CN112990984A - Advertisement video recommendation method, device, equipment and storage medium - Google Patents

Advertisement video recommendation method, device, equipment and storage medium Download PDF

Info

Publication number
CN112990984A
CN112990984A CN202110416715.5A CN202110416715A CN112990984A CN 112990984 A CN112990984 A CN 112990984A CN 202110416715 A CN202110416715 A CN 202110416715A CN 112990984 A CN112990984 A CN 112990984A
Authority
CN
China
Prior art keywords
advertisement
video
label
similarity
tag
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
Application number
CN202110416715.5A
Other languages
Chinese (zh)
Inventor
王雷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Huanwang Technology Co Ltd
Original Assignee
Guangdong Huanwang Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Huanwang Technology Co Ltd filed Critical Guangdong Huanwang Technology Co Ltd
Priority to CN202110416715.5A priority Critical patent/CN112990984A/en
Publication of CN112990984A publication Critical patent/CN112990984A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Computer Interaction (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an advertisement video recommendation method, device, equipment and storage medium. The method comprises the following steps: acquiring user operation data of a user at a television end, and determining whether to start an advertisement recommendation mode according to the user operation data; if the advertisement recommendation mode is started, acquiring a current video tag of the television; calculating the similarity between the current video label and all advertisement video labels in a preset media library according to a preset label recommendation rule, and sequencing the similarity; and selecting a set number of advertisement videos from the media library according to the similarity sorting result to play in sequence. According to the method, a plurality of advertisement videos meeting the user preference are selected to be played in sequence through the current video tags watched by the user, so that the resource management utilization rate during video watching is improved, and the advertisement playing rate and the user product experience are improved.

Description

Advertisement video recommendation method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of television application video playing, in particular to an advertisement video recommendation method, device, equipment and storage medium.
Background
At present, when the video playing of the large-screen application of the television is paused, the advertisement position can be displayed during pausing. The television side application can recommend the played advertisement according to various modes.
Currently, information stream video recommendation, screen-on recommendation and home page home screen recommendation are mainly adopted in short video TV end application mainstream recommendation. In the above recommendation method, if the television video is in a playing state, the advertisement is played in a picture mode only when the television video is paused, and no relevant content is recommended except for the paused advertisement picture. At present, the television end mainly carries out the fixed delivery of advertisement resources in a scheduling mode, and scheduling strategies at each time are all in a fixed form, namely the sequence of advertisements is fixed, and the advertisement sequencing is mostly determined according to the requirements of advertisers. Therefore, the advertisement playing mode in the current television video playing process is single, and the advertisement type is single.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a storage medium for recommending advertisement videos, which overcome the disadvantages of the prior art. The problem of single playing mode and type of the current advertisement is solved.
In order to achieve the purpose, the invention adopts the following technical scheme:
an advertisement video recommendation method, comprising:
acquiring user operation data of a user at a television end, and determining whether to start an advertisement recommendation mode according to the user operation data;
if the advertisement recommendation mode is started, acquiring a current video tag of the television;
calculating the similarity between the current video label and all advertisement video labels in a preset media library according to a preset label recommendation rule, and sequencing the similarity;
and selecting a set number of advertisement videos from the media library according to the similarity sorting result to play in sequence.
Optionally, the determining whether to start an advertisement recommendation mode according to the user operation data includes:
judging whether the user operation data contain preset starting operation or not; the preset starting operation comprises the following steps: pause operation, fast forward operation, and fast rewind operation;
and if the preset starting operation is included, determining to start the advertisement recommendation mode.
Optionally, the calculating, according to a preset tag recommendation rule, the similarity between the current video tag and all advertisement video tags in the preset media library includes:
respectively calculating a current video label vector corresponding to the current video label and an advertisement label vector corresponding to the advertisement video label by combining a preset video label library;
and calculating the similarity according to the current video tag vector and the advertisement tag vector.
Optionally, the calculating, with reference to a preset video tag library, a current video tag vector corresponding to the current video tag and an advertisement tag vector corresponding to the advertisement video tag respectively includes:
calculating the current video weight of each label in the current video labels corresponding to all labels in the video label library, and counting the current video weight to construct the current video label vector;
and calculating the advertisement video weight of each label in the advertisement video labels corresponding to all the labels in the video label library, and counting the advertisement video weight to construct the advertisement label vector.
Optionally, the calculating the similarity according to the current video tag vector and the advertisement tag vector includes:
and calculating the similarity by combining the current video label vector and the advertisement label vector by utilizing a cosine similarity formula.
Optionally, the method further includes:
setting labels of all videos played by the television terminal, and storing the videos with the labels into a preset television video library for a user to select to play;
and setting a label of the advertisement video to be played, and storing the advertisement video with the label into the media library.
Optionally, the selecting a set number of advertisement videos from the media library according to the similarity ranking result to play sequentially includes:
selecting a set number of videos to be broadcasted with advertisements according to the similarity sorting result;
judging whether a played video exists in the advertisement video to be played;
and if so, deleting the played video of the advertisement to be played, and reselecting the video of the advertisement to be played according to the similarity sorting result.
An advertising video recommendation apparatus comprising:
the advertisement recommendation judging module is used for acquiring user operation data of a user at a television end and determining whether to start an advertisement recommendation mode according to the user operation data;
the current video tag acquisition module is used for acquiring a current video tag of the television terminal if the advertisement recommendation mode is started;
the tag similarity calculation module is used for calculating the similarity between the current video tag and all advertisement video tags in a preset media library according to a preset tag recommendation rule and sequencing the similarity;
and the advertisement playing module is used for selecting a set number of advertisement videos from the media library to be played in sequence according to the similarity sorting result.
An advertisement video recommendation apparatus comprising:
a processor, and a memory coupled to the processor;
the memory is used for storing a computer program, and the computer program is at least used for executing the advertisement video recommendation method;
the processor is used for calling and executing the computer program in the memory.
A storage medium storing a computer program which, when executed by a processor, implements the steps of the advertising video recommendation method as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
the application discloses an advertisement video recommendation method, which comprises the following steps: the method comprises the steps of obtaining user operation data of a user at a television end, determining whether an advertisement recommendation mode is started or not, obtaining a current video label if the advertisement recommendation mode is started, calculating the similarity between the current video label and an advertisement video label by combining a label recommendation rule, and finally selecting a plurality of advertisement videos through the similarity to play sequentially. According to the method, the favorite advertisement videos are recommended to the user according to the currently played videos, the number of the advertisement videos played at the same time is multiple, and the advertisement videos can be automatically played in sequence, so that the effect that the user can watch the advertisement videos all the time and the advertisement videos can be played continuously is achieved, the resource management utilization rate of the television-side videos is improved, and the application activity is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for recommending advertisement videos according to an embodiment of the present invention;
FIG. 2 is a block diagram of an apparatus for recommending advertisement video according to an embodiment of the present invention;
fig. 3 is a block diagram of an advertisement video recommendation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Fig. 1 is a flowchart of an advertisement video recommendation method according to an embodiment of the present invention. Referring to fig. 1, an advertisement video recommendation method includes:
step 101: and acquiring user operation data of a user at the television end. When a user watches television video, the TV short video application is firstly opened, when the user opens the television for watching the television video or watches the television video, the user can carry out interactive operation on an interactive interface of a television end, television end equipment can automatically generate user operation data, and the requirements of the user can be determined according to the user operation data.
Step 102: and determining whether to start an advertisement recommendation mode according to the user operation data. After user operation data is acquired, firstly, judging the specific meaning of the user operation data, and specifically judging whether the user operation data contains a preset starting operation, wherein the preset starting operation comprises the following steps: pause operation, fast forward operation, and fast rewind operation. When a user carries out pause, fast forward and fast backward operations in the playing process of the television video, the advertisement video is played, and therefore a proper advertisement video is selected to be played.
Step 103: and if the advertisement recommendation mode is started, acquiring the current video label of the television. When advertisement recommendation is to be performed, a video currently played by a television end, namely a current video, is obtained first, and then a tag of the current video is obtained. Before all videos in a video library of a television end are stored, the tags of the videos are set, that is to say, the videos capable of being played are provided with attribute tags. When the video currently played by the television is acquired, the video contains the label. Similarly, the advertisement video in the media library storing the advertisement video is also provided with a tag, the tag setting is already performed on the advertisement video to be played before the advertisement video to be played is stored in the media library, and the tag corresponding to the advertisement video can be automatically acquired when the advertisement video is called at a later stage. It should be noted that there are multiple tags for each video, whether it is a television video tag or an advertisement video tag. For example: the television video "the rest of the celebration" has the following labels: tags for TV drama, star, ancient drama, etc.
Step 104: and calculating the similarity between the current video label and all advertisement video labels in the preset media library according to a preset label recommendation rule, and sequencing the similarity.
When calculating the similarity between the current video label and the advertisement video label, firstly calculating the weight of all labels in a video label library corresponding to each label in the current video label, and then counting all weights to construct a current video label vector; and similarly, calculating the advertisement video weight of all the labels in the video label library corresponding to each label in all the advertisement video labels, and counting all the weights to construct an advertisement label vector. And finally, calculating the similarity by combining the current video label vector and the advertisement label vector by utilizing a cosine similarity formula.
The specific calculation process is as follows: suppose a video set is V ═ V1,v2,…,vnIn which v is1,v2,…,vnIs the corresponding video; wherein, v is1And as the current playing video, the rest videos are advertisement videos. Assume that all video tag sets are T ═ T1,t2,…,tmWhere t is1,t2,…,tnIs the corresponding label; where n and m can be very large numbers, from hundreds of thousands to millions, and the specific number can be determined according to practical circumstances.
Suppose two videos v1，v2Is expressed as follows, (where T is T ═ T1,t2,…,tmThe order of the labels in (h) to encode the vector),
v1→(w11,w12,w13,…,w1m)＝p1；
v2→(w21,w22,w23,…,w2m)＝p2；
wijthe weight corresponding to the label is adopted, one-hot coding is adopted, and the weight values are only two: w is aij0 or wijIf one of the video tags or advertisement tags is weighted in the corresponding video tag library, w 1ij1 is the weight of the corresponding label.
The cosine similarity formula is adopted
Figure BDA0003026212080000061
To calculate v1，v2The similarity between them. Specifically, if the weight of the advertisement video tag is 8 and the weight of the television video tag is 9, the similarity between the two is 8/9.
V can be calculated1With all other videos (except v)1Self) similarity:
[sim(v1,v2),sim(v1,v3),sim(v1,v4),…,sim(v1,vn)]. And then selecting a plurality of advertisement videos from the first start of the similarity by utilizing the sequence in the similarity set for playing.
Step 105: and selecting a set number of advertisement videos from the media library according to the similarity sorting result to play in sequence.
After a plurality of advertisement videos are selected, firstly, duplicate removal processing is carried out on the selected videos, whether the situation that a user has already watched within a set time exists in the selected advertisement videos is judged, and if the situation that the user has already watched exists, the advertisement videos are deleted. And after the advertisement video is deleted, selecting the unselected advertisement video as the advertisement video to be played according to the previous similarity sequencing sequence, and performing duplication elimination processing on the newly added advertisement video to be played in the same way until all the advertisement videos to be played are the advertisement videos which are not watched by the user.
After the advertisement video to be played is determined, the 1 st advertisement video in the recommendation list is automatically obtained as the next video, the user can directly play the advertisement video by clicking, and the next advertisement video in the recommendation list is automatically played after the video is played.
Meanwhile, when the advertisement video is displayed, the area 1 on the current television interface is positioned at the bottom of the television interface in a mode of two display areas, the selected multiple advertisement videos are displayed in sequence respectively, the advertisement video with the first similarity rank is displayed on the right half part of the middle area of the television interface, a user can directly start to play the advertisement video by clicking the video, and after the advertisement video is played, the advertisement video with the second similarity can be automatically played, namely, the second advertisement video is displayed at the bottom of the television interface.
It should be noted that, the above-mentioned advertisement videos are selected to be played in a set number, and the specific size of the set number is not limited and may be determined according to actual situations. For example, in the present application, it is specified that the number of the advertisement videos is set to be 5, that is, the advertisement videos with the top 5 degrees of similarity are selected to be displayed on a television screen for the user to select.
In the above embodiment, when the user watches videos on the television for pause, fast forward or fast backward operation, the watching preference of the user is determined by acquiring the current videos and the video tags selected and played by the user, a plurality of advertisement videos close to the preference of the user are selected to be played according to the current video tags representing the preference of the user, and the first advertisement video is automatically played and put down one advertisement video after the playing is completed. The resource management utilization rate is improved when the video is watched in the full screen mode, the next favorite video is automatically recommended according to the user behavior, the effect that the user keeps watching the video all the time and the short video continues playing in an 'infinite' mode is achieved, the stay time of the user is prolonged, and the application activity is indirectly improved.
Corresponding to the advertisement video recommendation method provided by the embodiment of the invention, the embodiment of the invention also provides an advertisement video recommendation device. Please see the examples below.
Fig. 2 is a block diagram of an advertisement video recommendation apparatus according to an embodiment of the present invention. Referring to fig. 2, an advertisement video recommendation apparatus includes:
the advertisement recommendation judging module 201 is configured to obtain user operation data of a user at a television end, and determine whether to start an advertisement recommendation mode according to the user operation data.
A current video tag obtaining module 202, configured to obtain a current video tag of the television terminal if the advertisement recommendation mode is started.
And the tag similarity calculation module 203 is configured to calculate similarities between the current video tag and all advertisement video tags in the preset media library according to a preset tag recommendation rule, and perform similarity ranking.
And the advertisement playing module 204 is configured to select a set number of advertisement videos from the media library according to the similarity sorting result and play the selected advertisement videos in sequence.
On the basis of the above embodiment, the apparatus of the present application further includes:
the television video label setting module is used for setting labels of all videos played by the television end and storing the videos with the labels into a preset television video library for a user to select to play;
and the advertisement video label setting module is used for setting the label of the advertisement video to be played and storing the advertisement video with the label into the media library.
In more detail, the advertisement recommendation determining module 201 is specifically configured to: acquiring user operation data of a user at a television end, and judging whether the user operation data contains a preset starting operation; the preset starting operation comprises the following steps: pause operation, fast forward operation, and fast rewind operation; and if the preset starting operation is included, determining to start the advertisement recommendation mode.
The tag similarity calculation module 203 is specifically configured to: calculating the current video weight of each label in the current video labels corresponding to all labels in the video label library, and counting the current video weight to construct the current video label vector; and calculating the advertisement video weight of each label in the advertisement video labels corresponding to all the labels in the video label library, and counting the advertisement video weight to construct the advertisement label vector. And calculating the similarity by combining the current video label vector and the advertisement label vector by utilizing a cosine similarity formula.
The advertisement playing module 204 is specifically configured to: selecting a set number of videos to be broadcasted with advertisements according to the similarity sorting result; judging whether a played video exists in the advertisement video to be played; and if so, deleting the played video of the advertisement to be played, and reselecting the video of the advertisement to be played according to the similarity sorting result.
In the device, when a user watches television videos, video pausing, fast forwarding and fast rewinding are carried out, a label of favorite behaviors of the user is determined based on the current watching video of the user, recommendation of advertisement videos related to the current video and automatic recommendation of the next video are carried out according to the label, the resource management utilization rate when the videos are watched in a full screen mode is improved, the next favorite video is automatically recommended according to the user behaviors, the user can watch the videos all the time, unlimited continuous playing is realized in short videos, the stay time of the user is prolonged, and the application activity is indirectly improved.
In order to more clearly introduce the hardware device for implementing the embodiment of the present invention, the embodiment of the present invention further provides an advertisement video recommendation device corresponding to the advertisement video recommendation method provided by the embodiment of the present invention. Please see the examples below.
Fig. 3 is a block diagram of an advertisement video recommendation apparatus according to an embodiment of the present invention. Referring to fig. 3, an advertisement video recommendation apparatus includes:
a processor 301, and a memory 302 connected to the processor 301;
the memory 302 is used for storing a computer program at least for executing the advertisement video recommendation method; the processor 301 is used for calling and executing the computer program in the memory 302.
Meanwhile, the application also discloses a storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps in the advertisement video recommendation method are realized.
According to the television video label watched by the user at present, the advertisement video meeting the user's liking is selected to be played, and meanwhile, the linkage playing of the advertisement videos can be automatically carried out in the advertisement video playing process, so that the resource management utilization rate when the videos are watched is improved, the product experience of the user is improved, and the user dwell time is further prolonged.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (10)

1. An advertisement video recommendation method, comprising:
acquiring user operation data of a user at a television end, and determining whether to start an advertisement recommendation mode according to the user operation data;
if the advertisement recommendation mode is started, acquiring a current video tag of the television;
calculating the similarity between the current video label and all advertisement video labels in a preset media library according to a preset label recommendation rule, and sequencing the similarity;
and selecting a set number of advertisement videos from the media library according to the similarity sorting result to play in sequence.
2. The method of claim 1, wherein the determining whether to initiate an advertisement recommendation mode based on the user operation data comprises:
judging whether the user operation data contain preset starting operation or not; the preset starting operation comprises the following steps: pause operation, fast forward operation, and fast rewind operation;
and if the preset starting operation is included, determining to start the advertisement recommendation mode.
3. The method of claim 1, wherein the calculating the similarity between the current video tag and all advertisement video tags in a preset media library according to a preset tag recommendation rule comprises:
respectively calculating a current video label vector corresponding to the current video label and an advertisement label vector corresponding to the advertisement video label by combining a preset video label library;
and calculating the similarity according to the current video tag vector and the advertisement tag vector.
4. The method of claim 3, wherein the calculating a current video tag vector corresponding to the current video tag and an advertisement tag vector corresponding to the advertisement video tag respectively in combination with a preset video tag library comprises:
calculating the current video weight of each label in the current video labels corresponding to all labels in the video label library, and counting the current video weight to construct the current video label vector;
and calculating the advertisement video weight of each label in the advertisement video labels corresponding to all the labels in the video label library, and counting the advertisement video weight to construct the advertisement label vector.
5. The method of claim 3, wherein said calculating the similarity from the current video tag vector and the advertisement tag vector comprises:
and calculating the similarity by combining the current video label vector and the advertisement label vector by utilizing a cosine similarity formula.
6. The method of claim 1, further comprising:
setting labels of all videos played by the television terminal, and storing the videos with the labels into a preset television video library for a user to select to play;
and setting a label of the advertisement video to be played, and storing the advertisement video with the label into the media library.
7. The method of claim 1, wherein the selecting a set number of advertisement videos from the media library for sequential playing according to the similarity ranking result comprises:
selecting a set number of videos to be broadcasted with advertisements according to the similarity sorting result;
judging whether a played video exists in the advertisement video to be played;
and if so, deleting the played video of the advertisement to be played, and reselecting the video of the advertisement to be played according to the similarity sorting result.
8. An advertisement video recommendation apparatus, comprising:
the advertisement recommendation judging module is used for acquiring user operation data of a user at a television end and determining whether to start an advertisement recommendation mode according to the user operation data;
the current video tag acquisition module is used for acquiring a current video tag of the television terminal if the advertisement recommendation mode is started;
the tag similarity calculation module is used for calculating the similarity between the current video tag and all advertisement video tags in a preset media library according to a preset tag recommendation rule and sequencing the similarity;
and the advertisement playing module is used for selecting a set number of advertisement videos from the media library to be played in sequence according to the similarity sorting result.
9. An advertisement video recommendation apparatus, comprising:
a processor, and a memory coupled to the processor;
the memory for storing a computer program for performing at least the advertising video recommendation method of any of claims 1-7;
the processor is used for calling and executing the computer program in the memory.
10. A storage medium storing a computer program which, when executed by a processor, performs the steps of the advertisement video recommendation method according to any one of claims 1-7.
CN202110416715.5A 2021-04-19 2021-04-19 Advertisement video recommendation method, device, equipment and storage medium Pending CN112990984A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110416715.5A CN112990984A (en) 2021-04-19 2021-04-19 Advertisement video recommendation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110416715.5A CN112990984A (en) 2021-04-19 2021-04-19 Advertisement video recommendation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112990984A true CN112990984A (en) 2021-06-18

Family

ID=76341053

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110416715.5A Pending CN112990984A (en) 2021-04-19 2021-04-19 Advertisement video recommendation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112990984A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114596126A (en) * 2022-04-26 2022-06-07 土巴兔集团股份有限公司 Advertisement recommendation method and device

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104965889A (en) * 2015-06-17 2015-10-07 腾讯科技（深圳）有限公司 Content recommendation method and apparatus
WO2017101423A1 (en) * 2015-12-14 2017-06-22 乐视控股（北京）有限公司 Advertisement push method and apparatus, video server and terminal device
CN107690081A (en) * 2017-05-25 2018-02-13 腾讯科技（北京）有限公司 Video broadcasting method and device and storage medium, electronic installation
CN108268540A (en) * 2016-12-31 2018-07-10 深圳市优朋普乐传媒发展有限公司 A kind of video recommendation method based on video similarity, system and terminal
CN110019944A (en) * 2017-12-21 2019-07-16 飞狐信息技术（天津）有限公司 A kind of recommended method and system of video
CN110413837A (en) * 2019-05-30 2019-11-05 腾讯科技（深圳）有限公司 Video recommendation method and device
CN111382352A (en) * 2020-03-02 2020-07-07 腾讯科技（深圳）有限公司 Data recommendation method and device, computer equipment and storage medium
CN111754272A (en) * 2020-07-02 2020-10-09 腾讯科技（北京）有限公司 Advertisement recommendation method, recommended advertisement display method, device and equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104965889A (en) * 2015-06-17 2015-10-07 腾讯科技（深圳）有限公司 Content recommendation method and apparatus
WO2017101423A1 (en) * 2015-12-14 2017-06-22 乐视控股（北京）有限公司 Advertisement push method and apparatus, video server and terminal device
CN108268540A (en) * 2016-12-31 2018-07-10 深圳市优朋普乐传媒发展有限公司 A kind of video recommendation method based on video similarity, system and terminal
CN107690081A (en) * 2017-05-25 2018-02-13 腾讯科技（北京）有限公司 Video broadcasting method and device and storage medium, electronic installation
CN110019944A (en) * 2017-12-21 2019-07-16 飞狐信息技术（天津）有限公司 A kind of recommended method and system of video
CN110413837A (en) * 2019-05-30 2019-11-05 腾讯科技（深圳）有限公司 Video recommendation method and device
CN111382352A (en) * 2020-03-02 2020-07-07 腾讯科技（深圳）有限公司 Data recommendation method and device, computer equipment and storage medium
CN111754272A (en) * 2020-07-02 2020-10-09 腾讯科技（北京）有限公司 Advertisement recommendation method, recommended advertisement display method, device and equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
皇甫晓涛 等人: "《数字广告概论》", 中国传媒大学出版社, pages: 176 - 115 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114596126A (en) * 2022-04-26 2022-06-07 土巴兔集团股份有限公司 Advertisement recommendation method and device

Similar Documents

Publication Publication Date Title
CN110209843B (en) Multimedia resource playing method, device, equipment and storage medium
CN107846561B (en) Method and system for determining and displaying contextually targeted content
US9430532B2 (en) Media content rankings for discovery of novel content
US9032435B2 (en) Ad selection and next video recommendation in a video streaming system exclusive of user identity-based parameter
CN109168026A (en) Instant video display methods, device, terminal device and storage medium
CN106060637A (en) Video recommendation method, device and system
CN110062270B (en) Advertisement display method and device
CN109889880B (en) Information display method, device, equipment and storage medium for concerned user
CN113792181A (en) Video recommendation method, device, equipment and medium
CN105872717A (en) Video processing method and system, video player and cloud server
US11838604B2 (en) Generating crowdsourced trailers based on forward or rewind commands
US20140344070A1 (en) Context-aware video platform systems and methods
WO2019001166A1 (en) Television advertisement pushing method, system and electronic device
CN112507163B (en) Duration prediction model training method, recommendation method, device, equipment and medium
CN104581399B (en) The method and system that hot word is searched in a kind of TV box
CN110177306A (en) Video broadcasting method, device, mobile terminal and medium based on mobile terminal
US20230421859A1 (en) Systems and methods for recommending content using progress bars
CN104967690A (en) Information push method and device
CN113766268A (en) Video processing method and device, electronic equipment and readable medium
CN114051160B (en) Video display method and device
CN112990984A (en) Advertisement video recommendation method, device, equipment and storage medium
US20240121485A1 (en) Method, apparatus, device, medium and program product for obtaining text material
US20190141415A1 (en) Enhanced playback bar
CN104954874A (en) Multimedia data playing method and apparatus
US11336946B1 (en) Presenting options for selecting content via navigation bars and designated content spaces

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