CN113660535B - System and method for monitoring content change of EPG column of IPTV service - Google Patents
System and method for monitoring content change of EPG column of IPTV service Download PDFInfo
- Publication number
- CN113660535B CN113660535B CN202110947262.9A CN202110947262A CN113660535B CN 113660535 B CN113660535 B CN 113660535B CN 202110947262 A CN202110947262 A CN 202110947262A CN 113660535 B CN113660535 B CN 113660535B
- Authority
- CN
- China
- Prior art keywords
- content
- early warning
- picture
- module
- poster
- 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
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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26283—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for associating distribution time parameters to content, e.g. to generate electronic program guide data
-
- 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
-
- 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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
-
- 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
- H04N21/4782—Web browsing, e.g. WebTV
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a system and a method for monitoring EPG column content change of IPTV service, which comprises a content classification capturing and identifying module, a capturing module for capturing all poster pictures under each classification, a PaddleOCR (optical character recognition) based picture identifying module and a zabbix based poster picture early warning module, and the specific implementation steps comprise: step 1, content classification capturing and identification; step 2, capturing content classification; step 3, identifying all poster pictures; and 4, early warning the poster picture. The invention can monitor the content classification change of the IPTV in the operators at three sides of mobile, unicom and telecom, the poster picture change under the content classification, and the like, can inform relevant operators of tracking in real time, and improves the operation accuracy and response speed; the requirement aims to abandon the original manual identification mode, greatly reduce the labor cost and enable the identification work to be intelligent, accurate and rapid under the background of big data.
Description
Technical Field
The invention relates to the technical field of network televisions, in particular to a system and a method for identifying and monitoring content changes of EPG (electronic program guide) columns of IPTV (Internet protocol television) services based on PaddleOCR (Picture optical character recognition).
Background
The IPTV, i.e. the interactive network television, is a brand-new technology that integrates various technologies such as internet, multimedia, communication, etc. into a whole by using a broadband cable television network, and provides various interactive services including digital television for home users. The user can enjoy the IPTV service at home. After the IPTV set-top box is turned on, a menu with combined pictures and texts appears on a television screen, which is an 'Electronic Program Guide' (EPG), also called a television Program Guide, and the EPG has the important function of sorting programs according to various rules, so that a terminal user can quickly find favorite channels and programs.
EPG columns are classified in various ways, poster pictures of the columns in the EPG frequently change along with contents, and an asynchronous interface is formed between a broadcasting control platform for managing and controlling EPG contents and the EPG; in order to ensure that the content of the poster image is consistent with that of the broadcasting control platform, an early warning prompt needs to be generated on the broadcasting control platform when the poster image needing to be displayed by the EPG changes, so that the operation and the editing can sense the information synchronization state between the EPG and the broadcasting control platform. But at present, a large amount of manual identification is needed, the efficiency is low, the accuracy is low, and the labor cost is high.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a method for identifying and monitoring the content change of an EPG column of the IPTV service based on the PaddleOCR picture.
The technical scheme adopted by the invention for solving the technical problem is as follows: the utility model provides a system for control IPTV business EPG column content changes, includes that content classification snatchs and identification module, all poster pictures under each classification snatch the module, based on paddleOCR picture identification module, based on zabbix poster picture early warning module, wherein:
the content classification capturing and identifying module comprises a content classification capturing module and a content classification identifying module, the content classification capturing module requests url through content classification and captures response html, webpage content is analyzed, all content classifications are obtained, and all obtained content is stored in a local file; the content classification identification module compares the obtained classified contents at different time points before and after the obtained classified contents are stored in the local file to obtain a comparison result, and prompts the content classification change of all poster picture capturing modules under each classification;
all poster picture grabbing modules in all classes send requests for content classification, a selenium plug-in is used for simulating a Google browser, the requests are sent, response html is grabbed, webpage content is analyzed, img labels are screened out, all poster picture paths src are obtained, and all obtained poster picture paths are downloaded to corresponding directories;
the poster picture identification module based on the PaddleOCR identifies and records the content names in the poster pictures into a local file through a PaddleOCR open-source deep learning tool, compares the new and old content names, and sends the comparison result to the poster picture early warning module based on zabbix for comparison;
the early warning module based on the zabbix poster picture monitors and early warns based on the zabbix and recognizes that the early warning information is, early warns.
A method for identifying and monitoring EPG column changes of IPTV service based on PaddleOCR pictures comprises the following specific implementation steps:
step 1, content classification capturing and identification: acquiring all content classification A, storing all the acquired content in a local file, then identifying, comparing the classification content A and the classification content B acquired at different time points before and after, acquiring a comparison result, prompting that the content classification is changed, and triggering the captured content classification;
step 2, captured content classification: capturing all content classifications through all poster picture capturing modules under all classifications, screening img labels, storing all obtained contents in a local file, obtaining all poster picture paths src, and downloading all obtained poster picture paths to a corresponding directory;
and 3, identifying all poster pictures: identifying content names in poster pictures by using a poster picture identification module based on PaddleOCR, recording the content names into a local file, comparing new and old contents to obtain a comparison result, and sending the comparison result to a poster picture early warning module based on zabbix for monitoring;
and 4, early warning the poster picture: monitoring the comparison result by adopting a zabbix-based poster picture early warning module, searching whether a zabbix trigger is matched with a warning condition, and when the trigger receives reminding information that poster content names generate differences and recognizes that the reminding information is early warning information, early warning can be carried out.
Specifically, in the step 1, a content classification capturing and identifying module is adopted to capture and identify, a selenium plug-in is used to simulate a google browser through a content classification request url, a request is sent, a response html is captured, and webpage content is analyzed.
Specifically, in step 3, the poster image identification module based on PaddleOCR acquires image information by means of a PaddleOCR learning model, identifies the content name in the poster image, denoises the content name, and removes invalid image information, so that the content name is more accurate.
Specifically, the method for identifying the content name in the poster picture based on the PaddleOCR poster picture identification module in the step 3 is as follows:
3.5.1 executing python PaddleOCR/tools/prefer/predict _ system. Py XXX command to obtain script execution result;
3.5.2 serializing the script execution result, and transcoding the script execution result into a character string in a UTF-8 encoding format;
3.5.3 obtaining name information, namely original picture content name information, according to the character string;
3.5.4 denoises the content name, firstly initializes a file with invalid characters, traverses the file, checks whether the name information contains the invalid characters, and deletes the invalid characters if the name information contains the invalid characters, so that the content is more accurate;
3.5.5 if the returned name information is an empty string, the PaddleOCR learning model cannot identify the picture, firstly resolving an MD5 value from the picture, and storing the picture into a temporary file in a form that a path is a key and the MD5 value is a value;
the method aims to identify whether the content name in the picture is changed or not by comparing the MD5 value during secondary scanning, prompt if the content name is changed, and send an instruction to the zabbix-based poster picture early warning module for early warning.
Specifically, the method for constructing the zabbix poster picture-based early warning module in the step 4 comprises the following steps:
4.1 definition host
Newly building a host, and configuring information such as a host name, a visible name, a group and the like;
4.2 defining monitoring items
Newly building a monitoring item and configuring a name;
4.3 define flip-flop
Newly building a trigger, configuring a name, setting an early warning expression, and sending early warning once information is received and matched and when the information is matched;
4.4 sending instructions to zabbix for monitoring and early warning.
The invention has the following beneficial effects: the invention can monitor the content classification change of the IPTV in the operators at three sides of mobile, unicom and telecom, the poster picture change under the content classification, and the like, can inform relevant operators of tracking in real time, and improves the operation accuracy and response speed; the demand aims to abandon the original manual identification mode, greatly reduce the labor cost and ensure that the identification work is intelligent, accurate and rapid under the background of big data.
Drawings
FIG. 1 is a diagram of a module call relationship of the present invention.
FIG. 2 is a flow chart of the present invention.
FIG. 3 is a diagram illustrating a host definition according to the present invention.
FIG. 4 is a diagram illustrating a definition of a monitoring item according to the present invention.
FIG. 5 is a diagram of a definition flip-flop according to the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings.
According to the system for identifying and monitoring the EPG column change of the IPTV service based on the PaddleOCR picture shown in figure 1, the early warning module is adopted for early warning, the early warning module is an EPG content poster picture early warning module, and the whole module is divided into: the system comprises a content classification grabbing and identifying module, all poster picture grabbing modules under various classifications, a PaddleOCR (optical character recognition) based picture recognition module and a zabbix based poster picture early warning module, wherein a development language selects python, a calling relation diagram of which is shown in figure 1, wherein:
the content classification grabbing and identifying module comprises a content classification grabbing module and a content identification module, wherein the content classification grabbing module sends a request and grabs a response html by using a selenium plug-in simulated Google browser through a content classification request url, the request is sent and a response html is captured, webpage content is analyzed, all content types are obtained, all obtained content is stored in a local gamestab.txt file, the identifying module obtains the content types at different time points before and after the gamestab.txt file for comparison, the identifying module aims at comparing new and old content types with lists to obtain a comparison result, and the content classification grabbing module prompts that the content types are changed;
all poster picture grabbing modules in each category send requests, namely a selenium plug-in is used for simulating a Google browser, the requests are sent, response html is grabbed, webpage content is analyzed, img labels are screened out, all poster picture paths src are obtained, and all obtained poster picture paths are downloaded to corresponding directories;
the poster picture identification module based on the PaddleOCR identifies the content name in the poster picture through a PaddleOCR open-source deep learning tool, records the content name in the poster picture to the games _ new.txt, compares the new content with the old content, and sends the comparison result to the poster picture early warning module based on zabbix for comparison;
the poster picture early warning module based on zabbix predefines a host, redefines monitoring items and finally defines a trigger based on zabbix monitoring and early warning, and early warning can be performed when the trigger receives game reminding information and recognizes that the game reminding information is early warning information.
As shown in fig. 2, 3, 4, and 5, a method for monitoring EPG column change of IPTV service based on PaddleOCR picture recognition specifically includes:
step 1, content classification capture and identification
Adopting a content classification capture and identification module to capture and identify, sending a request and capturing a response html through a content classification request url by using a selenium plug-in google simulating browser, analyzing webpage content, obtaining all content types A, storing all obtained content in a local gamestab.txt file, then identifying, reading a file B in the local gamestab.txt, comparing the content types A and B obtained at different time points before and after the comparison, recording the result, judging whether all content types are traversed, performing content classification identification aiming at classifying new and old content, comparing lists, obtaining a comparison result, prompting that the content classification is changed, triggering captured content classification, and obtaining the difference between two time points before and after the time point 1 obtains the classified content A and stores gamesTab _ txt, and recording the time point 2 obtains the classified content and stores the classified content after gamesTab _ txt;
step 2, captured content classification
After the identification position is changed in the step 1, triggering all poster picture grabbing modules under each classification to send a content classification request url, using a selenium plug-in simulated google browser to send a request and grab a response html, analyzing webpage content, acquiring all content classifications, screening img tags, storing all acquired content in a local games tab.
Step 3, all poster pictures are identified
Identifying content names in poster pictures by using a poster picture identification module based on PaddleOCR through a PaddleOCR open-source deep learning tool, recording the content names into local games _ new.txt, comparing new content with old content to obtain a comparison result, if game names in the poster pictures are compared as shown in FIG. 2, obtaining whether new or reduced games exist, and sending the comparison result to a poster picture early warning module based on zabbix for monitoring;
the construction steps of the PaddleOCR poster picture recognition module are as follows:
3.1 downloading Source codes
Because the tool is open source, the source code needs to be obtained first, and the source code address git clone https:// github.com/PaddlePaddle/PaddleOCR;
3.2 installation middleware
The source code simultaneously needs middleware, and the list of the middleware is as follows, shapely, imgauge, pyclipper, lmdb, opencv-python = =4.2.0.32, tqdm, numpy, visualdlpython-levenshtein;
3.3 obtaining OCR models
https// gite.com/paddlepaddler #/paddlepaddlewheel/PaddleOCR/blob/release/2.0/doc/doc _ ch/models _ list.md, and downloading three general inference models;
3.4 modifying Source code
Modify PaddleOCR/tools/info/predict _ system. Py 161 as under logo. Info ("name: { }, {: 3f }". Format (text, score)) print identification modification;
3.5 with the help of paddleOCR learning model, obtain picture information, discern the content name in the poster picture to denoising the content name, remove invalid picture information, make the content name more accurate, its implementation method is:
3.5.1 executing python PaddleOCR/tools/prefer/predict _ system. Py XXX command to obtain script execution result;
3.5.2 serializing the script execution result and transcoding the script execution result into a character string in a UTF-8 encoding format;
3.5.3 obtaining name information, namely original picture content name information, according to the character string;
3.5.4 denoises the content name, firstly initializes a file with invalid characters, traverses the file, checks whether the name information contains the invalid characters, and deletes the invalid characters if the name information contains the invalid characters, so that the content is more accurate;
3.5.5 if the returned name information is an empty string, the PaddleOCR learning model cannot identify the picture, firstly resolving an MD5 value from the picture, and storing the picture into a temporary file in a form that a path is a key and the MD5 value is a value;
the method aims at comparing MD5 values to identify whether the game name in the picture changes or not when secondary scanning is carried out, prompting if the game name changes, and sending an instruction to a zabbix-based poster picture early warning module for early warning;
step 4, early warning of poster picture
Monitoring a comparison result by adopting a poster picture early warning module based on zabbix, searching whether a zabbix trigger is matched with a warning condition or not, monitoring the poster picture of the intelligent operation and maintenance management platform based on the zabbix monitoring and early warning, wherein the design idea is that a host is defined firstly, monitoring items are defined, a trigger is defined at last, when the trigger receives reminding information of poster content difference and recognizes that the warning information is the warning information, early warning can be performed, and the specific method comprises the following steps:
4.1 definition host
Newly building a host, and configuring information such as a host name, a visible name, a group and the like;
4.2 defining monitoring items
Newly building a monitoring item, configuring a name, wherein the type is a zabbix collector, and the key value is a game;
4.3 define flip-flop
Newly building a trigger, configuring a name { ITEM.VALUE }, and sending an early warning when information is received and matched, wherein an early warning expression { dianxinyx: game.str (game list early warning) } = 1;
4.4 sending instructions to zabbix for monitoring and early warning
os.system ("zabbix _ sender-z" + zabbixIP + "-s ' dianxinyx ' -k game-o '" + result + ") zabbixIP is the zabbix server address.
The present invention is not limited to the above embodiments, and any structural changes made under the teaching of the present invention shall fall within the protection scope of the present invention, which is similar or similar to the technical solutions of the present invention.
The techniques, shapes, and configurations not described in detail in the present invention are all known techniques.
Claims (4)
1. A system for monitoring content change of EPG column of IPTV service is characterized in that: comprises a grabbing module, an identification module and an early warning module, wherein,
the capturing module is used for sending a URL request, acquiring webpage HTML format data under all content classifications, storing the webpage HTML format data in a local file, screening HTML format data under all the captured content classifications, screening img tags, storing all the img tags in the local file, acquiring all poster picture paths src, and downloading the poster picture paths src to a corresponding directory;
the identification module is used for comparing the acquired content types at different time points before and after the acquired content types are stored in the local file, acquiring a comparison result and prompting that the content types are changed to the capture module;
the identification module acquires picture information by means of a PaddleOCR learning model, identifies content names in poster pictures, removes noise of the content names, removes invalid picture information to enable the content names to be more accurate, identifies the content names in the poster pictures, records the content names in a local file, compares the content names originally stored in the local file with the content names just identified, and sends comparison results to the early warning module;
the early warning module is based on zabbix monitoring and early warning, and the monitoring and early warning method comprises the steps of defining a host, a monitoring item, defining a zabbix trigger, setting an early warning expression, matching once a comparison result sent by the identification module is received, searching whether the early warning condition is matched or not by the zabbix trigger, and giving early warning if the early warning condition is matched.
2. A method for monitoring content change of EPG column of IPTV service is characterized in that: the method comprises the following steps:
step 1, content classification capture and identification: the method comprises the steps that a grabbing module sends a URL request to obtain webpage HTML format data under all content classification, then an identification module identifies, compares the types of the obtained contents at different time points before and after the obtained contents are stored in a local file to obtain a comparison result, and when the types of the obtained contents change, prompts the grabbing module that the types of the contents change and triggers the grabbing module;
step 2, capturing all poster pictures under the content classification category: the method comprises the steps that a grabbing module sends a URL request, webpage HTML format data under all content classifications are obtained, the grabbed HTML format data under all content classifications are screened, img tags are screened out, all the img tags are stored in a local file, all poster picture paths src are obtained, and the paths src are downloaded to a corresponding directory;
and 3, identifying all poster pictures: identifying the content name in the poster picture by adopting an identification module, recording the content name into a local file, comparing the content name obtained by the identification with the content name obtained by the identification in the last storage, and sending a result of change to an early warning module;
and 4, early warning the poster picture: the method comprises the steps of defining a host, monitoring items and a zabbix trigger, setting an early warning expression, matching once a comparison result sent by an identification module is received, searching whether an early warning condition is matched or not by the zabbix trigger, and giving an early warning if the early warning condition is matched.
3. A method for monitoring content changes of EPG columns of IPTV services according to claim 2, characterized in that: in the step 3, the recognition module acquires the picture information by means of the PaddleOCR learning model, recognizes the content name in the poster picture, denoises the content name, and removes invalid picture information, so that the content name is more accurate.
4. A method for monitoring content changes of EPG columns of IPTV services according to claim 3, wherein: the method for identifying the content name in the poster picture by the identification module in the step 3 comprises the following steps:
3.5.1 executing python first
A PaddleOCR/tools/invoke/predict _ system. Py XXX command, and acquiring a script execution result;
3.5.2 serializing the script execution result, and transcoding the script execution result into a character string in a UTF-8 encoding format;
3.5.3 obtaining original picture content name information according to the character string;
3.5.4 denoises the content name, firstly initializes a file with invalid characters, traverses the file, checks whether the content name information contains the invalid characters, and deletes the invalid characters if the content name information contains the invalid characters, so that the content is more accurate;
3.5.5 if the returned content name information is an empty string, the PaddleOCR learning model cannot recognize the picture, and we analyze the picture to obtain an MD5 value, and store the picture in a temporary file in a form that a path is a key and the MD5 value is a value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947262.9A CN113660535B (en) | 2021-08-18 | 2021-08-18 | System and method for monitoring content change of EPG column of IPTV service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947262.9A CN113660535B (en) | 2021-08-18 | 2021-08-18 | System and method for monitoring content change of EPG column of IPTV service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113660535A CN113660535A (en) | 2021-11-16 |
| CN113660535B true CN113660535B (en) | 2023-03-24 |
Family
ID=78480765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110947262.9A Active CN113660535B (en) | 2021-08-18 | 2021-08-18 | System and method for monitoring content change of EPG column of IPTV service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113660535B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080273114A1 (en) * | 2007-05-04 | 2008-11-06 | Hardacker Robert L | STB channel reader |
| CN104978270A (en) * | 2015-07-03 | 2015-10-14 | 上海触乐信息科技有限公司 | Automatic software testing method and apparatus |
| US10448107B2 (en) * | 2016-11-11 | 2019-10-15 | Lg Electronics Inc. | Display device |
| CN108446227A (en) * | 2018-03-12 | 2018-08-24 | 广东睿江云计算股份有限公司 | A kind of virtual machine browser compatibility test method based on selenium |
| CN108595583B (en) * | 2018-04-18 | 2022-12-02 | 平安科技（深圳）有限公司 | Dynamic graph page data crawling method, device, terminal and storage medium |
| CN111507344A (en) * | 2019-01-30 | 2020-08-07 | 北京奇虎科技有限公司 | Method and device for recognizing characters from image |
| CN109901968A (en) * | 2019-01-31 | 2019-06-18 | 阿里巴巴集团控股有限公司 | A kind of automation page data method of calibration and device |
| CN112214397B (en) * | 2020-09-09 | 2022-05-20 | 腾讯科技（深圳）有限公司 | User interface test method and device, computer equipment and storage medium |
| CN112882947B (en) * | 2021-03-15 | 2024-06-11 | 深圳市腾讯信息技术有限公司 | Interface testing method, device, equipment and storage medium |
-
2021
- 2021-08-18 CN CN202110947262.9A patent/CN113660535B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113660535A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008378B (en) | Corpus collection method, device, equipment and storage medium based on artificial intelligence | |
| CN107301245B (en) | Power information video search system | |
| CN106407393A (en) | An information processing method and device for intelligent apparatuses | |
| WO2022001600A1 (en) | Information analysis method, apparatus, and device, and storage medium | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| CN112149642A (en) | Text image recognition method and device | |
| CN113038153A (en) | Financial live broadcast violation detection method, device and equipment and readable storage medium | |
| CN104142955A (en) | Method and terminal for recommending learning courses | |
| WO2024193538A1 (en) | Video data processing method and apparatus, device, and readable storage medium | |
| CN114422271B (en) | Data processing method, device, equipment and readable storage medium | |
| CN106484913A (en) | Method and server that a kind of Target Photo determines | |
| CN111597361B (en) | Multimedia data processing method, device, storage medium and equipment | |
| CN113660535B (en) | System and method for monitoring content change of EPG column of IPTV service | |
| CN117493606A (en) | Video retrieval method, device, system, electronic equipment and storage medium | |
| CN112634896A (en) | Operation method of application program on intelligent terminal and intelligent terminal | |
| CN102902737B (en) | A kind of network image is independently collected and screening technique | |
| CN112165626B (en) | Image processing method, resource acquisition method, related equipment and medium | |
| CN114443904A (en) | Video query method, video query device, computer equipment and computer readable storage medium | |
| CN107368532A (en) | A kind of user agent's field information processing method and system | |
| CN111859118A (en) | Intelligent information recommendation method and device based on document directory | |
| CN118429658B (en) | Information extraction method and information extraction model training method | |
| CN116483946B (en) | Data processing method, device, equipment and computer program product | |
| CN116594658B (en) | Version upgrading method and device for metadata, electronic equipment and medium | |
| CN110516143B (en) | Business data extraction method and device based on browser | |
| CN114612822A (en) | Intelligent supervision method for mobile audio-visual equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |