or the conduct for corresponding to the buyer's guide in the live video
Corresponding to the settled time point at end of previous buyer's guide and the start time point corresponding to the buyer's guide in the live video.
6. a kind of system of video content Rapid matching product, including：
Live video record device is configured as the live video that recording includes multiple buyer's guides；
Processing unit is configured as：
Determine the beginning and the end time point that each buyer's guide is corresponded respectively in the live video；
The live video is divided into the multiple video clips for respectively including each buyer's guide according to the beginning and the end time point；
And
The multiple video clip is associated with the corresponding commodity in Online Store respectively.
7. system according to claim 6, wherein described be configured to determine that in the live video corresponds respectively to often
The processing unit at the beginning and the end time point of a buyer's guide is configured to：
Each buyer's guide is corresponded respectively in the live video to determine by detecting the repeating frame in the live video
The beginning and the end time point.
8. system according to claim 7, wherein the repeating frame being configured as by detecting in the live video
To determine that the processing unit at the beginning and the end time point for corresponding respectively to each buyer's guide in the live video is further configured
For：
Obtain multiple key frames in the live video；
Successively for each key frame in the multiple key frame, following operation is executed：
The key frame is converted into gray scale picture；
Limb recognition is carried out to the gray scale picture, to generate edge picture；
The edge picture is normalized, edge picture is normalized to generate；
By the normalization edge picture of the previous adjacent key frame of normalization edge picture and the key frame carry out two into
System compares, to judge the similarity or diversity factor of the two；
In response to determining that the similarity of the two is more than predetermined similarity threshold or diversity factor is less than predetermined difference degree threshold value, judge
The key frame is repeating frame with the adjacent key frame；And
In response to determining that pre-determined number or predetermined time continuously occurs in repeating frame, determine that the live video reaches a commodity and is situated between
The start time point to continue, or reach the start time point at the end settled time point and a buyer's guide of previous buyer's guide.
9. system according to claim 6, wherein described be configured to determine that in the live video corresponds respectively to often
The processing unit at the beginning and the end time point of a buyer's guide is configured to：
Each commodity in the live video are identified by using artificial intelligence image recognition technology to determine that the live streaming regards
The beginning and the end time point of each buyer's guide is corresponded respectively in frequency.
10. system according to claim 6, wherein the processing unit is additionally configured to：
While recording the live video, difference the multiple commodity of restocking；
Wherein, the place for being configured to determine that the beginning and the end time point that each buyer's guide is corresponded respectively in the live video
Reason device is configured to：
Using the time of the restocking commodity as start time point or the conduct for corresponding to the buyer's guide in the live video
Super time point beginning in the live video corresponding to the settled time point at end of previous buyer's guide and corresponding to the buyer's guide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785715.0A CN108650531A (en) | 2018-07-17 | 2018-07-17 | The method and system of video content Rapid matching product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785715.0A CN108650531A (en) | 2018-07-17 | 2018-07-17 | The method and system of video content Rapid matching product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108650531A true CN108650531A (en) | 2018-10-12 |
Family
ID=63751442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810785715.0A Pending CN108650531A (en) | 2018-07-17 | 2018-07-17 | The method and system of video content Rapid matching product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108650531A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111385642A (en) * | 2018-12-29 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Media information processing method, device, server, equipment and storage medium |
| CN111432225A (en) * | 2020-03-11 | 2020-07-17 | 北京意匠文枢科技有限公司 | Method and equipment for commodity video cutting |
| CN111586474A (en) * | 2020-05-21 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Live video processing method and device |
| CN111935155A (en) * | 2020-08-12 | 2020-11-13 | 北京字节跳动网络技术有限公司 | Method, apparatus, server and medium for generating target video |
| CN111954078A (en) * | 2020-08-24 | 2020-11-17 | 上海连尚网络科技有限公司 | Video generation method and device for live broadcast |
| CN111954077A (en) * | 2020-08-24 | 2020-11-17 | 上海连尚网络科技有限公司 | Video stream processing method and device for live broadcast |
| CN112055225A (en) * | 2019-06-06 | 2020-12-08 | 阿里巴巴集团控股有限公司 | Live broadcast video interception, commodity information generation and object information generation methods and devices |
| CN112399258A (en) * | 2019-08-13 | 2021-02-23 | 腾讯科技（深圳）有限公司 | Live playback video generation playing method and device, storage medium and electronic equipment |
| CN113891166A (en) * | 2021-10-22 | 2022-01-04 | 北京达佳互联信息技术有限公司 | Data processing method, data processing device, computer equipment and medium |
| CN114341912A (en) * | 2019-09-09 | 2022-04-12 | 全景株式会社 | Management server and management program |
| CN114363641A (en) * | 2020-10-13 | 2022-04-15 | 阿里巴巴集团控股有限公司 | Target video generation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102036107A (en) * | 2010-11-30 | 2011-04-27 | 深圳市同洲电子股份有限公司 | Method, system and commodity service terminal for TV shopping based on interactive VOD system |
| CN106162213A (en) * | 2016-07-11 | 2016-11-23 | 福建方维信息科技有限公司 | A kind of merchandise display method and system based on net cast shopping |
| WO2017057789A1 (en) * | 2015-10-02 | 2017-04-06 | 양성호 | System for product introduction and purchase for electronic commerce on mobile device and method thereof |
| CN106791895A (en) * | 2016-11-29 | 2017-05-31 | 北京小米移动软件有限公司 | Interactive approach and device in electric business application program |
| TWM557404U (en) * | 2017-12-22 | 2018-03-21 | 行動拍拍賣科技股份有限公司 | Device for selling products quickly in live broadcast platform |
-
2018
- 2018-07-17 CN CN201810785715.0A patent/CN108650531A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102036107A (en) * | 2010-11-30 | 2011-04-27 | 深圳市同洲电子股份有限公司 | Method, system and commodity service terminal for TV shopping based on interactive VOD system |
| WO2017057789A1 (en) * | 2015-10-02 | 2017-04-06 | 양성호 | System for product introduction and purchase for electronic commerce on mobile device and method thereof |
| CN106162213A (en) * | 2016-07-11 | 2016-11-23 | 福建方维信息科技有限公司 | A kind of merchandise display method and system based on net cast shopping |
| CN106791895A (en) * | 2016-11-29 | 2017-05-31 | 北京小米移动软件有限公司 | Interactive approach and device in electric business application program |
| TWM557404U (en) * | 2017-12-22 | 2018-03-21 | 行動拍拍賣科技股份有限公司 | Device for selling products quickly in live broadcast platform |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111385642A (en) * | 2018-12-29 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Media information processing method, device, server, equipment and storage medium |
| CN112055225A (en) * | 2019-06-06 | 2020-12-08 | 阿里巴巴集团控股有限公司 | Live broadcast video interception, commodity information generation and object information generation methods and devices |
| CN112055225B (en) * | 2019-06-06 | 2023-02-17 | 阿里巴巴集团控股有限公司 | Live broadcast video interception, commodity information generation and object information generation methods and devices |
| CN112399258B (en) * | 2019-08-13 | 2022-06-07 | 腾讯科技（深圳）有限公司 | Live playback video generation playing method and device, storage medium and electronic equipment |
| CN112399258A (en) * | 2019-08-13 | 2021-02-23 | 腾讯科技（深圳）有限公司 | Live playback video generation playing method and device, storage medium and electronic equipment |
| CN114341912A (en) * | 2019-09-09 | 2022-04-12 | 全景株式会社 | Management server and management program |
| CN111432225A (en) * | 2020-03-11 | 2020-07-17 | 北京意匠文枢科技有限公司 | Method and equipment for commodity video cutting |
| CN111586474A (en) * | 2020-05-21 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Live video processing method and device |
| CN111935155A (en) * | 2020-08-12 | 2020-11-13 | 北京字节跳动网络技术有限公司 | Method, apparatus, server and medium for generating target video |
| US11750898B2 (en) | 2020-08-12 | 2023-09-05 | Beijing Bytedance Network Technology Co., Ltd. | Method for generating target video, apparatus, server, and medium |
| CN111954077A (en) * | 2020-08-24 | 2020-11-17 | 上海连尚网络科技有限公司 | Video stream processing method and device for live broadcast |
| CN111954078A (en) * | 2020-08-24 | 2020-11-17 | 上海连尚网络科技有限公司 | Video generation method and device for live broadcast |
| CN114363641A (en) * | 2020-10-13 | 2022-04-15 | 阿里巴巴集团控股有限公司 | Target video generation method and device |
| CN113891166A (en) * | 2021-10-22 | 2022-01-04 | 北京达佳互联信息技术有限公司 | Data processing method, data processing device, computer equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108650531A (en) | The method and system of video content Rapid matching product | |
| CN109145784B (en) | Method and apparatus for processing video | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN111368141B (en) | Video tag expansion method, device, computer equipment and storage medium | |
| EP3989158A1 (en) | Method, apparatus and device for video similarity detection | |
| CN108960316A (en) | Method and apparatus for generating model | |
| EP3896610A1 (en) | Information presentation method and device | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN111522996A (en) | Video clip retrieval method and device | |
| CN109165574B (en) | Video detection method and device | |
| JP2020517038A (en) | Business object recommendation method, device, electronic device and storage medium | |
| US20210312331A1 (en) | Dynamic video content optimization | |
| CN117238451B (en) | Training scheme determining method, device, electronic equipment and storage medium | |
| CN108230033A (en) | For the method and apparatus of output information | |
| CN116894711A (en) | Commodity recommendation reason generation method and device and electronic equipment | |
| CN112784103A (en) | Information pushing method and device | |
| CN107968743A (en) | The method and apparatus of pushed information | |
| CN117391824B (en) | Method and device for recommending articles based on large language model and search engine | |
| WO2023217194A1 (en) | Dynamic video cover generation method | |
| CN117611272A (en) | Commodity recommendation method and device and electronic equipment | |
| CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
| CN111768250A (en) | Method, device, computer readable medium and electronic equipment | |
| EP2704036A2 (en) | Movie selecting | |
| CN113837986A (en) | Method, apparatus, electronic device, and medium for recognizing tongue picture | |
| CN113704596A (en) | Method and apparatus for generating a set of recall information |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181012 |
|
| WD01 | Invention patent application deemed withdrawn after publication |