CN116228320B - Live advertisement putting effect analysis system and method - Google Patents
Live advertisement putting effect analysis system and method Download PDFInfo
- Publication number
- CN116228320B CN116228320B CN202310232368.XA CN202310232368A CN116228320B CN 116228320 B CN116228320 B CN 116228320B CN 202310232368 A CN202310232368 A CN 202310232368A CN 116228320 B CN116228320 B CN 116228320B
- Authority
- CN
- China
- Prior art keywords
- data
- evaluation
- historical
- live
- advertisement
- 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.)
- Active
Links
- 230000000694 effects Effects 0.000 title claims abstract description 138
- 238000004458 analytical method Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 356
- 230000003993 interaction Effects 0.000 claims abstract description 72
- 230000006870 function Effects 0.000 claims description 46
- 230000001537 neural effect Effects 0.000 claims description 46
- 230000009471 action Effects 0.000 claims description 38
- 238000013528 artificial neural network Methods 0.000 claims description 38
- 230000004913 activation Effects 0.000 claims description 36
- 238000012795 verification Methods 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 14
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 230000003213 activating effect Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 88
- 238000004364 calculation method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- 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
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
-
- 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
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- 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)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Computer Graphics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a live advertisement putting effect analysis system and a live advertisement putting effect analysis method, wherein first evaluation data, second evaluation data, third evaluation data and fourth evaluation data are extracted from historical live broadcasting behavior data, historical first inter-live broadcasting data, historical interaction behavior data and first playing terminal data which are acquired from a cloud server to generate an advertisement putting effect analysis model; and extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience and second playing terminal data, and obtaining an advertisement putting effect analysis report by combining an advertisement putting effect analysis model. The method and the system can comprehensively analyze the advertisement putting effect of the live broadcasting room based on the behavior state of the main broadcasting room, the arrangement condition of the live broadcasting room, the behavior state of the audience and the attribute/performance of the video playing terminal, and improve the efficiency and the accuracy.
Description
Technical Field
The invention relates to the technical field of live broadcasting, in particular to a live broadcasting advertisement putting effect analysis system and method.
Background
With the development of mobile internet technology, video live broadcast technology is widely applied, and as live broadcast has the characteristics of rich content types, strong interaction and the like, a large number of users are attracted to watch live broadcast on a live broadcast platform, and even watch live broadcast video of a host broadcast in a live broadcast room becomes daily entertainment of people. And the merchant selects to put advertisements on the live platform according to the characteristic of large user flow of the live platform. However, in the related art, when the advertisement is put on the live platform, a relatively rough mode is generally adopted, and the putting effect of the live advertisement is not effectively analyzed, so that the income of putting the advertisement on the live platform cannot reach the expectations.
Disclosure of Invention
Based on the problems, the invention provides a system and a method for analyzing the live advertisement putting effect, and by the scheme of the invention, the effect of putting the advertisement in the live broadcasting room can be comprehensively analyzed based on the behavior state of the main broadcasting room, the arrangement condition of the live broadcasting room, the behavior state of the audience and the attribute/performance of the video playing terminal, so that the efficiency and the accuracy are improved.
In view of this, an aspect of the present invention proposes a live advertisement delivery effect analysis system, including: the system comprises a cloud server, a plurality of live broadcast servers, a plurality of video servers and a plurality of playing terminals; wherein,
The cloud server is configured to:
acquiring historical live broadcast behavior data of a first main broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
the cloud server acquires historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
marking the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a marking number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively;
generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data;
Acquiring live broadcast behavior data of a second main broadcast of the second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second play terminal data in a second preset time range;
extracting fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live action data, the second live room data, the interactive action data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
Optionally, in the step that the cloud server acquires, from a first direct broadcast server in the plurality of direct broadcast servers, historical direct broadcast behavior data of a first host broadcast in a first direct broadcast room and historical first direct broadcast room data in the first direct broadcast room within a first preset time range, the cloud server is specifically configured to:
determining the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sending a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
Configuring the first direct broadcast server to:
after the first direct broadcast server receives the first data acquisition instruction, selecting a corresponding first data set according to the first data acquisition instruction;
and processing and classifying the first data set to respectively obtain the historical live broadcast behavior data and the historical first live broadcast room data.
Optionally, in the step of extracting first, second, third and fourth evaluation data from the historical live behavior data, the historical first live room data, the historical interaction behavior data and the first playing terminal data, respectively, the cloud server is specifically configured to:
extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data;
extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data;
extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data and expression data and limb action data from the historical interaction behavior data as the third evaluation data;
And extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data.
Optionally, in the step of generating an advertisement delivery effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data, the cloud server is specifically configured to:
establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data;
establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data;
establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data;
Establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter;
and inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model.
Optionally, in the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement delivery effect analysis model, the cloud server is specifically configured to:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
Dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
the input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
The third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second input data is in data connection with the third hidden layer;
the third concealing layer activates the second input data through the third activation function, then obtains fourth output data through matrix calculation, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
the normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result;
generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
Another aspect of the present invention provides a live advertisement delivery effect analysis method, which is applied to a live advertisement delivery effect analysis system, where the live advertisement delivery effect analysis system includes a cloud server, a plurality of live servers, a plurality of video servers, and a plurality of playing terminals, and the method includes:
the cloud server acquires historical live broadcast behavior data of a first host broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
the cloud server acquires historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
the cloud server marks the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a mark number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively;
Generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data;
the cloud server acquires live broadcast behavior data of a second main broadcast of the second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data in a second preset time range;
extracting fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live action data, the second live room data, the interactive action data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
Optionally, the step of the cloud server obtaining, from a first direct broadcast server in the plurality of direct broadcast servers, historical direct broadcast behavior data of a first host broadcast in a first direct broadcast room in a first preset time range and historical first direct broadcast room data in the first direct broadcast room includes:
The cloud server determines the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sends a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
after receiving the first data acquisition instruction, the first direct broadcast server selects a corresponding first data set according to the first data acquisition instruction;
and the first direct broadcast server processes and classifies the first data set to obtain the historical direct broadcast behavior data and the historical first direct broadcast room data respectively.
Optionally, the step of extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live action data, the historical first live room data, the historical interaction action data and the first playing terminal data respectively includes:
extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data;
extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data;
Extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data and expression data and limb action data from the historical interaction behavior data as the third evaluation data;
and extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data.
Optionally, the step of generating an advertisement delivery effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data includes:
establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data;
establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data;
establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data;
Establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter;
and inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model.
Optionally, the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement delivery effect analysis model includes:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
Dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
the input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
The third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second input data is in data connection with the third hidden layer;
the third concealing layer activates the second input data through the third activation function, then obtains fourth output data through matrix calculation, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
the normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result;
generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
By adopting the technical scheme, the cloud server is used for acquiring the historical live broadcast behavior data and the historical first direct broadcast inter-data from the first direct broadcast server, acquiring the historical interaction behavior data and the first play terminal data from the video server, and extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data after processing the historical live broadcast behavior data, the historical first direct broadcast inter-data, the historical interaction behavior data and the first play terminal data; generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data; and extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data, and obtaining an advertisement putting effect analysis report by combining an advertisement putting effect analysis model. By the scheme of the invention, the effect of advertising in the live broadcasting room based on the behavior state of the main broadcasting, the arrangement condition of the live broadcasting room, the behavior state of the audience and the attribute/performance of the video playing terminal can be comprehensively analyzed, and the efficiency and the accuracy are improved.
Drawings
FIG. 1 is a schematic block diagram of a live advertisement delivery effectiveness analysis system provided by one embodiment of the present invention;
fig. 2 is a flowchart of a method for analyzing a live advertisement delivery effect according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
A system and method for analyzing the effectiveness of live advertising according to some embodiments of the present invention are described below with reference to fig. 1-2.
As shown in fig. 1, one embodiment of the present invention provides a live advertisement delivery effect analysis system, including: the system comprises a cloud server, a plurality of live broadcast servers, a plurality of video servers and a plurality of playing terminals; wherein,
the cloud server is configured to:
acquiring historical live broadcast behavior data of a first main broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
the cloud server acquires historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
Marking the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a marking number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively;
generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data;
acquiring live broadcast behavior data of a second main broadcast of the second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second play terminal data in a second preset time range;
extracting fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live action data, the second live room data, the interactive action data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
It can be understood that, in this embodiment, the cloud server is used for overall management of the live broadcast server and the video server, and performs deep processing and universality processing of data; the live broadcast server is arranged on the side closer to the live broadcast camera system and is used for carrying out preliminary processing on the data transmitted by the live broadcast camera system, and the functions/management ranges of the live broadcast servers can be configured in a classified manner according to the regional range, the main broadcasting style, the live broadcast content type and the like; the video server is arranged on the side closer to the playing terminal and is used for carrying out adaptability processing on data sent to or sent by the playing terminal; the playing terminal is used for users/spectators to watch live videos and participate in live interaction through the live client, and can be intelligent terminals such as intelligent mobile phones, tablet computers, desktop computers and intelligent televisions.
According to the scheme of the embodiment of the invention, the cloud server acquires the historical live broadcast behavior data and the historical first direct broadcast inter-data from the first direct broadcast server, acquires the historical interaction behavior data and the first playing terminal data from the video server, and extracts first evaluation data, second evaluation data, third evaluation data and fourth evaluation data after processing the historical live broadcast behavior data, the historical first direct broadcast inter-data, the historical interaction behavior data and the first playing terminal data; generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data; and extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data, and obtaining an advertisement putting effect analysis report by combining an advertisement putting effect analysis model. By the scheme of the invention, the effect of advertising in the live broadcasting room based on the behavior state of the main broadcasting, the arrangement condition of the live broadcasting room, the behavior state of the audience and the attribute/performance of the video playing terminal can be comprehensively analyzed, and the efficiency and the accuracy are improved.
It should be noted that the block diagram of the live advertisement delivery effect analysis system shown in fig. 1 is only schematic, and the number of the illustrated modules does not limit the protection scope of the present invention.
In some possible embodiments of the present invention, in the step of the cloud server obtaining, from a first direct broadcast server of the plurality of direct broadcast servers, historical direct broadcast behavior data of a first host broadcast of a first direct broadcast room within a first preset time range, and historical first direct broadcast room data of the first direct broadcast room, the cloud server is specifically configured to:
determining the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sending a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
configuring the first direct broadcast server to:
after the first direct broadcast server receives the first data acquisition instruction, selecting a corresponding first data set according to the first data acquisition instruction;
and processing and classifying the first data set to respectively obtain the historical live broadcast behavior data and the historical first live broadcast room data.
It may be appreciated that, in this embodiment, the cloud server determines the first direct broadcast server from the plurality of direct broadcast servers according to a first rule (such as specifying a regional scope, specifying a hosting style, specifying a direct broadcast content type, etc.), and sends a first data acquisition instruction including the first preset time scope (determined according to periodicity, seasonal features, a great promotion period, etc. of the commodity transaction) to the first direct broadcast server; after receiving the first data acquisition instruction, the first direct broadcast server selects a corresponding first data set according to the first data acquisition instruction; the first direct broadcast server processes (e.g., removes redundant values/null values, normalizes, etc.) and classifies the first data set to obtain the historical direct broadcast behavior data and the historical first direct broadcast room data, respectively.
In some possible embodiments of the present invention, in the step of extracting first evaluation data, second evaluation data, third evaluation data, and fourth evaluation data from the historical live action data, the historical first live room data, the historical interaction action data, and the first playing terminal data, respectively, the cloud server is specifically configured to:
extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data;
extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data;
extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data and expression data and limb action data from the historical interaction behavior data as the third evaluation data;
and extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data.
It can be understood that, in order to more comprehensively analyze the advertisement delivery effect, comprehensive evaluation needs to be performed on factors having key influences on advertisement conversion in the live broadcast process, in this embodiment, first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data are extracted from the historical live broadcast behavior data as the first evaluation data, and the anchor performance has the most direct influence on the consumption behavior of the audience; extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data of the bargain from the historical first inter-broadcasting data as the second evaluation data, wherein factors to be considered are important when advertisement putting can be carried out when people, arranged visual effects, background music, advertisement putting frequency, commodity is a re-purchased commodity or not and the like in a live broadcasting room; extracting input barrage data, virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data, expression data and limb action data from the historical interaction behavior data as the third evaluation data, wherein the participation degree of audiences/the heat degree of interaction behavior can show the consumption tendency of the audiences; and extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data, wherein the data influence visual experience when a viewer watches the live video on the playing terminal, such as unclear commodity details caused by color display difference and resolution difference, and the like, and the advertisement data can carry explanatory/explanatory characters and display the explanatory characters on the first playing terminal when necessary to help the viewer select.
In some possible embodiments of the present invention, in the step of generating an advertisement delivery effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data, and the fourth evaluation data, the cloud server is specifically configured to:
establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data;
establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data;
establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data;
Establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter;
and inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model.
It may be understood that, in order to generate scientificity and accuracy of the model, the association relationship between each evaluation factor needs to be correctly straightened, in this embodiment, for the specific content of each item in the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data, first evaluation dimension data, second evaluation dimension data, third evaluation dimension data and fourth evaluation dimension data are respectively established based on the first time sequence, the second time sequence, the third time sequence and the fourth time sequence, and then the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data are input into a neural network to generate the advertisement delivery effect analysis model.
In some possible embodiments of the present invention, in the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data, and the fourth evaluation dimension data into a neural network to generate the advertisement delivery effect analysis model, the cloud server is specifically configured to:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
The input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
the third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second input data is in data connection with the third hidden layer;
the third concealing layer activates the second input data through the third activation function, then obtains fourth output data through matrix calculation, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
The normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result;
generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
It can be understood that, in order to generate an intelligent and accurate advertisement putting effect analysis model, the training is performed by using a neural network in the implementation, by constructing an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer and a first neural network of an output layer consisting of 3 neural units as the neural network, after giving an initial value to weights connected among the neurons, training can be started by inputting a training set data set, and then the advertisement putting effect analysis model is finally obtained through testing and adjustment. The advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement effect dimension indexes corresponding to each effect grade, and different advertisement throwing opportunities can be selected according to different reactions of different audiences; different advertisement effect grades and advertisement delivery dimension indexes corresponding to each effect grade can be output for reference of advertisers according to the requirements of different advertisers.
Referring to fig. 2, another embodiment of the present invention provides a live advertisement delivery effect analysis method, which is applied to a live advertisement delivery effect analysis system, where the live advertisement delivery effect analysis system includes a cloud server, a plurality of live servers, a plurality of video servers, and a plurality of playing terminals, and the method includes:
the cloud server acquires historical live broadcast behavior data of a first host broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
the cloud server acquires historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
the cloud server marks the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a mark number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively;
Generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data;
the cloud server acquires live broadcast behavior data of a second main broadcast of the second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data in a second preset time range;
extracting fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live action data, the second live room data, the interactive action data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
It can be understood that, in this embodiment, the cloud server is used for overall management of the live broadcast server and the video server, and performs deep processing and universality processing of data; the live broadcast server is arranged on the side closer to the live broadcast camera system and is used for carrying out preliminary processing on the data transmitted by the live broadcast camera system, and the functions/management ranges of the live broadcast servers can be configured in a classified manner according to the regional range, the main broadcasting style, the live broadcast content type and the like; the video server is arranged on the side closer to the playing terminal and is used for carrying out adaptability processing on data sent to or sent by the playing terminal; the playing terminal is used for users/spectators to watch live videos and participate in live interaction through the live client, and can be intelligent terminals such as intelligent mobile phones, tablet computers, desktop computers and intelligent televisions.
According to the scheme of the embodiment of the invention, the cloud server acquires the historical live broadcast behavior data and the historical first direct broadcast inter-data from the first direct broadcast server, acquires the historical interaction behavior data and the first playing terminal data from the video server, and extracts first evaluation data, second evaluation data, third evaluation data and fourth evaluation data after processing the historical live broadcast behavior data, the historical first direct broadcast inter-data, the historical interaction behavior data and the first playing terminal data; generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data; and extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data, and obtaining an advertisement putting effect analysis report by combining an advertisement putting effect analysis model. By the scheme of the invention, the effect of advertising in the live broadcasting room based on the behavior state of the main broadcasting, the arrangement condition of the live broadcasting room, the behavior state of the audience and the attribute/performance of the video playing terminal can be comprehensively analyzed, and the efficiency and the accuracy are improved.
In some possible embodiments of the present invention, the step of the cloud server obtaining, from a first direct broadcast server of the plurality of direct broadcast servers, historical direct broadcast behavior data of a first host broadcast of a first direct broadcast room within a first preset time range, and historical first direct broadcast room data of the first direct broadcast room includes:
the cloud server determines the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sends a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
after receiving the first data acquisition instruction, the first direct broadcast server selects a corresponding first data set according to the first data acquisition instruction;
and the first direct broadcast server processes and classifies the first data set to obtain the historical direct broadcast behavior data and the historical first direct broadcast room data respectively.
It may be appreciated that, in this embodiment, the cloud server determines the first direct broadcast server from the plurality of direct broadcast servers according to a first rule (such as specifying a regional scope, specifying a hosting style, specifying a direct broadcast content type, etc.), and sends a first data acquisition instruction including the first preset time scope (determined according to periodicity, seasonal features, a great promotion period, etc. of the commodity transaction) to the first direct broadcast server; after receiving the first data acquisition instruction, the first direct broadcast server selects a corresponding first data set according to the first data acquisition instruction; the first direct broadcast server processes (e.g., removes redundant values/null values, normalizes, etc.) and classifies the first data set to obtain the historical direct broadcast behavior data and the historical first direct broadcast room data, respectively.
In some possible embodiments of the present invention, the step of extracting first, second, third and fourth evaluation data from the historical live behavior data, the historical first live room data, the historical interaction behavior data and the first playing terminal data, respectively, includes:
extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data;
extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data;
extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data and expression data and limb action data from the historical interaction behavior data as the third evaluation data;
and extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data.
It can be understood that, in order to more comprehensively analyze the advertisement delivery effect, comprehensive evaluation needs to be performed on factors having key influences on advertisement conversion in the live broadcast process, in this embodiment, first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data are extracted from the historical live broadcast behavior data as the first evaluation data, and the anchor performance has the most direct influence on the consumption behavior of the audience; extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data of the bargain from the historical first inter-broadcasting data as the second evaluation data, wherein factors to be considered are important when advertisement putting can be carried out when people, arranged visual effects, background music, advertisement putting frequency, commodity is a re-purchased commodity or not and the like in a live broadcasting room; extracting input barrage data, virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchasing data, expression data and limb action data from the historical interaction behavior data as the third evaluation data, wherein the participation degree of audiences/the heat degree of interaction behavior can show the consumption tendency of the audiences; and extracting first terminal attribute data, first display parameters and first environment parameters when video is played from the first playing terminal data as fourth evaluation data, wherein the data influence visual experience when a viewer watches the live video on the playing terminal, such as unclear commodity details caused by color display difference and resolution difference, and the like, and the advertisement data can carry explanatory/explanatory characters and display the explanatory characters on the first playing terminal when necessary to help the viewer select.
In some possible embodiments of the present invention, the step of generating an advertisement delivery effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data, and the fourth evaluation data includes:
establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data;
establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data;
establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data;
Establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter;
and inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model.
It may be understood that, in order to generate scientificity and accuracy of the model, the association relationship between each evaluation factor needs to be correctly straightened, in this embodiment, for the specific content of each item in the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data, first evaluation dimension data, second evaluation dimension data, third evaluation dimension data and fourth evaluation dimension data are respectively established based on the first time sequence, the second time sequence, the third time sequence and the fourth time sequence, and then the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data are input into a neural network to generate the advertisement delivery effect analysis model.
In some possible embodiments of the present invention, the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data, and the fourth evaluation dimension data into a neural network to generate the advertisement delivery effect analysis model includes:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
The input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
the third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second input data is in data connection with the third hidden layer;
the third concealing layer activates the second input data through the third activation function, then obtains fourth output data through matrix calculation, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
The normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result; generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
It can be understood that, in order to generate an intelligent and accurate advertisement putting effect analysis model, the training is performed by using a neural network in the implementation, by constructing an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer and a first neural network of an output layer consisting of 3 neural units as the neural network, after giving an initial value to weights connected among the neurons, training can be started by inputting a training set data set, and then the advertisement putting effect analysis model is finally obtained through testing and adjustment. The advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement effect dimension indexes corresponding to each effect grade, and different advertisement throwing opportunities can be selected according to different reactions of different audiences; different advertisement effect grades and advertisement delivery dimension indexes corresponding to each effect grade can be output for reference of advertisers according to the requirements of different advertisers.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned method of the various embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
The foregoing has outlined rather broadly the more detailed description of embodiments of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, the above examples being provided solely to assist in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Although the present invention is disclosed above, the present invention is not limited thereto. Variations and modifications, including combinations of the different functions and implementation steps, as well as embodiments of the software and hardware, may be readily apparent to those skilled in the art without departing from the spirit and scope of the invention.
Claims (6)
1. A live advertisement delivery effect analysis system, comprising: the system comprises a cloud server, a plurality of live broadcast servers, a plurality of video servers and a plurality of playing terminals; wherein,
the cloud server is configured to:
acquiring historical live broadcast behavior data of a first main broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
acquiring historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
marking the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a marking number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively, wherein the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data are specifically as follows: extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data; extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data; extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchase data, expression data of audiences and limb action data of the audiences from the historical interaction behavior data as third evaluation data; extracting first terminal attribute data, a first display parameter and a first environment parameter when playing video from the first playing terminal data as fourth evaluation data;
Generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data, wherein the advertisement putting effect analysis model specifically comprises the following steps: establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data; establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data; establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data; establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter; inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model;
Correspondingly acquiring live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data in a second preset time range;
extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live broadcast behavior data, the second live broadcast room data, the interactive behavior data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
2. The live advertising effectiveness analysis system of claim 1, wherein in the step of the cloud server obtaining, from a first live server of the plurality of live servers, historical live behavior data of a first host of a first live room within a first preset time range, historical first live room data of the first live room, the cloud server is specifically configured to:
determining the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sending a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
Configuring the first direct broadcast server to:
after the first direct broadcast server receives the first data acquisition instruction, selecting a corresponding first data set according to the first data acquisition instruction;
and processing and classifying the first data set to respectively obtain the historical live broadcast behavior data and the historical first live broadcast room data.
3. The live advertisement placement effect analysis system according to claim 2, wherein in the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data, and the fourth evaluation dimension data into a neural network to generate the advertisement placement effect analysis model, the cloud server is specifically configured to:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
Dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
the input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
The third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second output data is in data connection with the third hidden layer;
the third concealing layer activates the second output data through the third activation function, then calculates fourth output data through a matrix, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
the normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result;
generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
4. A live advertisement putting effect analysis method, which is applied to the live advertisement putting effect analysis system as set forth in any one of claims 1 to 3, wherein the live advertisement putting effect analysis system includes a cloud server, a plurality of live servers, a plurality of video servers and a plurality of playing terminals, and the method includes:
the cloud server acquires historical live broadcast behavior data of a first host broadcast of a first live broadcast room and historical first live broadcast room data of the first live broadcast room in a first preset time range from a first live broadcast server in the plurality of live broadcast servers;
the cloud server acquires historical interaction behavior data of a first audience of the first living broadcast room and first playing terminal data of a playing terminal of the first audience in the first preset time range from a first video server of the plurality of video servers;
the cloud server marks the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data by taking the corresponding occurrence time as a mark number;
extracting first evaluation data, second evaluation data, third evaluation data and fourth evaluation data from the historical live broadcast behavior data, the historical first live broadcast room data, the historical interaction behavior data and the first playing terminal data respectively, wherein the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data are specifically: extracting first anchor action data, first anchor dressing data, first anchor voice data and first anchor virtual dressing data from the historical live broadcast behavior data as the first evaluation data; extracting historical online people number, historical environment data, historical background sound data, historical advertisement putting frequency and historical commodity data for delivery from the historical first inter-direct broadcasting data as second evaluation data; extracting input barrage data, gift virtual gift data, praise data, forwarding data, click advertisement data, shopping cart and commodity purchase data, expression data of audiences and limb action data of the audiences from the historical interaction behavior data as third evaluation data; extracting first terminal attribute data, a first display parameter and a first environment parameter when playing video from the first playing terminal data as fourth evaluation data;
Generating an advertisement putting effect analysis model according to the first evaluation data, the second evaluation data, the third evaluation data and the fourth evaluation data, wherein the advertisement putting effect analysis model specifically comprises the following steps: establishing first evaluation dimension data based on a first time sequence according to the first anchor action data, the first anchor dressing data, the first anchor voice data and the first anchor virtual makeup data; establishing second evaluation dimension data based on a second time sequence according to the historical online population, the historical environmental data, the historical background sound data, the historical advertisement putting frequency and the historical commodity data; establishing third interactive evaluation dimension data based on a third time sequence according to the input barrage data, the gift giving virtual gift data, the praise data, the forwarding data, the expression data and the limb action data, and establishing third advertisement feedback evaluation dimension data based on a fourth time sequence according to the click advertisement data, the shopping cart adding data and the commodity purchasing data; establishing fourth evaluation dimension data based on a fifth time sequence according to the first terminal attribute data, the first display parameter and the first environment parameter; inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a neural network to generate the advertisement putting effect analysis model;
The cloud server correspondingly acquires live broadcast behavior data of a second main broadcast of a second live broadcast room, second live broadcast room data of the second live broadcast room, interaction behavior data of a second audience of the second live broadcast room and second playing terminal data in a second preset time range;
extracting corresponding fifth evaluation data, sixth evaluation data, seventh evaluation data and eighth evaluation data from the live broadcast behavior data, the second live broadcast room data, the interactive behavior data and the second playing terminal data respectively;
and inputting the fifth evaluation data, the sixth evaluation data, the seventh evaluation data and the eighth evaluation data into the advertisement putting effect analysis model to obtain an advertisement putting effect analysis report.
5. The method for analyzing live advertisement delivery effect according to claim 4, wherein the step of the cloud server acquiring, from a first live server of the plurality of live servers, historical live behavior data of a first host of a first live room within a first preset time range, and historical first live room data of the first live room comprises:
the cloud server determines the first direct broadcasting server from the plurality of direct broadcasting servers according to a first rule, and sends a first data acquisition instruction containing the first preset time range to the first direct broadcasting server;
After receiving the first data acquisition instruction, the first direct broadcast server selects a corresponding first data set according to the first data acquisition instruction;
and the first direct broadcast server processes and classifies the first data set to obtain the historical direct broadcast behavior data and the historical first direct broadcast room data respectively.
6. The method of claim 5, wherein the step of inputting the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data, and the fourth evaluation dimension data into a neural network to generate the advertisement placement effect analysis model comprises:
selecting as the neural network a first neural network including an input layer consisting of 5 neural units, a first hidden layer consisting of 36 neural units, a first activation function, a second hidden layer consisting of 20 neural units, a second activation function, an analog output layer, a third hidden layer consisting of 9 neural units, a third activation function, a verification coefficient layer, and an output layer consisting of 3 neural units;
Dividing the first evaluation dimension data, the second evaluation dimension data, the third interaction evaluation dimension data, the third advertisement feedback evaluation dimension data and the fourth evaluation dimension data into a training set data set and a testing set data set according to a preset proportion;
inputting the training set data set into a neural unit constituting the input layer of the neural network to obtain first output data;
the input layer transmits the first output data to the first hidden layer which is connected with the input layer through matrix operation;
the first concealing layer receives first output data, activates the first output data through the first activation function to obtain second output data, and sends the activated second output data to the second concealing layer;
the second concealing layer receives the second output data, activates the second output data through the second activating function to obtain third output data, and sends the activated third output data to the analog output layer;
the analog output layer calculates the third output data through a matrix to obtain an analog output value, and inputs the analog output value into the third hidden layer;
The third concealing layer calculates the analog output value through a matrix to obtain a verification output result;
the second output data is in data connection with the third hidden layer;
the third concealing layer activates the second output data through the third activation function, then calculates fourth output data through a matrix, and sends the fourth output data and the verification output result to the verification coefficient layer for verification to obtain a normalization coefficient;
the normalization coefficient and the analog output value are sent to the output layer, and the output layer normalizes the analog output value to obtain a mimicry result;
generating a first advertisement putting effect analysis model by combining the mimicry result;
inputting the test set data set into the first advertisement putting effect analysis model to obtain positive feedback data and negative feedback data;
correcting the first advertisement putting effect analysis model according to the positive feedback data and the inverse feedback data to generate the advertisement putting effect analysis model;
the advertisement effect analysis model comprises a plurality of advertisement effect grades and advertisement dimension indexes corresponding to each effect grade.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310232368.XA CN116228320B (en) | 2023-03-01 | 2023-03-01 | Live advertisement putting effect analysis system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310232368.XA CN116228320B (en) | 2023-03-01 | 2023-03-01 | Live advertisement putting effect analysis system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116228320A CN116228320A (en) | 2023-06-06 |
CN116228320B true CN116228320B (en) | 2024-02-06 |
Family
ID=86588981
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310232368.XA Active CN116228320B (en) | 2023-03-01 | 2023-03-01 | Live advertisement putting effect analysis system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116228320B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107770580A (en) * | 2016-08-19 | 2018-03-06 | 北京市商汤科技开发有限公司 | Method of video image processing, device and terminal device |
CN108965916A (en) * | 2017-05-25 | 2018-12-07 | 腾讯科技(深圳)有限公司 | A kind of method, the method, device and equipment of model foundation of live video assessment |
CN111754267A (en) * | 2020-06-29 | 2020-10-09 | 蚌埠科睿达机械设计有限公司 | Data processing method and system based on block chain |
CN113506124A (en) * | 2021-06-21 | 2021-10-15 | 安徽西柚酷媒信息科技有限公司 | Method for evaluating media advertisement putting effect in intelligent business district |
WO2022077881A1 (en) * | 2020-10-16 | 2022-04-21 | 广州华多网络科技有限公司 | Virtual live streaming method and apparatus, device and storage medium |
CN115147152A (en) * | 2022-07-01 | 2022-10-04 | 浙江出海数字技术有限公司 | Advertisement putting effect data acquisition and statistical analysis system |
CN115392958A (en) * | 2022-08-15 | 2022-11-25 | 北京奇虎科技有限公司 | Live broadcast behavior analysis method, device, equipment and storage medium |
CN115719252A (en) * | 2022-12-01 | 2023-02-28 | 北京爱奇艺科技有限公司 | Video bullet screen advertisement delivery method, device, equipment and storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10217117B2 (en) * | 2011-09-15 | 2019-02-26 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods and services, entertainment and auctions, with geospatial mapping technology |
-
2023
- 2023-03-01 CN CN202310232368.XA patent/CN116228320B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107770580A (en) * | 2016-08-19 | 2018-03-06 | 北京市商汤科技开发有限公司 | Method of video image processing, device and terminal device |
CN108965916A (en) * | 2017-05-25 | 2018-12-07 | 腾讯科技(深圳)有限公司 | A kind of method, the method, device and equipment of model foundation of live video assessment |
CN111754267A (en) * | 2020-06-29 | 2020-10-09 | 蚌埠科睿达机械设计有限公司 | Data processing method and system based on block chain |
WO2022077881A1 (en) * | 2020-10-16 | 2022-04-21 | 广州华多网络科技有限公司 | Virtual live streaming method and apparatus, device and storage medium |
CN113506124A (en) * | 2021-06-21 | 2021-10-15 | 安徽西柚酷媒信息科技有限公司 | Method for evaluating media advertisement putting effect in intelligent business district |
CN115147152A (en) * | 2022-07-01 | 2022-10-04 | 浙江出海数字技术有限公司 | Advertisement putting effect data acquisition and statistical analysis system |
CN115392958A (en) * | 2022-08-15 | 2022-11-25 | 北京奇虎科技有限公司 | Live broadcast behavior analysis method, device, equipment and storage medium |
CN115719252A (en) * | 2022-12-01 | 2023-02-28 | 北京爱奇艺科技有限公司 | Video bullet screen advertisement delivery method, device, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
Y美术公司抖音直播营销策略研究;王娟;中国优秀硕士学位论文全文数据库 (哲学与人文科学辑)(第01期);F081-572 * |
Also Published As
Publication number | Publication date |
---|---|
CN116228320A (en) | 2023-06-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9861895B2 (en) | Apparatus and methods for multimedia games | |
CN108259936B (en) | Question-answering method based on live broadcast technology, server and storage medium | |
CN107808295B (en) | Multimedia data delivery method and device | |
CN106202393B (en) | Media information pushing method and device | |
Han et al. | An investigation of the smartphone user's in–game purchase intention | |
US20140200959A1 (en) | Predicting future performance of games | |
CN102216945B (en) | Networking with media fingerprints | |
CN105894313A (en) | Methods And Apparatus To Associate Transactions With Media Impressions | |
CN106302471B (en) | Method and device for recommending virtual gift | |
CN104966202A (en) | Network live broadcast transaction platform system | |
CN116340813B (en) | User behavior analysis system and method for live platform | |
CN105812844A (en) | User advertisement push method and system of TV | |
CN111612588A (en) | Commodity presentation method and device, computing equipment and computer-readable storage medium | |
US11783383B2 (en) | Method and system for providing advertising in immersive digital environments | |
CN116132749B (en) | Advertisement marketing method combined with live broadcast and carried goods | |
CN116228320B (en) | Live advertisement putting effect analysis system and method | |
JP2014002683A (en) | Content distribution device | |
US20220405784A1 (en) | Method and system for granular-level segmentation of users based on online activities in real-time | |
CN114996553A (en) | Dynamic video cover generation method | |
CN114429362A (en) | Advertisement product delivery method and device, electronic device and readable storage medium | |
CN113011912A (en) | Media information processing method, device, electronic equipment and storage medium | |
US20220414696A1 (en) | Method and system for running high performance marketing campaigns for granular-level segments of users in real-time | |
Ling Ge | Research on the Influence of Mobile E-commerce Webcast on Users' Online Shopping Intentions | |
US20230148188A1 (en) | Systems and methods for remote crowd participation during a live event | |
Liu | How to Promote In-Game Advertising based on User Experience Design |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240106 Address after: 510000 room 513, building 2, No. 96, panghe Road, Huangpu District, Guangzhou, Guangdong Province Applicant after: Guangzhou NetYouYou Data Technology Co.,Ltd. Address before: Building 201, No.1, Xunmei Science and Technology Plaza, No. 8 Keyuan Road, Science and Technology Park Community, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province, 518000 Applicant before: Shenzhen Kuaimei Cosmetics Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |