CN113438544A - Processing method of internet streaming media big data barrage - Google Patents
Processing method of internet streaming media big data barrage Download PDFInfo
- Publication number
- CN113438544A CN113438544A CN202110703106.8A CN202110703106A CN113438544A CN 113438544 A CN113438544 A CN 113438544A CN 202110703106 A CN202110703106 A CN 202110703106A CN 113438544 A CN113438544 A CN 113438544A
- Authority
- CN
- China
- Prior art keywords
- barrage
- character data
- streaming media
- bullet screen
- data
- 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.)
- Withdrawn
Links
Images
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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/75—Media network packet handling
-
- 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
- H04N21/454—Content or additional data filtering, e.g. blocking advertisements
-
- 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
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
Abstract
The invention relates to an internet streaming media big data bullet screen processing system which comprises an image recognition module, an illegal vocabulary database, a vocabulary filtering module, a screening module, a bullet screen obtaining module and a control module, wherein the bullet screen obtaining module is used for comparing the number of a first bullet screen in a first unit time with the preset number in the first unit time, if the number of the first bullet screen in the first unit time is larger than the preset number in the first unit time, converting a first bullet screen associated with third character data into a second bullet screen, and synthesizing the second bullet screen and streaming media to send the second bullet screen to a user terminal. The invention screens the barrage related to the first text data in each frame image of the streaming media as the second barrage finally output to the user terminal through the mode, thereby ensuring that when a barrage with huge data volume is input simultaneously, the barrage data related to the video content can be screened as much as possible to be synthesized with the streaming media and sent to the user terminal, and further filtering the barrage data which is irrelevant to the streaming media content, such as abuse, advertisements, gossip and the like.
Description
The patent application of the invention is divisional application. The patent number of the original case is 2019106472422, the application date is 7/17/2019, and the invention name is an internet streaming media big data bullet screen processing system and a processing method.
Technical Field
The invention relates to a big data barrage technology, in particular to a system for processing a stream media big data barrage.
Background
Currently, the barrage becomes an important element for watching videos and live broadcasts for many audiences. More and more people watch the bullet screen and send the bullet screen become the current trend. However, as the number of bullet screens increases, many illegal messages such as yellow, violence, advertisement, religion, politics, etc. appear on the bullet screens. Even if illegal information is not available, the barrages are mutually rhythmic, and the transmitted barrages irrelevant to the streaming media content can influence the watching of the user.
Therefore, a processing system for managing the streaming media big data barrage is needed.
Disclosure of Invention
The invention aims to provide a processing system for governing a streaming media big data barrage.
The invention relates to an internet streaming media big data barrage processing system, which comprises
The image identification module is used for identifying first character data appearing in each frame in the streaming media;
an illegal vocabulary database for storing illegal vocabularies;
the vocabulary filtering module is used for comparing the first character data with the illegal vocabulary in the illegal vocabulary database, and if the first character data are not matched with the illegal vocabulary in the illegal vocabulary database, the first character data are converted into second character data;
the screening module is used for converting the second character data which continuously appear and exceed the preset frame number into third character data;
the bullet screen acquisition module is used for inputting a first bullet screen;
and the control module is used for comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number of the first barrage in the first unit time is larger than the preset number, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage to the user terminal.
The invention relates to an internet streaming media big data barrage processing system, wherein a mode that a control module converts a first barrage associated with third character data into a second barrage is as follows:
comparing the character number a of the characters which are the same as the first bullet screen data in each first bullet screen according to the characters of the third character data and the character number n;
and converting a part of the first bullet screen, which is close to the input time and is closer to the time of a first frame in which the third character data continuously appears, into a second bullet screen according to the sequence of the number of characters a from large to small and the same number of characters a, wherein the number of the second bullet screens is equal to the preset number in the first unit time.
The invention relates to an internet streaming media big data barrage processing system, wherein a mode of identifying first character data appearing in each frame in a streaming media by an image identification module is as follows:
defining the position of each frame in the streaming media in which the first character data is identified to exceed a first preset threshold value in a second unit time as a caption area, and setting other positions of each frame as non-caption areas;
judging whether the first character data exceeds a second preset threshold value at the second time, if not, outputting the first character data, and if so, outputting a harmony score d according to the character number b and the position coefficient c of each first character data, which are the same as the illegal words in the illegal word database, according to the following formula:
wherein, when the first text data is in the caption area, c is 0.9, and when the first text data is in the non-caption area, c is 0.1.1;
and outputting first character data of a second preset threshold value in a descending order.
The invention relates to an internet streaming media big data bullet screen processing system, wherein a second preset threshold value is (1, + ∞).
The invention relates to an internet streaming media big data bullet screen processing system, wherein 200 second preset thresholds are provided.
The invention relates to an internet streaming media big data bullet screen processing system, wherein the second unit time is (60s, infinity).
The invention relates to an internet streaming media big data bullet screen processing system, wherein the second unit time is 300 s.
The invention relates to a processing method of an internet streaming media big data bullet screen processing system, which comprises the following steps:
step 1, storing the illegal vocabulary,
step 2, identifying first character data appearing in each frame in the streaming media;
step 3, comparing the first character data with the illegal words in the illegal word database, and if the first character data and the illegal words are not matched, converting the first character data into second character data;
step 4, converting the second character data which continuously appear and exceed the preset frame number into third character data;
step 5, inputting a first bullet screen;
and 6, comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number of the first barrage in the first unit time is larger than the preset number in the first unit time, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage to the user terminal.
The difference between the internet streaming media big data barrage processing system and the prior art is that the internet streaming media big data barrage processing system screens the barrage related to the first text data in each frame image of the streaming media through the mode to serve as the second barrage finally output to the user terminal, so that when the barrage with huge data volume is input simultaneously, the barrage data related to the video content and the streaming media can be screened as much as possible to be synthesized and sent to the user terminal, and the barrage data which is irrelevant to the streaming media content, such as abuse, advertisements, gossip and the like, can be filtered.
The following describes a system for processing a large data barrage of internet streaming media according to the present invention with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart of a method of an internet streaming media big data bullet screen processing system.
Detailed Description
As shown in FIG. 1, the present invention provides a system for processing a large data barrage of internet streaming media, which comprises
The image identification module is used for identifying first character data appearing in each frame in the streaming media;
an illegal vocabulary database for storing illegal vocabularies;
the vocabulary filtering module is used for comparing the first character data with the illegal vocabulary in the illegal vocabulary database, and if the first character data are not matched with the illegal vocabulary in the illegal vocabulary database, the first character data are converted into second character data;
the screening module is used for converting the second character data which continuously appear and exceed the preset frame number into third character data;
the bullet screen acquisition module is used for inputting a first bullet screen;
and the control module is used for comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number of the first barrage in the first unit time is larger than the preset number, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage to the user terminal.
The invention screens the barrage related to the first text data in each frame image of the streaming media as the second barrage finally output to the user terminal through the mode, thereby ensuring that when a barrage with huge data volume is input simultaneously, the barrage data related to the video content can be screened as much as possible to be synthesized with the streaming media and sent to the user terminal, and further filtering the barrage data which is irrelevant to the streaming media content, such as abuse, advertisements, gossip and the like.
The streaming media can be video on demand or live video.
Wherein the preset number of frames may be (1, 600).
Wherein, when the frame number of the streaming media is usually 30 frames per second, the preset frame number is preferably 150 frames;
when the number of frames of the streaming media is usually 60 frames per second, the preset number of frames is preferably 300 frames.
The illegal words can be telephone numbers, addresses, abusive words, advertisement words, political words, mars, wherein the mars can refer to scrambled words or illegal fonts, because the scrambled words can be words generated due to error recognition in the recognition picture, and the illegal fonts can imply advertisements, pornography, politics, violence, and the like.
The number of the first bullet screens in the first unit time and the preset number of the first bullet screens in the first unit time can be represented by a speed unit, for example, 5 bullet screens per second, where the first unit time can be 1 second, the preset number can be (1, 100), and preferably 10 bullet screens, because too many bullet screens can be stacked, the user cannot see the content of the bullet screens, and the significance of the bullet screens is lost.
When the method is used, for example, the frame number of a live video of the streaming media is 30 frames per second, and the preset frame number is preferably 150 frames, that is, the time represented by the preset frame number of the identified second text data is 5 seconds, then, the first text data is identified in each frame through the image identification module; the first character data of the vocabulary filtering module, which is not matched with the illegal vocabulary, is converted into second character data; the screening module converts the second character data which continuously appear for more than 5 seconds into third character data; acquiring a first barrage input by a user; and comparing the speed of the first barrage with the preset number in the first unit time, if the speed of the first barrage is larger than the preset number, only outputting the first barrage associated with the third character data, converting the first barrage into a second barrage and outputting the second barrage to the user terminal.
Preferably, the manner of converting the first barrage associated with the third text data into the second barrage by the control module is as follows:
comparing the character number a of the characters which are the same as the first bullet screen data in each first bullet screen according to the characters of the third character data and the character number n;
and converting a part of the first bullet screen, which is close to the input time and is closer to the time of a first frame in which the third character data continuously appears, into a second bullet screen according to the sequence of the number of characters a from large to small and the same number of characters a, wherein the number of the second bullet screens is equal to the preset number in the first unit time.
According to the method, under the condition that the preset number in the first unit time allows, the first bullet screen which is more similar to the character number of the third character data, has earlier input time and better accords with the streaming media content is screened out and converted into the second bullet screen.
When in use, the following can be specifically mentioned: if the number of the first bullet screens in the first unit time is larger than the preset number of the first bullet screens in the first unit time, converting a part of the first bullet screens, of which the input time is closer to the time of the first frames in which the third character data continuously appear, into second bullet screens;
if the number of the first bullet screens in the first unit time is less than or equal to the preset number in the first unit time, comparing the sum of the number of the first bullet screens in the first unit time, in which a is n-1, and the number of the first bullet screens in the first unit time, in which a is n, with the preset number in the first unit time, if the sum is greater than the preset number in the first unit time, converting a part of the first bullet screens in which the input time is closer to the time of the first frame in which the third character data continuously appears, in which a is n-1, and the first bullet screens in which a is n, into second bullet screens,
if the sum of the number of the first bullet screen with a-n-2, the first bullet screen with a-n-1 and the first bullet screen with a-n is less than or equal to the preset number in the first unit time, if the sum of the number of the first bullet screen with a-n and the first bullet screen with a-n is greater than the preset number in the first unit time, converting a part of the first bullet screen with a-n-2, the first bullet screen with a-n-1 and the first bullet screen with a-n, which are closer to the time of the first frame in which the input time and the third character data continuously appear, into a second bullet screen,
if the sum of the number of the first bullet screen with a-n-3, the first bullet screen with a-n-2, the first bullet screen with a-n-1 and the first bullet screen with a-n is less than or equal to the preset number in the first unit time, if the sum is greater than the preset number in the first unit time, a part a of the first bullet screen with a-n-3 and a first bullet screen with a-n-2, a first bullet screen with a-n-1 and a first bullet screen with a-n, which are the parts of the input time and the time of the first frame where the third character data continuously appears, are converted into a second bullet screen,
......
......
for example, the frame number of the live video of the streaming media is 30 frames per second, and the preset frame number is preferably 150 frames, that is, the time represented by the preset frame number of the identified second text data is 5 seconds, and the third text data is "i love china", so that n is 4. If the plurality of input first bullet screens are respectively 'i love in china', 'china', and the input time of the first frame which is continuously present from the third character data 'i love in china' is respectively: if "I love China" for 3 seconds, "I love China" for 2.7 seconds, "love China" for 4.7 seconds, "love China" for 1.7 seconds, "China" for 3.7 seconds, the above 5 units are bullet curtains in the first unit time, and the preset number allowed to appear in the first unit time is 4, the first bullet screen of 'I love China', 'I love China' and 'love China' with the same character number level is converted into the second bullet screen, and then the comparison between 'love China' 1.7 seconds and 'China' 3.7 seconds is carried out, because the time of the first frame which is a short distance from the patriotic to the third character data and appears continuously is only 1.7 seconds, the patriotic is converted into the second barrage, and the Chinese is deleted, therefore, the first bullet screen which is more similar to the third character data in character quantity and earlier in input time and more accords with the streaming media content is screened out and converted into the second bullet screen.
Wherein, 1 Chinese character, 1 English word between two spaces, 1 Arabic figure are a character quantity, the punctuation mark does not count the character quantity, of course, the punctuation mark can also record the character quantity.
Preferably, the manner of identifying the first text data appearing in each frame in the streaming media by the image identification module is as follows:
defining the position of each frame in the streaming media in which the first character data is identified to exceed a first preset threshold value in a second unit time as a caption area, and setting other positions of each frame as non-caption areas;
judging whether the first character data exceeds a second preset threshold value at the second time, if not, outputting the first character data, and if so, outputting a harmony score d according to the character number b and the position coefficient c of each first character data, which are the same as the illegal words in the illegal word database, according to the following formula:
wherein, when the first text data is in the caption area, c is 0.9, and when the first text data is in the non-caption area, c is 0.1.1;
and outputting first character data of a second preset threshold value in a descending order.
The invention avoids generating excessive meaningless first character data caused by the occurrence of messy codes when converting characters in the picture by limiting the number of the first character data captured in the picture, and the messy codes of characters are approximately the same, for example, the messy codes of characters are complex characters, one character can be arranged in an illegal vocabulary, the first character data with the same character number b as the illegal vocabulary is removed, and the non-caption area can represent the character style which really appears in the streaming media, compared with the caption, the invention can embody the content of the streaming media, thereby improving the weight of the first character data of the non-caption area and reducing the weight of the first character data of the caption area.
The unit of the number b of characters is one.
The second preset threshold may be (1, + ∞), preferably 200, that is, within five minutes, if the number of the recognized first text data is less than or equal to 200, the first text data is output, and if the number of the recognized first text data is greater than 200, the first text data is screened, so that excessive first text data generated due to excessive messy codes generated due to bug and the like in the image conversion text is avoided, the problem of occupying the storage capacity of the database is avoided, and acceleration and optimization are also brought to the matching of the first text data.
The second unit time is (60s, + ∞), preferably 5 minutes, that is, the second unit time may be more than one minute.
Wherein the first preset threshold may be (10%, 99%), preferably 30%. That is, if the number of times that the first character data appears at a position exceeds 30% every 5 minutes, it is determined that the position is a caption area and the other positions are non-caption areas.
Preferably, the second preset threshold is (1, + ∞).
Preferably, the number of the second preset threshold is 200.
Preferably, the second unit time is (60s, + ∞).
Preferably, the second unit time is 300 s.
The invention relates to a processing method of an internet streaming media big data bullet screen processing system, which comprises the following steps:
step 1, storing the illegal vocabulary,
step 2, identifying first character data appearing in each frame in the streaming media;
step 3, comparing the first character data with the illegal words in the illegal word database, and if the first character data and the illegal words are not matched, converting the first character data into second character data;
step 4, converting the second character data which continuously appear and exceed the preset frame number into third character data;
step 5, inputting a first bullet screen;
and 6, comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number of the first barrage in the first unit time is larger than the preset number in the first unit time, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage to the user terminal.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solution of the present invention by those skilled in the art should fall within the protection scope defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (3)
1. A processing method of an internet streaming media big data barrage processing system is characterized by comprising the following steps:
step 1, storing the illegal vocabulary,
step 2, identifying first character data appearing in each frame in the streaming media;
step 3, comparing the first character data with the illegal words in the illegal word database, and if the first character data and the illegal words are not matched, converting the first character data into second character data;
step 4, converting the second character data which continuously appear and exceed the preset frame number into third character data;
step 5, inputting a first bullet screen;
step 6, comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number is larger than the preset number, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage and the streaming media to the user terminal;
wherein, the system for processing the internet streaming media big data barrage comprises
The image identification module is used for identifying first character data appearing in each frame in the streaming media;
an illegal vocabulary database for storing illegal vocabularies;
the vocabulary filtering module is used for comparing the first character data with the illegal vocabulary in the illegal vocabulary database, and if the first character data are not matched with the illegal vocabulary in the illegal vocabulary database, the first character data are converted into second character data;
the screening module is used for converting the second character data which continuously appear and exceed the preset frame number into third character data;
the bullet screen acquisition module is used for inputting a first bullet screen;
the control module is used for comparing the number of the first barrage in the first unit time with the preset number in the first unit time, if the number of the first barrage in the first unit time is larger than the preset number in the first unit time, converting the first barrage associated with the third text data into a second barrage, and synthesizing the second barrage and the streaming media to send the second barrage and the streaming media to the user terminal;
the mode that the control module converts the first barrage associated with the third text data into the second barrage is as follows:
comparing the character number a of the characters which are the same as the first bullet screen data in each first bullet screen according to the characters of the third character data and the character number n;
converting a part of the first bullet screen, which is close to the input time and is closer to the time of a first frame in which the third character data continuously appears, into a second bullet screen according to the sequence of the number of characters a from large to small and the number of characters a is the same, wherein the number of the second bullet screens is equal to the preset number in the first unit time;
the mode of the image identification module for identifying the first character data appearing in each frame in the streaming media is as follows:
defining the position of each frame in the streaming media in which the first character data is identified to exceed a first preset threshold value in a second unit time as a caption area, and setting other positions of each frame as non-caption areas;
judging whether the first character data exceeds a second preset threshold value at a second time, if not, outputting the first character data, and if so, outputting a harmony score d according to the character number b and the position coefficient c of each first character data, which are the same as the illegal words in the illegal word database, according to the following formula:
wherein, when the first text data is in the caption area, c is 0.9, and when the first text data is in the non-caption area, c is 0.1;
outputting first character data of a second preset threshold value in a descending order;
the second unit time is 300 s.
2. The processing method of the internet streaming media big data bullet screen processing system according to claim 1, characterized in that: the illegal words comprise telephone numbers, addresses, abusive words, advertisement words and mars.
3. The processing method of the internet streaming media big data bullet screen processing system according to claim 2, characterized in that: the Mars language comprises messy code characters or illegal fonts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703106.8A CN113438544A (en) | 2019-07-17 | 2019-07-17 | Processing method of internet streaming media big data barrage |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703106.8A CN113438544A (en) | 2019-07-17 | 2019-07-17 | Processing method of internet streaming media big data barrage |
| CN201910647242.2A CN110351596B (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system and processing method |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910647242.2A Division CN110351596B (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system and processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113438544A true CN113438544A (en) | 2021-09-24 |
Family
ID=68176669
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910647242.2A Active CN110351596B (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system and processing method |
| CN202110703404.7A Withdrawn CN113395573A (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system |
| CN202110703106.8A Withdrawn CN113438544A (en) | 2019-07-17 | 2019-07-17 | Processing method of internet streaming media big data barrage |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910647242.2A Active CN110351596B (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system and processing method |
| CN202110703404.7A Withdrawn CN113395573A (en) | 2019-07-17 | 2019-07-17 | Internet streaming media big data bullet screen processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN110351596B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046651B (en) * | 2019-12-27 | 2023-04-28 | 淄博职业学院 | Chinese comment analysis method |
| CN111541949B (en) * | 2020-04-30 | 2021-09-14 | 上海哔哩哔哩科技有限公司 | Interaction method and system for barrage colored eggs |
| CN111586469B (en) * | 2020-05-12 | 2021-10-26 | 腾讯科技（深圳）有限公司 | Bullet screen display method and device and electronic equipment |
| CN111914546A (en) * | 2020-06-13 | 2020-11-10 | 王雪峰 | Artificial intelligence big data analysis processing system and method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105430512A (en) * | 2015-11-06 | 2016-03-23 | 腾讯科技（北京）有限公司 | Method and device for displaying information on video image |
| CN107707931B (en) * | 2016-08-08 | 2021-09-10 | 阿里巴巴集团控股有限公司 | Method and device for generating interpretation data according to video data, method and device for synthesizing data and electronic equipment |
| CN107147949B (en) * | 2017-05-05 | 2020-05-05 | 中广热点云科技有限公司 | Live broadcast time shifting playing progress control method and system |
| CN109819342B (en) * | 2017-11-22 | 2022-01-11 | 腾讯科技（深圳）有限公司 | Barrage content control method and device, computer equipment and storage medium |
| CN108495184B (en) * | 2018-02-06 | 2021-08-20 | 北京奇虎科技有限公司 | Method and device for adding barrage to video |
| CN109462730A (en) * | 2018-10-25 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Method and apparatus based on video acquisition panorama sketch |
| CN109361962B (en) * | 2018-11-26 | 2019-08-16 | 上海竑讯信息科技有限公司 | Internet stream media big data barrage information processing system and processing method |
| CN110019817A (en) * | 2018-12-04 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of detection method, device and the electronic equipment of text in video information |
| CN109840509B (en) * | 2019-02-15 | 2020-12-01 | 北京工业大学 | Multilayer cooperative identification method and device for bad anchor in network live video |
-
2019
- 2019-07-17 CN CN201910647242.2A patent/CN110351596B/en active Active
- 2019-07-17 CN CN202110703404.7A patent/CN113395573A/en not_active Withdrawn
- 2019-07-17 CN CN202110703106.8A patent/CN113438544A/en not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| CN110351596B (en) | 2021-07-27 |
| CN113395573A (en) | 2021-09-14 |
| CN110351596A (en) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110351596B (en) | Internet streaming media big data bullet screen processing system and processing method | |
| US9769545B2 (en) | System and method for automatically authoring interactive television content | |
| US8495003B2 (en) | System and method for scoring stream data | |
| KR101150748B1 (en) | System and method for generating a multimedia summary of multimedia streams | |
| US11080749B2 (en) | Synchronising advertisements | |
| CN110688526A (en) | Short video recommendation method and system based on key frame identification and audio textualization | |
| US20070074097A1 (en) | System and method for dynamic transrating based on content | |
| US7876381B2 (en) | Telop collecting apparatus and telop collecting method | |
| EP1246166A2 (en) | Speech recognition based captioning system | |
| JP2004526373A (en) | Parental control system for video programs based on multimedia content information | |
| JP4332700B2 (en) | Method and apparatus for segmenting and indexing television programs using multimedia cues | |
| US6271892B1 (en) | Method and apparatus for compressing a sequence of information-bearing frames having at least two media | |
| US6278493B1 (en) | Information processor, information processing method as well as broadcasting system and broadcasting method | |
| CN110096619A (en) | Video data analysis method, analysis platform, terminal and storage medium | |
| US20120310633A1 (en) | Filtering device and filtering method | |
| US11736744B2 (en) | Classifying segments of media content using closed captioning | |
| JP2007305054A (en) | Content receiver and content receiving program | |
| CN115393765A (en) | Video subtitle translation method, device and equipment | |
| CN114760523A (en) | Audio and video processing method, device, equipment and storage medium | |
| KR101522649B1 (en) | Apparatus and method for classifying watching grade of digital broadcasting by closed-cation analysis real time | |
| CN110012361B (en) | Big data bullet screen processing system and method | |
| Laverty et al. | Extraction of Teletext Subtitles from Broadcast Television for Archival and Analysis | |
| CN111711866A (en) | Television program playing method and device, electronic equipment and storage medium | |
| Ghosh et al. | Indexing of multilingual news telecast using audio-visual keywords |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210924 |