CN111444685B - News production system and method based on big data and artificial intelligence - Google Patents
News production system and method based on big data and artificial intelligence Download PDFInfo
- Publication number
- CN111444685B CN111444685B CN202010224419.0A CN202010224419A CN111444685B CN 111444685 B CN111444685 B CN 111444685B CN 202010224419 A CN202010224419 A CN 202010224419A CN 111444685 B CN111444685 B CN 111444685B
- Authority
- CN
- China
- Prior art keywords
- data
- news
- interview
- manuscripts
- module
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- 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
- G06F16/35—Clustering; Classification
Abstract
The application provides a news production system and a method based on big data and artificial intelligence, wherein an interview module in the system is used for collecting news clues, scheduling a reporter according to the news clues, receiving interview manuscripts returned by the reporter, and uploading the interview manuscripts to a data center module; the data center module is used for storing the interview manuscripts; the intelligent editing module is used for acquiring interview manuscripts in the data center module and editing the interview manuscripts so as to acquire news manuscripts; the manuscript distribution module is used for distributing the news manuscripts; the intelligent tracking module is used for tracking the distributed news manuscripts so as to obtain tracking data. The system effectively improves news production efficiency and improves news content quality.
Description
Technical Field
The application belongs to the technical field of news media, and particularly relates to a news production system and method based on big data and artificial intelligence.
Background
The existing news manuscript is generally produced by the following steps: first, gather cues: including receiving news cues through news hotlines, providing cues through communicants, or collecting cues through reporters, editing moments, and focusing on network hotspots. Secondly, manually analyzing the collected report questions of the clues, sending the report questions to the related leaders, and after the leaders review the report questions, sending the reporters to interview site interviews. The reporter then transmits the interview content back to the editor, who then processes the interview content. The editing processing steps comprise: the picture is manually cut and checked, the video is dubbed, the caption is matched, the cover diagram is selected, the interview recording is repeatedly listened and written, and the text content is processed and arranged to form a news manuscript. Finally, the news manuscript is transmitted to the proofreading, the proofreading carries out text correction on the news manuscript content, and after the proofreading is correct, the news manuscript is transmitted to paper media, new media and the like for publishing. However, the existing whole production process is time-consuming and labor-consuming and is easy to make mistakes.
Disclosure of Invention
Aiming at the defects in the prior art, the news production system and method based on big data and artificial intelligence provided by the application effectively improve the news production efficiency and the news content quality.
In a first aspect, a news production system based on big data and artificial intelligence, comprising:
interview module: the system comprises a data center module, a news thread module, a report module and a report module, wherein the report module is used for collecting news threads, scheduling a reporter according to the news threads, receiving interview manuscripts returned by the reporter and uploading the interview manuscripts to the data center module;
and a data center module: the interview manuscripts are used for storing the interview manuscripts;
and an intelligent editing module: the method comprises the steps of acquiring interview manuscripts in a data center module, and editing the interview manuscripts to obtain news manuscripts;
manuscript distribution module: for distributing the news manuscripts;
and the intelligent tracking module: the method is used for tracking the distributed news manuscripts to obtain tracking data.
Preferably, the interview module specifically includes:
news clue module: for collecting news cues;
and a command scheduling module: for scheduling a reporter according to the news feed;
and the intelligent acquisition and writing module is as follows: and the interview manuscript is used for receiving the interview manuscripts returned by the reporter and uploading the interview manuscripts to the data center module.
Preferably, the news clue module is specifically configured to:
acquiring big data from a preset data channel in real time, performing data mining, data cleaning and data calculation on the big data to acquire the news clues, and classifying the news clues;
the news feed includes a combination of one or more of the following: type, time, geographic location, persona relationship, event, and event progress profile.
Preferably, the commanding and dispatching module is specifically configured to:
acquiring current position information of all the journalists in the journalist database in real time, and updating the position information of the journalists in the journalist database according to the current position information of the journalists; wherein the reporter information recorded in the reporter database comprises a combination of one or more of the following factors: name, contact, interview, and location information;
when a news clue from the news clue module is received, scheduling factors in the news clue are acquired, the scheduling factors of the news clue are matched with the reporter database, a reporter with factors consistent with the scheduling factors of the news clue is acquired, and an interview task is generated and distributed to the reporter.
Preferably, the intelligent writing module is specifically configured to:
the reporter looks up the interview task through the terminal equipment; receiving interview data uploaded by a reporter through terminal equipment, analyzing the interview data to obtain interview manuscripts, and uploading the interview manuscripts to a data center module;
the interview data includes voice data, video data, image data, and/or text data.
Preferably, the intelligent editing module is specifically configured to:
acquiring voice data of interview manuscripts in a data center module, and converting the voice data into text data to obtain first finished text materials;
acquiring video data of interview manuscripts in a data center module, and performing video classification, video character recognition, video voice recognition, video fine granularity recognition, video image character recognition, video tag extraction, video dubbing, video subtitle matching, intelligent cutting and video cover selection on the video data to obtain a finished video material;
acquiring image data of interview manuscripts in a data center module, and performing image classification, image searching, character recognition, scene recognition, label extraction and image effect enhancement on the image data to obtain a finished product image material;
acquiring text data of interview manuscripts in a data center module, and performing text correction, emotion tendency analysis, dialogue emotion recognition, article tag, article classification and news abstract processing on the text data to obtain second finished product text materials;
the news manuscript is obtained after the first finished product text material, the finished product video material, the finished product image material and the second finished product text material are comprehensively edited and checked;
and sending the first finished text material, the finished video material, the finished image material, the second finished text material and the news manuscript to a data center module for storage.
Preferably, the contribution distribution module is specifically configured to:
distributing the news manuscripts in multiple platforms; the platform includes one or more of the following combinations: paper media print shops, PC terminals and mobile terminals.
Preferably, the intelligent tracking module is specifically configured to:
carrying out data tracking and propagation path tracking on the distributed news manuscripts to obtain tracking data;
and sending the tracking data to a data center module for storage.
Preferably, the system further comprises:
and an intelligent analysis module: the method is used for analyzing the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
In a second aspect, a news production method based on big data and artificial intelligence includes the steps of:
the interview module collects news clues, dispatches the journalist according to the news clues, receives interview manuscripts returned by the journalist, and uploads the interview manuscripts to the data center module;
the data center module stores the interview manuscript;
the intelligent editing module acquires interview manuscripts in the data center module, and edits the interview manuscripts to acquire news manuscripts;
the manuscript distribution module distributes the news manuscripts;
the intelligent tracking module tracks the distributed news manuscripts to obtain tracking data;
and the intelligent analysis module analyzes the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
According to the technical scheme, the news production system and the news production method based on big data and artificial intelligence can automatically generate news manuscripts to form a news ecological closed loop, so that news production efficiency is effectively improved, and news content quality is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a block diagram of a system according to a first embodiment of the present application.
Fig. 2 is a flowchart of a method according to a third embodiment of the present application.
Detailed Description
Embodiments of the technical scheme of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and thus are merely examples, and are not intended to limit the scope of the present application. It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Embodiment one:
a news production system based on big data and artificial intelligence, see fig. 1, comprising:
interview module: the system comprises a data center module, a news thread module, a report module and a report module, wherein the report module is used for collecting news threads, scheduling a reporter according to the news threads, receiving interview manuscripts returned by the reporter and uploading the interview manuscripts to the data center module;
in particular, the interview module may collect news feeds from the internet or other sources (e.g., newspapers, broadcasters, etc.). And after receiving the news clues, the interview module schedules the reporter according to the news clues, schedules the proper reporter to the news clue place for interview, and collects interview manuscripts of the reporter after the reporter arrives at the news clue place for interview.
And a data center module: the interview manuscripts are used for storing the interview manuscripts;
specifically, the data center module mainly stores data, and may also store news threads, edited news articles, tracking data, analysis data, and the like.
And an intelligent editing module: the method comprises the steps of acquiring interview manuscripts in a data center module, and editing the interview manuscripts to obtain news manuscripts;
specifically, the intelligent editing module automatically edits and collates interview manuscripts of a reporter to obtain formal news manuscripts capable of being published.
Manuscript distribution module: for distributing the news manuscripts;
specifically, the contribution distribution module automatically distributes news contributions to each media platform for publishing.
And the intelligent tracking module: the method is used for tracking the distributed news manuscripts to obtain tracking data.
Specifically, the intelligent tracking module is used for tracking the distributed news manuscripts, such as tracking the access amount, forwarding path, comments and the like of the news manuscripts, so that the automatic tracking of the published news manuscripts is realized.
And an intelligent analysis module: the method is used for analyzing the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
Specifically, the intelligent analysis module is used for analyzing the tracking data to comprehensively obtain the publishing condition, the browsing condition and the like of the news manuscript. When a user accesses the news manuscript, the region where the user is located, the terminal used, the comment and the propagation path are recorded. The propagation path includes forwarding the news article to the other or to another person.
The method can automatically generate news manuscripts to form a news ecological closed loop, effectively improve news production efficiency and improve news content quality.
Embodiment two:
the second embodiment is based on the first embodiment, and further description is given of each module.
1. The interview module comprises a news clue module, a command scheduling module and an intelligent interview module.
(1) And a news clue module.
Acquiring big data from a preset data channel in real time, performing data mining, data cleaning and data calculation on the big data to acquire the news clues, and classifying the news clues;
the news feed includes a combination of one or more of the following: type, time, geographic location, persona relationship, event, and event progress profile.
Specifically, the data mining steps mainly include defining questions, building a data mining library, analyzing data, preparing data, building a model, evaluating the model, and implementing. Defining a problem, namely defining a mining purpose. And carrying out data collection, data description, selection, data quality evaluation, data cleaning, data merging and other steps according to the mining purpose, and loading a data mining library. Analyzing the data to find the data field that has the greatest effect on the predicted output. Preparing the data includes selecting variables, selecting records, creating new variables and converting variables. The model is built by using a part of data, and then the obtained model is tested and verified by using the rest data. After the model is built, the model must be evaluated. Finally, the model is established and verified for implementation.
The data cleaning mainly screens and cleans repeated and redundant data, supplements and completes the missing data, corrects or deletes the wrong data, and finally finishes the data into data which can be further processed and used. Data computation is the process of processing data in a relationship established by a pattern.
The news clue module is used for processing big data (such as data acquired in real time by the Internet or keyword information acquired by other channels) acquired through various data channels and then finishing the big data into valuable news clues. News types include messages, communications, reporting literature, and the like.
(2) And commanding the scheduling module.
Acquiring current position information of all the journalists in the journalist database in real time, and updating the position information of the journalists in the journalist database according to the current position information of the journalists; wherein the reporter information recorded in the reporter database comprises a combination of one or more of the following factors: name, contact, interview, and location information;
when a news clue from the news clue module is received, scheduling factors in the news clue are acquired, the scheduling factors of the news clue are matched with the reporter database, a reporter with factors consistent with the scheduling factors of the news clue is acquired, and an interview task is generated and distributed to the reporter.
Specifically, the commanding and dispatching module is used for dispatching a proper reporter to the news cue generating place for interview according to the news cue of the news cue module. Factors for scheduling include interviewing tampering and location information. For example, if the news thread occurs at site A, the news thread may be assigned to a reporter near site A for interview based on the location information of the reporter. Also, for example, if the news feed is technical news, a reporter may be scheduled for interviewing that is good at technical news interviews.
The command dispatching module updates the current position information of the reporter in the reporter database in real time, and ensures that the current position information of each reporter can be accurately dispatched when dispatching is carried out. The scheduling factors in the news cues can be set by the user according to the situation.
(3) And an intelligent acquisition and writing module.
The reporter looks up the interview task through the terminal equipment; receiving interview data uploaded by a reporter through terminal equipment, analyzing the interview data to obtain interview manuscripts, and uploading the interview manuscripts to a data center module;
the interview data includes voice data, video data, image data, and/or text data.
Specifically, the intelligent interview module is generally used by a reporter, the intelligent interview module is installed on the terminal device, and the reporter uploads interview data, such as audio, video, pictures or characters recorded by the reporter, through the terminal device after interview is completed. Analyzing the interview data includes error correction, duplicate checking, and the like.
2. And an intelligent editing module.
Acquiring voice data of interview manuscripts in a data center module, and converting the voice data into text data to obtain first finished text materials;
specifically, when the received interview content is voice, the intelligent editing module converts a voice signal into text and then uploads the text to the data center module for storage.
Acquiring video data of interview manuscripts in a data center module, and performing video classification, video character recognition, video voice recognition, video fine granularity recognition, video image character recognition, video tag extraction, video dubbing, video subtitle matching, intelligent cutting and video cover selection on the video data to obtain a finished video material;
specifically, when the received interview content is video, the intelligent editing module classifies the video, character recognition, voice recognition, fine granularity recognition, image and text recognition, label extraction, dubbing, subtitle matching, intelligent cutting, video cover selection and the like. For example: videos are classified into science and technology, life, news, etc. Character recognition methods may include recognition of faces and actions (walking, waving hands, jogging, boxing, clapping hands, running, etc.). For example, three general methods of background subtraction, inter-frame difference and optical flow can be used. The method recognizes the voice in the video and automatically extracts the person and the voice in the video. Video fine-grained identification is basically a classification task that uses both global information and local information. For fine-grained identification of flowers, for example, global information is the entire image taken by the user, while local information is the flowers or important parts of the flowers in the image. The intelligent editing module automatically dubs the caption to the video and intercepts a frame of image with the most representativeness as a video cover. And finally, editing the finished video material, and uploading the finished video material to a data center module for storage.
Acquiring image data of interview manuscripts in a data center module, and performing image classification, image searching, character recognition, scene recognition, label extraction and image effect enhancement on the image data to obtain a finished product image material;
specifically, when the received interview content is an image, the intelligent editing module classifies the image, searches, character recognition, scene recognition, label extraction and effect enhancement, forms a finished image material, and uploads the finished image material to the data center module for storage. And (5) extracting key features in the image by image searching to finish searching. The intelligent editing module is also used for identifying people and scenes (including background images and the like) in the images and separating the people from the scenes. Image effect enhancement is used to enhance certain features in an image according to editing requirements.
Acquiring text data of interview manuscripts in a data center module, and performing text correction, emotion tendency analysis, dialogue emotion recognition, article tag, article classification and news abstract processing on the text data to obtain second finished product text materials;
specifically, when the received interview content is text, the intelligent editing module performs error correction, emotion tendency analysis, dialogue emotion recognition, article labeling, classification and news abstract processing on the text to obtain second finished product text materials, and uploads the second finished product text materials to the data center module for storage. Error correction is to correct grammatical errors, mispronounced words, etc. in text data. Emotional tendency analysis and dialogue emotion recognition are used to obtain the emotion of the interviewed person during interview. The news digest process is used to automatically summarize the text data to obtain a digest of the text data.
The news manuscript is obtained after the first finished product text material, the finished product video material, the finished product image material and the second finished product text material are comprehensively edited and checked;
specifically, the intelligent editing module performs comprehensive editing and auditing on the first finished text material, the finished video material, the finished image material and the second finished text material of the same interview content to obtain a news manuscript which can be published.
And sending the first finished text material, the finished video material, the finished image material, the second finished text material and the news manuscript to a data center module for storage.
3. And the manuscript distribution module.
Distributing the news manuscripts in multiple platforms; the platform includes one or more of the following combinations: paper media print shops, PC terminals and mobile terminals (including APP applications, cell phone WAP terminals and applets, for example).
Specifically, the contribution distribution module can distribute news contributions to multiple platforms, and the approach of publishing the news contributions is expanded. The news publisher can select a published platform according to own requirements.
4. And an intelligent tracking module.
Carrying out data tracking and propagation path tracking on the distributed news manuscripts to obtain tracking data;
and sending the tracking data to a data center module for storage.
Specifically, the intelligent tracking module performs data tracking and propagation path tracking on the distributed news manuscripts, so that tracing of the news manuscripts can be realized, and the sources of the news manuscripts can be queried. For example, when network violence is detected, the source of the network violence can be queried according to the tracking data, and timely stopping or correcting can be performed.
For a brief description of the system provided by the embodiments of the present application, reference may be made to the corresponding content in the foregoing system embodiments where the description of the embodiments is not mentioned.
Embodiment III:
a news production method based on big data and artificial intelligence, see fig. 2, comprising the steps of:
s1: the interview module collects news clues, dispatches the journalist according to the news clues, receives interview manuscripts returned by the journalist, and uploads the interview manuscripts to the data center module;
s2: the data center module stores the interview manuscript;
s3: the intelligent editing module acquires interview manuscripts in the data center module, and edits the interview manuscripts to acquire news manuscripts;
s4: the manuscript distribution module distributes the news manuscripts;
s5: the intelligent tracking module tracks the distributed news manuscripts to obtain tracking data;
s6: and the intelligent analysis module analyzes the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
The method can automatically generate news manuscripts to form a news ecological closed loop, effectively improve news production efficiency and improve news content quality.
For a brief description of the method provided by the embodiments of the present application, reference may be made to the corresponding content in the foregoing system embodiments where the description of the embodiments is not mentioned.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application, and are intended to be included within the scope of the appended claims and description.
Claims (8)
1. A news production system based on big data and artificial intelligence, comprising:
interview module: the system comprises a data center module, a news thread module, a report module and a report module, wherein the report module is used for collecting news threads, scheduling a reporter according to the news threads, receiving interview manuscripts returned by the reporter and uploading the interview manuscripts to the data center module;
and a data center module: the interview manuscripts are used for storing the interview manuscripts;
and an intelligent editing module: the method comprises the steps of acquiring interview manuscripts in a data center module, and editing the interview manuscripts to obtain news manuscripts;
manuscript distribution module: for distributing the news manuscripts;
and the intelligent tracking module: the news manuscript tracking method comprises the steps of tracking distributed news manuscripts to obtain tracking data;
the intelligent stoping module is specifically used for:
the reporter looks up the interview task through the terminal equipment; receiving interview data uploaded by a reporter through terminal equipment, analyzing the interview data to obtain interview manuscripts, and uploading the interview manuscripts to a data center module;
the interview data comprises voice data, video data, image data and text data;
the intelligent editing module is specifically used for:
acquiring voice data of interview manuscripts in a data center module, and converting the voice data into text data to obtain first finished text materials;
acquiring video data of interview manuscripts in a data center module, and performing video classification, video character recognition, video voice recognition, video fine granularity recognition, video image character recognition, video tag extraction, video dubbing, video subtitle matching, intelligent cutting and video cover selection on the video data to obtain a finished video material;
acquiring image data of interview manuscripts in a data center module, and performing image classification, image searching, character recognition, scene recognition, label extraction and image effect enhancement on the image data to obtain a finished product image material;
acquiring text data of interview manuscripts in a data center module, and performing text correction, emotion tendency analysis, dialogue emotion recognition, article tag, article classification and news abstract processing on the text data to obtain second finished product text materials;
the news manuscript is obtained after the first finished product text material, the finished product video material, the finished product image material and the second finished product text material are comprehensively edited and checked;
and sending the first finished text material, the finished video material, the finished image material, the second finished text material and the news manuscript to a data center module for storage.
2. The news production system based on big data and artificial intelligence according to claim 1, characterized in that the interview module comprises in particular:
news clue module: for collecting news cues;
and a command scheduling module: for scheduling a reporter according to the news feed;
and the intelligent acquisition and writing module is as follows: and the interview manuscript is used for receiving the interview manuscripts returned by the reporter and uploading the interview manuscripts to the data center module.
3. The news production system based on big data and artificial intelligence according to claim 2, wherein the news cue module is specifically configured to:
acquiring big data from a preset data channel in real time, performing data mining, data cleaning and data calculation on the big data to acquire the news clues, and classifying the news clues;
the news feed includes a combination of one or more of the following: type, time, geographic location, persona relationship, event, and event progress profile.
4. The news production system based on big data and artificial intelligence according to claim 2, wherein the command scheduling module is specifically configured to:
acquiring current position information of all the journalists in the journalist database in real time, and updating the position information of the journalists in the journalist database according to the current position information of the journalists; wherein the reporter information recorded in the reporter database comprises a combination of one or more of the following factors: name, contact, interview, and location information;
when a news clue from the news clue module is received, scheduling factors in the news clue are acquired, the scheduling factors of the news clue are matched with the reporter database, a reporter with factors consistent with the scheduling factors of the news clue is acquired, and an interview task is generated and distributed to the reporter.
5. The news production system based on big data and artificial intelligence of claim 1, wherein the contribution distribution module is specifically configured to:
distributing the news manuscripts in multiple platforms; the platform includes one or more of the following combinations: paper media print shops, PC terminals and mobile terminals.
6. The news production system based on big data and artificial intelligence of claim 1, wherein the intelligent tracking module is specifically configured to:
carrying out data tracking and propagation path tracking on the distributed news manuscripts to obtain tracking data;
and sending the tracking data to a data center module for storage.
7. The big data and artificial intelligence based news production system of claim 1, further comprising:
and an intelligent analysis module: the method is used for analyzing the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
8. The news production method based on big data and artificial intelligence is characterized by comprising the following steps of:
the interview module collects news clues, dispatches the journalist according to the news clues, receives interview manuscripts returned by the journalist, and uploads the interview manuscripts to the data center module; the method specifically comprises the following steps: the reporter looks up the interview task through the terminal equipment; receiving interview data uploaded by a reporter through terminal equipment, analyzing the interview data to obtain interview manuscripts, and uploading the interview manuscripts to a data center module; the interview data comprises voice data, video data, image data and text data;
the data center module stores the interview manuscript;
the intelligent editing module acquires interview manuscripts in the data center module, and edits the interview manuscripts to acquire news manuscripts; the method specifically comprises the following steps: acquiring voice data of interview manuscripts in a data center module, and converting the voice data into text data to obtain first finished text materials; acquiring video data of interview manuscripts in a data center module, and performing video classification, video character recognition, video voice recognition, video fine granularity recognition, video image character recognition, video tag extraction, video dubbing, video subtitle matching, intelligent cutting and video cover selection on the video data to obtain a finished video material; acquiring image data of interview manuscripts in a data center module, and performing image classification, image searching, character recognition, scene recognition, label extraction and image effect enhancement on the image data to obtain a finished product image material; acquiring text data of interview manuscripts in a data center module, and performing text correction, emotion tendency analysis, dialogue emotion recognition, article tag, article classification and news abstract processing on the text data to obtain second finished product text materials; the news manuscript is obtained after the first finished product text material, the finished product video material, the finished product image material and the second finished product text material are comprehensively edited and checked; transmitting the first finished text material, the finished video material, the finished image material, the second finished text material and the news manuscript to a data center module for storage;
the manuscript distribution module distributes the news manuscripts;
the intelligent tracking module tracks the distributed news manuscripts to obtain tracking data;
and the intelligent analysis module analyzes the tracking data to obtain the access quantity, the access area, the access terminal, the access crowd, the gesture development, the comment viewpoint and/or the propagation path of the news manuscript.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010224419.0A CN111444685B (en) | 2020-03-26 | 2020-03-26 | News production system and method based on big data and artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010224419.0A CN111444685B (en) | 2020-03-26 | 2020-03-26 | News production system and method based on big data and artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111444685A CN111444685A (en) | 2020-07-24 |
| CN111444685B true CN111444685B (en) | 2023-09-29 |
Family
ID=71654629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010224419.0A Active CN111444685B (en) | 2020-03-26 | 2020-03-26 | News production system and method based on big data and artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111444685B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112533028B (en) * | 2020-12-10 | 2022-04-08 | 杭州次元岛科技有限公司 | Publishing system for live broadcast advertisement |
| CN115083428B (en) * | 2022-05-30 | 2023-05-30 | 湖南中周至尚信息技术有限公司 | Voice model recognition device for news broadcasting assistance and control method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750600A (en) * | 2011-11-29 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Quick response method and quick response system of news events and based on mobile terminal |
| CN104794104A (en) * | 2015-04-30 | 2015-07-22 | 努比亚技术有限公司 | Multimedia document generating method and device |
| CN108282544A (en) * | 2018-03-08 | 2018-07-13 | 江苏省广播电视总台 | Based on the existing convergent journalism making of media mysorethorn and dissemination system |
| CN109635154A (en) * | 2018-12-14 | 2019-04-16 | 成都索贝数码科技股份有限公司 | A method of internet picture and text contribution is automatically generated based on manuscript and news program |
-
2020
- 2020-03-26 CN CN202010224419.0A patent/CN111444685B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750600A (en) * | 2011-11-29 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Quick response method and quick response system of news events and based on mobile terminal |
| CN104794104A (en) * | 2015-04-30 | 2015-07-22 | 努比亚技术有限公司 | Multimedia document generating method and device |
| CN108282544A (en) * | 2018-03-08 | 2018-07-13 | 江苏省广播电视总台 | Based on the existing convergent journalism making of media mysorethorn and dissemination system |
| CN109635154A (en) * | 2018-12-14 | 2019-04-16 | 成都索贝数码科技股份有限公司 | A method of internet picture and text contribution is automatically generated based on manuscript and news program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111444685A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110351578B (en) | Method and system for automatically producing video programs according to scripts | |
| CN109275046B (en) | Teaching data labeling method based on double video acquisition | |
| CN111444685B (en) | News production system and method based on big data and artificial intelligence | |
| KR102024933B1 (en) | apparatus and method for tracking image content context trend using dynamically generated metadata | |
| US11621792B2 (en) | Real-time automated classification system | |
| CN112784078A (en) | Video automatic editing method based on semantic recognition | |
| CN112883204A (en) | Intelligent media fusion cloud service platform based on big data | |
| CN115580758A (en) | Video content generation method and device, electronic equipment and storage medium | |
| Kannao et al. | Segmenting with style: detecting program and story boundaries in TV news broadcast videos | |
| CN112291574B (en) | Large-scale sports event content management system based on artificial intelligence technology | |
| CN112468754A (en) | Method and device for acquiring stroke record data based on audio and video recognition technology | |
| CN112468753B (en) | Method and device for acquiring and checking record data based on audio and video recognition technology | |
| Fersini et al. | Multimedia summarization in law courts: a clustering-based environment for browsing and consulting judicial folders | |
| US20190332829A1 (en) | System and method for identifying and tagging assets within an av file | |
| CN111274960A (en) | Video processing method and device, storage medium and processor | |
| Co et al. | Automatic topic-based lecture video segmentation | |
| Kaneko et al. | AI-driven smart production | |
| Kannao et al. | A system for semantic segmentation of TV news broadcast videos | |
| CN117395475B (en) | High-availability low-repetition store video production method and system | |
| KR20240040907A (en) | A system that automatically edits highlights | |
| Xu et al. | Automatic generated recommendation for movie trailers | |
| Edelkamp | Multimedia Data | |
| Wijewardena et al. | Improve Productivity and Create a Professional Sri Lankan Film Industry | |
| Gatica-Perez et al. | On automatic annotation of meeting databases | |
| Patil et al. | Holistic Approach for Multimodal Lecture Video Retrieval |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230904 Address after: 8th Floor, Ping Street, No. 85 Jiaochangkou, Yuzhong District, Chongqing 400010 Applicant after: Chongqing Upstream News Media Co.,Ltd. Address before: No. 60 Yanziyan, Yuzhong District, Chongqing 400010 Applicant before: Chongqing commercial newspaper |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |