CN112911375A - Product propaganda artificial intelligence detection system and method - Google Patents
Product propaganda artificial intelligence detection system and method Download PDFInfo
- Publication number
- CN112911375A CN112911375A CN202011413481.0A CN202011413481A CN112911375A CN 112911375 A CN112911375 A CN 112911375A CN 202011413481 A CN202011413481 A CN 202011413481A CN 112911375 A CN112911375 A CN 112911375A
- Authority
- CN
- China
- Prior art keywords
- product
- residual error
- error network
- preset number
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/045—Combinations of networks
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4331—Caching operations, e.g. of an advertisement for later insertion during playback
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to a product propaganda artificial intelligence detection system, comprising: the video caching mechanism is arranged in a video playing terminal for playing the TV play and is used for caching an image to be played of the TV play currently played by the video playing terminal; the product identification mechanism is used for taking a plurality of instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely the name of each recommended product; and the name analysis device is used for sending out an illegal propaganda signal when the name of the product prohibited from propaganda is related in the received names of the recommended products. The invention also relates to an artificial intelligence detection method for product publicity. The product propaganda artificial intelligence detection system and method disclosed by the invention are wide in application and convenient to control. Because the customized depth residual error network can be adopted to intelligently identify each broadcast picture of the TV play, the product propaganda of the TV play can be effectively audited and managed.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a product propaganda artificial intelligence detection system and method.
Background
Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence. The artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is not human intelligence, but can think like a human, and can also exceed human intelligence.
Artificial intelligence is a gate-challenging science that people who work must understand computer knowledge, psychology and philosophy. Artificial intelligence is a science that includes a very broad spectrum of fields, such as machine learning, computer vision, etc., and in general, one of the main goals of artificial intelligence research is to make machines competent for complex tasks that usually require human intelligence to complete. But the understanding of this "complex work" is different for different times and for different people.
At present, the drama is widely played in a long playing time range as a main place for advertising by merchants, however, in a specific playing process, some products are listed in a prohibited promotion directory and cannot be promoted, for example, tobacco and various prohibited articles, and some playing platforms or playing time periods are dramas which are not allowed to play the promoted products, so that an efficient and non-manual drama auditing and managing mechanism is needed to complete auditing and managing of a plurality of played dramas.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a product propaganda artificial intelligence detection system and method, which can intelligently identify each broadcast picture of a TV play by adopting a customized depth residual error network so as to distinguish whether each broadcast picture relates to a propaganda product or not and whether the propaganda product violates rules or not, thereby improving the efficiency and speed of TV play auditing.
Therefore, the invention at least needs to have the following three key points:
(1) intelligently identifying each broadcast picture of the television play to acquire the name of each related product, and further identifying whether the product name belongs to an illegal propaganda product;
(2) judging whether the television series belongs to the television series type of the propaganda product or not based on the intelligent identification result of each broadcasting picture of the television series;
(3) and introducing a customized depth residual error network to identify products of the images of the television drama, wherein the depth residual error network takes the pictures of a first preset number as the input of the depth residual error network and takes the names of the products of a second preset number as the output, and the second preset number is smaller than the first preset number.
According to an aspect of the present invention, there is provided a product promotion artificial intelligence detection system, the system comprising:
the video caching mechanism is arranged in a video playing terminal for playing the TV play and is used for caching an image to be played of the TV play currently played by the video playing terminal;
the brightness correction device is connected with the video cache mechanism and used for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
the directional processing equipment is arranged in the video playing terminal, is connected with the brightness correction equipment and is used for executing harmonic mean filtering processing on the received current correction image so as to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
the product identification mechanism is connected with the data merging equipment and used for taking the instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis device is connected with the product identification mechanism and is used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related to the name of each received recommended product;
the mark execution device is connected with the name analysis device and used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
According to another aspect of the present invention, there is also provided a product promotion artificial intelligence detection method, including:
the method comprises the steps that a video caching mechanism is arranged in a video playing terminal for playing the TV play and used for caching an image to be played of the TV play currently played by the video playing terminal;
using brightness correction equipment, connected with the video caching mechanism, for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area therein, and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
using directional processing equipment, setting the directional processing equipment in the video playing terminal, connecting with the brightness correction equipment, and executing harmonic mean filtering processing on the received current correction image to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
a product identification mechanism is used, is connected with the data merging equipment and is used for taking the plurality of instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis equipment is connected with the product identification mechanism and used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related in the received names of the recommended products;
the using mark execution device is connected with the name analysis device and is used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
The product propaganda artificial intelligence detection system and method disclosed by the invention are wide in application and convenient to control. Because the customized depth residual error network can be adopted to intelligently identify each broadcast picture of the TV play, the product propaganda of the TV play can be effectively audited and managed.
Detailed Description
Embodiments of the product promotion artificial intelligence detection system and method of the present invention will be described in detail below.
A television show is a form of a show that is specifically shown on television. It is compatible with elements of modern art such as film, drama, literature, music, dance, painting and moulding, and is a modern artistic style formed by integrating the expression methods of stage and film art and adapting to the characteristics of TV broadcast. Generally, a single episode and a series (tv album) are divided. The television series is developed along with the birth of the television broadcasting industry, a certain pushing effect is provided after the television series is developed, so that some television series websites are bred, and the typical classified television series online watching websites are popular with the public. In life, the definition of television series has been narrowed to only the television episode series, not other forms.
A tv show (also called an episode, a tv show program, a tv show, or a tv series) is an art style formed by combining the expression methods of stage and movie art in accordance with the characteristics of tv broadcast. The common unit play and continuous play are produced by using television technology and are shown through a television network. The invention of the television is continuously popularized, and finally, the artistic appreciation mode of people is changed. The playing platform of the television play is generally called a theater.
At present, the drama is widely played in a long playing time range as a main place for advertising by merchants, however, in a specific playing process, some products are listed in a prohibited promotion directory and cannot be promoted, for example, tobacco and various prohibited articles, and some playing platforms or playing time periods are dramas which are not allowed to play the promoted products, so that an efficient and non-manual drama auditing and managing mechanism is needed to complete auditing and managing of a plurality of played dramas.
In order to overcome the defects, the invention builds the artificial intelligent detection system and the artificial intelligent detection method for product propaganda, and can effectively solve the corresponding technical problem.
The product promotion artificial intelligence detection system shown according to the embodiment of the invention comprises:
the video caching mechanism is arranged in a video playing terminal for playing the TV play and is used for caching an image to be played of the TV play currently played by the video playing terminal;
the brightness correction device is connected with the video cache mechanism and used for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
the directional processing equipment is arranged in the video playing terminal, is connected with the brightness correction equipment and is used for executing harmonic mean filtering processing on the received current correction image so as to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
the product identification mechanism is connected with the data merging equipment and used for taking the instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis device is connected with the product identification mechanism and is used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related to the name of each received recommended product;
the mark execution device is connected with the name analysis device and used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
Next, the specific structure of the product promotion artificial intelligence detection system of the present invention will be further described.
In the product promotion artificial intelligence detection system:
the name analysis device is also used for sending out a compliance promotion signal when the name of the product prohibited for promotion is not related in the received names of the recommended products;
and the name analysis equipment is also used for sending a product unidentified instruction when the name of each received recommended product is empty.
In the product promotion artificial intelligence detection system:
and the mark execution equipment is also used for marking the current playing TV play with the un-advertised product when the product un-identified instruction is received.
In the product promotion artificial intelligence detection system:
training the deep residual network comprises: the method comprises the steps of adopting a first preset number of pictures including product objects or not including the product objects as input of a depth residual error network, and adopting a first preset number of pictures including the product objects or not including the product objects to relate to a second preset number of products as output to train the depth residual error network.
In the product promotion artificial intelligence detection system:
when the names of the second preset number of products output by the depth residual error network are all empty, no product exists in the first preset number of pictures input by the depth residual error network.
The artificial intelligence detection method for the product publicity shown according to the embodiment of the invention comprises the following steps:
the method comprises the steps that a video caching mechanism is arranged in a video playing terminal for playing the TV play and used for caching an image to be played of the TV play currently played by the video playing terminal;
using brightness correction equipment, connected with the video caching mechanism, for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area therein, and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
using directional processing equipment, setting the directional processing equipment in the video playing terminal, connecting with the brightness correction equipment, and executing harmonic mean filtering processing on the received current correction image to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
a product identification mechanism is used, is connected with the data merging equipment and is used for taking the plurality of instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis equipment is connected with the product identification mechanism and used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related in the received names of the recommended products;
the using mark execution device is connected with the name analysis device and is used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
Next, the specific steps of the product promotion artificial intelligence detection method of the present invention will be further described.
The product propaganda artificial intelligence detection method comprises the following steps: the name analysis device is also used for sending out a compliance promotion signal when the name of the product prohibited for promotion is not related in the received names of the recommended products;
and the name analysis equipment is also used for sending a product unidentified instruction when the name of each received recommended product is empty.
The product propaganda artificial intelligence detection method comprises the following steps:
and the mark execution equipment is also used for marking the current playing TV play with the un-advertised product when the product un-identified instruction is received.
The product propaganda artificial intelligence detection method comprises the following steps:
training the deep residual network comprises: the method comprises the steps of adopting a first preset number of pictures including product objects or not including the product objects as input of a depth residual error network, and adopting a first preset number of pictures including the product objects or not including the product objects to relate to a second preset number of products as output to train the depth residual error network.
The product propaganda artificial intelligence detection method comprises the following steps:
when the names of the second preset number of products output by the depth residual error network are all empty, no product exists in the first preset number of pictures input by the depth residual error network.
In addition, in the product promotion artificial intelligence detection system and method of the invention, a Deep Residual Shrinkage Network (DRSN) can be adopted to replace the Deep Residual Network. The Deep Residual shrinkage Network is an artificial intelligence algorithm, is a novel improvement of a Deep Residual Network (ResNet), introduces soft thresholding as a nonlinear layer into a Network structure of the ResNet, and aims to improve the characteristic learning effect of a Deep learning method on noise-containing data or complex data. More specifically, the prototype of the depth residual shrinkage Network can be considered to come from the Squeeze-and-Excitation Network (SENET), which essentially replaces the weighting of each feature channel in the SENET with the soft thresholding of each feature channel.
The foregoing description of the invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. The breadth and scope of the present invention should not be limited by any of the above-described exemplary embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art. Such modifications and variations include any relevant combination of the features disclosed. The embodiments were chosen and described in order to best explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to understand the invention for various embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the following claims and their equivalents.
Claims (10)
1. An artificial intelligence detection system for product promotion, the system comprising:
the video caching mechanism is arranged in a video playing terminal for playing the TV play and is used for caching an image to be played of the TV play currently played by the video playing terminal;
the brightness correction device is connected with the video cache mechanism and used for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
the directional processing equipment is arranged in the video playing terminal, is connected with the brightness correction equipment and is used for executing harmonic mean filtering processing on the received current correction image so as to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
the product identification mechanism is connected with the data merging equipment and used for taking the instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis device is connected with the product identification mechanism and is used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related to the name of each received recommended product;
the mark execution device is connected with the name analysis device and used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
2. The product promotion artificial intelligence detection system of claim 1, characterized in that:
the name analysis device is also used for sending out a compliance promotion signal when the name of the product prohibited for promotion is not related in the received names of the recommended products;
and the name analysis equipment is also used for sending a product unidentified instruction when the name of each received recommended product is empty.
3. The product promotion artificial intelligence detection system of claim 2, wherein:
and the mark execution equipment is also used for marking the current playing TV play with the un-advertised product when the product un-identified instruction is received.
4. The product promotion artificial intelligence detection system of claim 3, wherein:
training the deep residual network comprises: the method comprises the steps of adopting a first preset number of pictures including product objects or not including the product objects as input of a depth residual error network, and adopting a first preset number of pictures including the product objects or not including the product objects to relate to a second preset number of products as output to train the depth residual error network.
5. The product promotion artificial intelligence detection system of claim 4, wherein:
when the names of the second preset number of products output by the depth residual error network are all empty, no product exists in the first preset number of pictures input by the depth residual error network.
6. An artificial intelligence detection method for product publicity is characterized by comprising the following steps:
the method comprises the steps that a video caching mechanism is arranged in a video playing terminal for playing the TV play and used for caching an image to be played of the TV play currently played by the video playing terminal;
using brightness correction equipment, connected with the video caching mechanism, for performing brightness unevenness detection on the received image to be played to obtain a brightness unevenness area therein, and performing correction processing on the brightness unevenness area in the image to be played to obtain a current correction image;
using directional processing equipment, setting the directional processing equipment in the video playing terminal, connecting with the brightness correction equipment, and executing harmonic mean filtering processing on the received current correction image to obtain an instant processing image;
the data merging equipment is connected with the directional processing equipment and is used for obtaining a plurality of instant processing images which are continuous on a time axis and respectively correspond to a plurality of images to be played, and the number of the plurality of instant processing images is equal to a first preset number;
a product identification mechanism is used, is connected with the data merging equipment and is used for taking the plurality of instant processing images as input data of a depth residual error network so as to execute the depth residual error network and obtain output data of the depth residual error network, namely names of various recommended products;
the name analysis equipment is connected with the product identification mechanism and used for sending out illegal propaganda signals when the name of the product prohibited from propaganda is related in the received names of the recommended products;
the using mark execution device is connected with the name analysis device and is used for marking the propaganda product on the current playing TV play when receiving the product identification instruction;
the product identification mechanism is internally provided with an information storage unit for storing a product database, the product database is used for storing a deep residual error network, the deep residual error network takes pictures of a first preset number as input of the deep residual error network and names of products of a second preset number as output, and the second preset number is smaller than the first preset number;
the product equipment mechanism is also internally provided with a network training unit which is connected with the information storage unit to acquire a product database and train the deep residual error network;
the name analysis equipment is further used for sending out a product identification instruction when the name of each received recommended product is not empty.
7. The product promotion artificial intelligence detection method of claim 6, characterized in that:
the name analysis device is also used for sending out a compliance promotion signal when the name of the product prohibited for promotion is not related in the received names of the recommended products;
and the name analysis equipment is also used for sending a product unidentified instruction when the name of each received recommended product is empty.
8. The product promotion artificial intelligence detection method of claim 7, characterized in that:
and the mark execution equipment is also used for marking the current playing TV play with the un-advertised product when the product un-identified instruction is received.
9. The product promotion artificial intelligence detection method of claim 8, characterized in that:
training the deep residual network comprises: the method comprises the steps of adopting a first preset number of pictures including product objects or not including the product objects as input of a depth residual error network, and adopting a first preset number of pictures including the product objects or not including the product objects to relate to a second preset number of products as output to train the depth residual error network.
10. The product promotion artificial intelligence detection method of claim 9, characterized in that:
when the names of the second preset number of products output by the depth residual error network are all empty, no product exists in the first preset number of pictures input by the depth residual error network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011413481.0A CN112911375B (en) | 2020-12-07 | 2020-12-07 | Product propaganda artificial intelligence detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011413481.0A CN112911375B (en) | 2020-12-07 | 2020-12-07 | Product propaganda artificial intelligence detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112911375A true CN112911375A (en) | 2021-06-04 |
| CN112911375B CN112911375B (en) | 2021-11-02 |
Family
ID=76111420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011413481.0A Active CN112911375B (en) | 2020-12-07 | 2020-12-07 | Product propaganda artificial intelligence detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112911375B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109495783A (en) * | 2018-11-02 | 2019-03-19 | 平安科技（深圳）有限公司 | Video reviewing method, device, electronic equipment and medium |
| CN110099303A (en) * | 2019-06-05 | 2019-08-06 | 四川长虹电器股份有限公司 | A kind of media play system based on artificial intelligence |
| US20190347484A1 (en) * | 2018-05-10 | 2019-11-14 | Apptarix Mobility Solutions Pvt Ltd | System and method for grouping independent machine learnt artificial intelligence to generate collective "machine wisdom" to obtain higher accuracy in identification of tags, objects and actions in a video |
| CN111143612A (en) * | 2019-12-27 | 2020-05-12 | 广州市百果园信息技术有限公司 | Video auditing model training method, video auditing method and related device |
| CN111640150A (en) * | 2019-09-20 | 2020-09-08 | 于贵庆 | Video data source analysis system and method |
-
2020
- 2020-12-07 CN CN202011413481.0A patent/CN112911375B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190347484A1 (en) * | 2018-05-10 | 2019-11-14 | Apptarix Mobility Solutions Pvt Ltd | System and method for grouping independent machine learnt artificial intelligence to generate collective "machine wisdom" to obtain higher accuracy in identification of tags, objects and actions in a video |
| CN109495783A (en) * | 2018-11-02 | 2019-03-19 | 平安科技（深圳）有限公司 | Video reviewing method, device, electronic equipment and medium |
| CN110099303A (en) * | 2019-06-05 | 2019-08-06 | 四川长虹电器股份有限公司 | A kind of media play system based on artificial intelligence |
| CN111640150A (en) * | 2019-09-20 | 2020-09-08 | 于贵庆 | Video data source analysis system and method |
| CN111143612A (en) * | 2019-12-27 | 2020-05-12 | 广州市百果园信息技术有限公司 | Video auditing model training method, video auditing method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112911375B (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110740387B (en) | Barrage editing method, intelligent terminal and storage medium | |
| CN103052953B (en) | Messaging device, information processing method | |
| CN103686344B (en) | Strengthen video system and method | |
| WO2012020667A1 (en) | Information processing device, information processing method, and program | |
| CN106937172A (en) | Interactive approach and device during video playback based on artificial intelligence | |
| CN107562680A (en) | Data processing method, device and terminal device | |
| CN108307229A (en) | A kind of processing method and equipment of video-audio data | |
| Bielby et al. | Aesthetics of television criticism: Mapping critics’ reviews in an era of industry transformation | |
| CN103369408B (en) | Method for the content channel using user feedback | |
| CN113469152A (en) | Similar video detection method and device | |
| Sabin et al. | Cop shows: A critical history of police dramas on television | |
| CN111259245A (en) | Work pushing method and device and storage medium | |
| CN112911375B (en) | Product propaganda artificial intelligence detection system and method | |
| CN107846615A (en) | Visualize advertisement delivery system, put-on method and advertisement broadcast method | |
| CN112685637A (en) | Intelligent interaction method of intelligent equipment and intelligent equipment | |
| Bowrey et al. | Law and Creativity in the Age of the Entertainment Franchise | |
| London | Producing children’s television | |
| Chen et al. | RETRACTED: Innovation Strategy of Film and Television Creation under the Background of Big Data | |
| KR101674310B1 (en) | System and method for matching advertisement for providing advertisement associated with video contents | |
| Steward | Making the commercial personal: The authorial value of Jerry Bruckheimer Television | |
| Gracy | The imperative to preserve: competing definitions of value in the world of film preservation | |
| Newsinger | The ‘Cultural Burden’: regional film policy and practice in England | |
| Simpson | Black Images in Film—the 1940s to the Early 1960s | |
| US20230148007A1 (en) | System and method for playing audio corresponding to an image | |
| Baker et al. | Netflix, Dark Fantastic Genres and Intergenerational Viewing: Family Watch Together TV |
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: 20211012 Address after: 215500 science and Innovation Park, Changshu Economic and Technological Development Zone, Suzhou City, Jiangsu Province Applicant after: JIANGSU ZHONGBO JINGCHEN INFORMATION TECHNOLOGY Co.,Ltd. Address before: 225300 601a, building 1, No. 98, Yingchun East Road, hailing Industrial Park, Taizhou City, Jiangsu Province Applicant before: Taizhou langjiaxin Network Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |