CN112287172A - Video album generating method and device - Google Patents
Video album generating method and device Download PDFInfo
- Publication number
- CN112287172A CN112287172A CN202011182062.0A CN202011182062A CN112287172A CN 112287172 A CN112287172 A CN 112287172A CN 202011182062 A CN202011182062 A CN 202011182062A CN 112287172 A CN112287172 A CN 112287172A
- Authority
- CN
- China
- Prior art keywords
- information
- video
- information text
- generating
- determining
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 230000002194 synthesizing effect Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 206010035664 Pneumonia Diseases 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000003814 drug Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 229940079593 drug Drugs 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000002177 L01XE27 - Ibrutinib Substances 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- XYFPWWZEPKGCCK-GOSISDBHSA-N ibrutinib Chemical compound C1=2C(N)=NC=NC=2N([C@H]2CN(CCC2)C(=O)C=C)N=C1C(C=C1)=CC=C1OC1=CC=CC=C1 XYFPWWZEPKGCCK-GOSISDBHSA-N 0.000 description 2
- 229960001507 ibrutinib Drugs 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 229960005486 vaccine Drugs 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for generating a video album, wherein the method comprises the following steps: respectively obtaining information texts of specific subjects from various different media; determining named entities related to the subject in each information text; determining the subject label of each information text according to the named entity; putting the information text containing the same theme label into a set corresponding to the theme label; and generating a video album according to the information text in the set. The invention can improve the value degree and the transmission efficiency of the information content.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a method and a device for generating a video album.
Background
Currently, with the diversification of media, the news information distribution channels and ways for the same event are more and more diversified, and the interpretation angle of the same event by different publishers will be different, and may even be completely opposite. However, since different users usually focus on different media or have different preferences, most users can only see part of the information, which undoubtedly leads the user to recognize and understand the event, and affects the user to accurately judge the event. Therefore, how to more conveniently enable the user to obtain the comprehensive information of multiple angles for the same event is an important problem that the industry needs to solve.
Disclosure of Invention
The invention provides a video album generating method and device, which are used for improving the value degree and the transmission efficiency of information contents.
Therefore, the invention provides the following technical scheme:
a video album generating method, the method comprising:
respectively obtaining information texts of specific subjects from various different media;
determining named entities related to the subject in each information text;
determining the subject label of each information text according to the named entity;
putting the information text containing the same theme label into a set corresponding to the theme label;
and generating a video album according to the information text in the set.
Optionally, the method further comprises: determining the theme according to the network hot words or the set keywords;
the obtaining of the information text of the specific subject from the plurality of different media respectively comprises:
the information text of the specific subject is obtained from any two or more media as follows: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles.
Optionally, the determining the named entity related to the topic in each information text includes:
determining named entities related to the subject in each information text based on a pre-established domain knowledge base; and/or
And determining named entities related to the subject in each information text based on a pre-trained model.
Optionally, the determining the tag of the information text according to the named entity and the association relationship thereof includes:
and clustering the named entities and the incidence relation thereof, and determining the label of the information text according to a clustering result.
Optionally, the generating a video album according to the information text in the set includes:
generating a video unit corresponding to each information text in the set;
and splicing the video units to obtain a video album.
Optionally, the generating the video unit corresponding to the information text includes:
acquiring a picture matched with the information text and generating a basic video file containing the picture; the pictures comprise any one or more of the following: background pictures and entity word pictures;
generating an audio file corresponding to the information text;
and synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
A video album generating apparatus, the apparatus comprising:
the information acquisition module is used for respectively acquiring information texts with specific subjects from various different media;
the named entity determining module is used for determining the named entities related to the subject in each information text;
the marking module is used for determining the subject label of each information text according to the named entity;
the grouping module is used for putting the information texts containing the same theme tags into a set corresponding to the theme tags;
and the video album generating module is used for generating a video album according to the information text in the set.
Optionally, the apparatus further comprises:
the theme determining module is used for determining the theme according to the network hot words or the set keywords;
the information acquisition module respectively acquires the information text of the specific theme from any two or more media: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles.
Optionally, the named entity determining module includes:
the first determination module is used for determining named entities related to the theme in each information text based on a pre-established domain knowledge base; and/or
And the second determination module is used for determining the named entities related to the theme in each information text based on a pre-trained model.
Optionally, the labeling module is specifically configured to cluster the named entities and the association relationship thereof, and determine the label of the information text according to a clustering result.
Optionally, the video album generating module includes:
the video production unit is used for generating a video unit corresponding to each information text in the set;
and the splicing unit is used for splicing the video units to obtain a video album.
Optionally, the video production unit comprises:
the basic video generating unit is used for acquiring pictures matched with the information texts and generating basic video files containing the pictures; the pictures comprise any one or more of the following: background pictures and entity word pictures;
the audio generating unit is used for generating an audio file corresponding to the information text;
and the synthesis unit is used for synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
According to the video album generating method and device provided by the embodiment of the invention, the information texts with specific subjects are obtained from various different media, the information texts are labeled, the information texts with the same labels are put into the set corresponding to the labels, and the corresponding video album is generated by using the information texts in the set, so that the value degree and the transmission efficiency of the information content are greatly improved.
Drawings
FIG. 1 is a flow chart of a video album generating method according to an embodiment of the present invention;
fig. 2 is a block diagram of a video album generating apparatus according to an embodiment of the present invention.
Detailed Description
For an event, the way in which text from a single data source is propagated, whether from its content or visual effect, is limited. Most users will not spend much time and effort to hunt for various media, so it is hard to avoid the bias of user's cognition caused by the limitation of information media. Therefore, the embodiment of the invention provides a method and a system for generating a video album, which are used for acquiring information texts with specific subjects from various different media, labeling the information texts, putting the information texts with the same labels into a set corresponding to the labels, and generating the corresponding video album by using the information texts in the set, thereby greatly improving the value degree and the transmission efficiency of information contents.
Fig. 1 is a flowchart of a video album generating method according to an embodiment of the present invention, including the following steps:
For example, the informational text may be obtained from any two or more of the following mediums: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles. Of course, the present invention is not limited to these media, and other media may be used according to the actual application, and the embodiment of the present invention is not limited thereto.
It should be noted that, for information data of different media, it can be obtained through corresponding data interfaces, for example, for a biomedical article, it can be obtained through a free search engine PubMed; for the information disclosed on the webpage, corresponding data and the like can be obtained through a crawler tool.
The theme can be determined according to the network hot words or set keywords, certainly, the corresponding theme can be manually set according to the application requirements, and the information text of the specific theme can be obtained by matching the keywords in the theme. There may be one or more keywords in a topic, and the invention is not limited thereto.
In addition, considering that the reports of the same event by different media are transferred or quoted, similarity comparison can be further performed on the collected different information texts to remove some texts with high similarity, so as to avoid the situation that the collected information texts of different data sources are repeated, avoid unnecessary interference on subsequent processing caused by the repeated information texts, and avoid bad experience brought to the user by the repeated content of video units subsequently pushed to the user.
In the embodiment of the present invention, the information text deduplication processing may be performed in various manners, for example, in the following manner.
Firstly, calculating a Hash value of the title of each information text, and removing repeated information texts according to the calculated Hash value;
secondly, calculating a Hash value of a URL (uniform resource locator) of each information text, and removing repeated information texts according to the calculated Hash value;
and finally, performing similarity calculation on the content of each information text, such as a Simhash algorithm, and removing repeated information texts according to the calculation result. Step 102, determining the named entities related to the subject in each information text.
It should be noted that the collected information text may include not only a chinese text, but also texts in other languages, such as an english text, a french text, and the like. Therefore, after obtaining the information text, it first needs to perform language recognition, special symbol processing, etc. For the Chinese text, it is also necessary to perform word segmentation on each sentence in the information text.
In addition, the manner of determining the named entity associated with the topic can be different for information texts from different sources and different entity types. For example, when the type of named entity is a drug, there can be several ways:
(1) a document source (e.g., PubMed) extracts named entities from the title and abstract of the document.
(2) A regulatory agency source (e.g., NCT) extracts named entities from corresponding text fields.
(3) And the news source extracts named entities from the titles and texts of the news.
It should be noted that named entity identification also relates to the case of concept merging, i.e. merging into one entity if different aliases of the entity occur simultaneously. For example, if IMBRUVICA is the trade name Ibrutinib and appears in an informational text pointing to the same entity, it can be merged into a named entity.
It should be noted that different types of named entities may be included in the same information text, and in the embodiment of the present invention, the named entities of different types need to be extracted, so as to obtain named entities of various types (for example, types of drugs, companies, indications, and the like) related to the topic.
In the embodiment of the invention, the named entities related to the topics in the information text can be determined through key word matching, domain knowledge base query, model-based modes and the like.
The domain knowledge base is a set containing named entities and their relationships in the domain, and can also be regarded as a database. Different domains have different domain knowledge bases.
In an embodiment of the invention, the domain knowledge base comprises; a named entity dictionary and an entity relationship map. The named entity dictionary may include a standard dictionary and an expert dictionary, for example, for the medical field, the standard dictionary may have: a disease professional word bank, an indication professional word bank, a clinical word professional word bank, a biological medicine field organization library and the like. The expert dictionary refers to a word bank which is manually sorted and labeled by experts in the field. Wherein the entity relationship graph may include any one or more of the following relationships: a hierarchical relationship and an association relationship, the association relationship comprising: conceptual relationships, spatial relationships, functional relationships, and the like. The domain knowledge base can be established in various ways, and the embodiment of the invention is not limited.
It should be noted that the named entity includes not only the same entity as the keyword in the topic, but also a synonym or synonym of the keyword, and may also include a word having an association relationship with the keyword, and the association relationship may be determined by an entity relationship map in the domain knowledge base.
The model-based mode can be used as a supplement to a named entity dictionary which does not include the named entity words, for example, for some network new words, the named entity dictionary does not include the named entity words in time, and at the moment, a pre-trained entity recognition model is firstly utilized to determine whether the new words are entity words and the incidence relation between the entity words. And then determining the named entities related to the subject through keyword matching.
Of course, since the entity recognition model is trained based on a large amount of sample data, and has its own advantages, in practical applications, the named entities and their association relation related to the topic in each information text can also be determined based on the model.
It should be noted that, since each information text may include a plurality of named entities related to the topic, when determining the label of each information text, each extracted named entity may be used as a candidate topic, a time window period (for example, in units of days, weeks, or months) is set, word frequency count Δ F1 of the candidate entity at the start point of the time window period and word frequency count Δ F2 of the candidate entity at the end point of the time window period are respectively calculated, and the attention of each candidate topic is obtained through calculation according to the word frequency count. For example, it is calculated according to the following formula:
where δ (w) represents the topic attention when the named entity w is a candidate topic, Δ t represents the time window length, and ξ ═ 1.
It should be noted that the word frequency Δ F1 of the candidate entity at the start of the time window period may be a sum of occurrence times of the candidate entity in the previous time window period, and the word frequency Δ F2 of the end of the time window period may be a sum of occurrence times of the candidate entity in the current time window period.
After the attention degree of each candidate theme is obtained through calculation, Top n (n is the number of video albums needing to be generated, and the numerical value can be set according to actual needs) of the attention degree is taken as a theme label of the video album to be generated.
And 105, generating a video album according to the information text in the set.
Specifically, video units corresponding to each information text in the set may be generated first, and then the video units may be merged into a multi-angle reported video news, that is, a video album, by using a video stitching technique. Some transition animation and other beautification effects can be added among the video units.
The specific process of generating the video unit is as follows:
(1) generating an audio file corresponding to the information text;
(2) acquiring a picture matched with the information text and generating a basic video file containing the picture; the pictures include, but are not limited to, any one or more of the following: background pictures and entity word pictures;
for example, the base video may be formed by displaying different pictures in a loop, for example, a picture shows 3s, and a picture shows 3s, a 6s non-audio video file will be formed.
For another example, the generated audio file and the information text may be aligned in time sequence, and then, according to the content of the information text, a background picture and an entity word picture are synchronously added to the base video, for example, a corresponding entity word picture is displayed in a time period in which an entity word appears in the corresponding audio, and a background picture is displayed in other time periods. Furthermore, there may be one or more background pictures, for example, in the case of multiple background pictures, they may be displayed alternately or randomly.
Certainly, in practical application, the basic video can be made as required, and the rendering effect can be added to the picture displayed in the basic video according to the contents of the picture and the text of the picture, so that the video effect is better improved.
(3) And synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
It should be noted that the production of the video file can be performed by using some existing video tools, such as an FFmpeg video processing tool.
For example, an analysis article of the new coronary pneumonia development situation collected from data source a (news media), denoted as ID 001, identifies named entities (indications or drugs) in the article, and the identified named entities include indication entities: new coronary pneumonia;
a medical document of development progress of a new coronary pneumonia vaccine was obtained from data source B (PubMed literature source), and is denoted as ID 002, named entities (indications or drugs) in the document are identified, and the identified named entities include indication entities: new coronary pneumonia;
similarly, more informative text may be collected from other data sources, such as text ID 003 from data source C and text ID 004 from data source D.
Clustering the information texts according to the named entities and the incidence relation thereof in each identified information text, and if the ID 001 and the ID 002 have the same indication entity, namely new coronary pneumonia, according to the clustering result, putting the ID 001 and the ID 002 into the same set to generate a corresponding video album, wherein the labels of the video album are as follows: new coronary pneumonia.
When the video units corresponding to the information texts in the set are spliced, the video units may be filtered, for example, the number of the video units in the set is limited, or the video units are filtered according to the popularity of the information content corresponding to each video unit, and the remaining video units after filtering are then spliced.
In addition, when the video units are spliced, the video units can be further spliced according to a certain sorting rule, such as: and sequentially splicing according to the corresponding rules of the release time sequence of each information text, the hierarchical relationship sequence of the named entities in each information text, the weight of each information text and the like.
In addition, in the generated video album, the related information of each video unit, such as keywords, information sources, serial numbers, summaries, etc., can also be added to the start segment of the video unit, so as to better distinguish the different contents of the segments.
Further, in practical applications, the video special edition may be stored in a server, and when a user queries or browses information, a video album having the same event tag as the information is pushed to the user. Such as: automatically playing the video album in the current window, or displaying the link address of the video album through a floating window; of course, other pushing manners are also possible, and the embodiment of the present invention is not limited thereto.
According to the video album generating method provided by the embodiment of the invention, the information texts with specific subjects are obtained from various different media, the information texts are labeled, the information texts with the same labels are put into the set corresponding to the labels, and the corresponding video album is generated by using the information texts in the set, so that the value degree and the transmission efficiency of the information content are greatly improved.
Accordingly, an embodiment of the present invention further provides a video album generating apparatus, as shown in fig. 2, which is a structural block diagram of the apparatus.
In this embodiment, the apparatus includes the following modules:
the information acquisition module 201 is used for respectively acquiring information texts with specific subjects from various different media;
a named entity determining module 202, configured to determine a named entity related to the topic in each information text;
the marking module 203 is used for determining the subject label of each information text according to the named entity;
a grouping module 204, configured to put information texts containing the same theme tags into a set corresponding to the theme tags;
and a video album generating module 205, configured to generate a video album according to the information text in the set.
The topic may be determined in various ways according to application requirements, for example, the topic is determined by a corresponding topic determination module (not shown) according to network hot words or set keywords. A topic may include one or more keywords.
Correspondingly, the information collecting module 201 may obtain the information text of the specific topic by matching the information text with the keywords in the topic, for example, the information text of the specific topic may be obtained from any two or more of the following media: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles. Of course, in practical applications, there are no limitations to these media, and there may be other media, which are not listed here.
In addition, considering that reports of the same event by different media are sometimes transferred or quoted, so as to avoid the situation that the collected information texts of different data sources are repeated, the information collection module 201 may further perform similarity comparison on the collected different information texts, remove some texts with high similarity, avoid unnecessary interference on subsequent processing due to the repetition of the information texts, and avoid bad experience brought to the user due to the repetition of the content of the video unit subsequently pushed to the user.
In practical applications, the named entity determining module 202 may determine the named entity related to the topic in each information text in various ways, for example, the named entity determining module 202 may include: a first determination module, and/or a second determination module, wherein:
the first determination module is used for determining named entities related to the subject in each information text based on a pre-established domain knowledge base;
the second determination module is used for determining named entities related to the subject in each information text based on a pre-trained model.
The specific process of determining the named entity related to the topic in each information text based on the domain knowledge base and the model is described in detail above, and is not described herein again.
It should be noted that the named entity includes not only the same entity as the keyword in the topic, but also a synonym or synonym of the keyword, and may also include a word having an association relationship with the keyword, and the association relationship may be determined by an entity relationship map in the domain knowledge base.
Since each information text may include a plurality of named entities related to the topic and the named entities have different association relationships, in the embodiment of the present invention, the tagging module 203 may perform multi-angle and different-granularity clustering on the named entities and the association relationships thereof, and determine the tag of the information text according to the clustering result. Accordingly, the tag may be information such as an event, a keyword, an attribute category, and the like, and the embodiment of the present invention is not limited thereto.
One specific structure of the video album generating module 205 includes the following units:
the video production unit is used for generating a video unit corresponding to each information text in the set;
and the splicing unit is used for splicing the video units to obtain a video album. During splicing, some beautification effects such as transition animation and the like can be added among the video units.
The video making unit may make a video unit corresponding to each information text by using technologies of text-to-speech, audio-video synthesis, and the like, for example, a specific structure of the video making unit may include the following units:
the basic video generating unit is used for acquiring pictures matched with the information texts and generating basic video files containing the pictures; the pictures comprise any one or more of the following: background pictures and entity word pictures;
the audio generating unit is used for generating an audio file corresponding to the information text;
and the synthesis unit is used for synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
It should be noted that, when the splicing unit splices the video units, the splicing unit may also follow a certain ordering rule, such as: and sequentially splicing according to the corresponding rules of the release time sequence of each information text, the hierarchical relationship sequence of the named entities in each information text, the weight of each information text and the like.
In addition, in the generated video album, the related information of each video unit, such as keywords, information sources, serial numbers, summaries, etc., can also be added to the start segment of the video unit, so as to better distinguish the different contents of the segments. The adding process of the related information may be completed by the synthesizing unit when the video unit is generated, or may be completed by the splicing unit when the video unit is spliced, and the embodiment of the present invention is not limited thereto.
In order to avoid that the generated video album contains repeated content and brings poor experience to the user, the video album generating module 205 may further include a filtering unit, which is configured to filter the video units corresponding to the information texts in the set before the splicing unit splices the video units. Correspondingly, the splicing unit performs splicing processing on the video units left after filtering.
Further, in another embodiment of the apparatus of the present invention, the apparatus may further include: a video storage module and an information pushing module (not shown), wherein the video storage module is used for storing video albums corresponding to the tags. Correspondingly, the information pushing module is used for acquiring a video album with the same event label as the information from the video storage module when a user inquires or browses the information, and pushing the video album to the user. Such as: automatically playing the video album in the current window, or displaying the link address of the video album through a floating window; of course, other pushing manners are also possible, and the embodiment of the present invention is not limited thereto.
It should be noted that, for the embodiments of the video album generating apparatus, since the functional implementation of each module and unit is similar to that in the corresponding method, the embodiments of the video album generating apparatus are described more simply, and relevant points can be referred to the corresponding description of the embodiments of the method.
The video album generating device provided by the embodiment of the invention obtains the information texts with specific subjects from various different media, tags the information texts, puts the information texts with the same tags into the set corresponding to the tags, and generates the corresponding video album by using the information texts in the set, thereby greatly improving the value degree and the transmission efficiency of the information content.
By using the method and the device for generating the video album, information texts can be acquired from various different media regularly in an off-line mode, corresponding processing is carried out through the process introduced above, and corresponding tags and the video album are obtained and stored; when a subsequent user accesses or inquires corresponding information, the video album with the same label as the information text is pushed to the user, so that the value degree and the transmission efficiency of the information content are effectively improved, and the user experience is improved.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Furthermore, the above-described system embodiments are merely illustrative, wherein modules and units illustrated as separate components may or may not be physically separate, i.e., may be located on one network element, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Accordingly, the embodiment of the present invention further provides an apparatus for a video album generating method, where the apparatus is an electronic device, and for example, the apparatus may be a mobile terminal, a computer, a tablet device, a personal digital assistant, or the like. The electronic device may include one or more processors, memory; wherein the memory is used for storing computer executable instructions and the processor is used for executing the computer executable instructions to realize the method of the previous embodiments.
The present invention has been described in detail with reference to the embodiments, and the description of the embodiments is provided to facilitate the understanding of the method and apparatus of the present invention, and is intended to be a part of the embodiments of the present invention rather than the whole embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative effort shall fall within the protection scope of the present invention, and the content of the present description shall not be construed as limiting the present invention. Therefore, any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. A video album generating method, the method comprising:
respectively obtaining information texts of specific subjects from various different media;
determining named entities related to the subject in each information text;
determining the subject label of each information text according to the named entity;
putting the information text containing the same theme label into a set corresponding to the theme label;
and generating a video album according to the information text in the set.
2. The method of claim 1, further comprising:
determining the theme according to the network hot words or the set keywords;
the obtaining of the information text of the specific subject from the plurality of different media respectively comprises:
the information text of the specific subject is obtained from any two or more media as follows: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles.
3. The method of claim 1, wherein determining the named entity in each informational text that is associated with the topic comprises:
determining named entities related to the subject in each information text based on a pre-established domain knowledge base; and/or
And determining named entities related to the subject in each information text based on a pre-trained model.
4. The method of claim 1, wherein determining the label of the informative text according to the named entity and its associated relationship comprises:
and clustering the named entities and the incidence relation thereof, and determining the label of the information text according to a clustering result.
5. The method of any of claims 1 to 4, wherein generating a video album based on the informative text in the collection comprises:
generating a video unit corresponding to each information text in the set;
and splicing the video units to obtain a video album.
6. The method of claim 5, wherein the generating the video unit corresponding to the informative text comprises:
acquiring a picture matched with the information text and generating a basic video file containing the picture; the pictures comprise any one or more of the following: background pictures and entity word pictures;
generating an audio file corresponding to the information text;
and synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
7. A video album generating apparatus, characterized in that the apparatus comprises:
the information acquisition module is used for respectively acquiring information texts with specific subjects from various different media;
the named entity determining module is used for determining the named entities related to the subject in each information text;
the marking module is used for determining the subject label of each information text according to the named entity;
the grouping module is used for putting the information texts containing the same theme tags into a set corresponding to the theme tags;
and the video album generating module is used for generating a video album according to the information text in the set.
8. The apparatus of claim 7, further comprising:
the theme determining module is used for determining the theme according to the network hot words or the set keywords;
the information acquisition module respectively acquires the information text of the specific theme from any two or more media: news media, journal articles, web pages, information published by regulatory agencies, WeChat public articles.
9. The apparatus of claim 7, wherein the named entity determination module comprises:
the first determination module is used for determining named entities related to the theme in each information text based on a pre-established domain knowledge base; and/or
And the second determination module is used for determining the named entities related to the theme in each information text based on a pre-trained model.
10. The apparatus of claim 7,
the marking module is specifically used for clustering the named entities and the incidence relations thereof and determining the labels of the information texts according to the clustering results.
11. The apparatus of any of claims 7-10, wherein the video album generating module comprises:
the video production unit is used for generating a video unit corresponding to each information text in the set;
and the splicing unit is used for splicing the video units to obtain a video album.
12. The apparatus of claim 11, wherein the video production unit comprises:
the basic video generating unit is used for acquiring pictures matched with the information texts and generating basic video files containing the pictures; the pictures comprise any one or more of the following: background pictures and entity word pictures;
the audio generating unit is used for generating an audio file corresponding to the information text;
and the synthesis unit is used for synthesizing the basic video file and the audio file to obtain a video unit corresponding to the information text.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011182062.0A CN112287172A (en) | 2020-10-29 | 2020-10-29 | Video album generating method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011182062.0A CN112287172A (en) | 2020-10-29 | 2020-10-29 | Video album generating method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287172A true CN112287172A (en) | 2021-01-29 |
Family
ID=74352594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011182062.0A Pending CN112287172A (en) | 2020-10-29 | 2020-10-29 | Video album generating method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287172A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108170838A (en) * | 2018-01-12 | 2018-06-15 | 平安科技（深圳）有限公司 | The visualization that topic develops shows method, application server and computer readable storage medium |
| CN108241856A (en) * | 2018-01-12 | 2018-07-03 | 新华智云科技有限公司 | Information generation method and equipment |
| CN109710773A (en) * | 2018-12-17 | 2019-05-03 | 北京百度网讯科技有限公司 | The generation method and its device of event body |
| CN110162796A (en) * | 2019-05-31 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Special Topics in Journalism creation method and device |
-
2020
- 2020-10-29 CN CN202011182062.0A patent/CN112287172A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108170838A (en) * | 2018-01-12 | 2018-06-15 | 平安科技（深圳）有限公司 | The visualization that topic develops shows method, application server and computer readable storage medium |
| CN108241856A (en) * | 2018-01-12 | 2018-07-03 | 新华智云科技有限公司 | Information generation method and equipment |
| CN109710773A (en) * | 2018-12-17 | 2019-05-03 | 北京百度网讯科技有限公司 | The generation method and its device of event body |
| CN110162796A (en) * | 2019-05-31 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Special Topics in Journalism creation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hider | Information resource description: creating and managing metadata | |
| Allan | Automatic hypertext construction | |
| US20020038299A1 (en) | Interface for presenting information | |
| CN111046221B (en) | Song recommendation method, device, terminal equipment and storage medium | |
| US20100274770A1 (en) | Transductive approach to category-specific record attribute extraction | |
| Hyvönen et al. | CultureSampo—Finnish culture on the Semantic Web 2.0. Thematic perspectives for the end-user | |
| JP2010092476A (en) | Display method, system and storage medium | |
| Lipczak et al. | The impact of resource title on tags in collaborative tagging systems | |
| Xu et al. | LogCanvas: visualizing search history using knowledge graphs | |
| WO2014000130A1 (en) | Method or system for automated extraction of hyper-local events from one or more web pages | |
| Kousha et al. | Can the impact of scholarly images be assessed online? An exploratory study using image identification technology | |
| RU2459242C1 (en) | Method of generating and using recursive index of search engines | |
| Kipp | Exploring the context of user, creator and intermediary tagging | |
| Nguyen et al. | Web search clustering and labeling with hidden topics | |
| Sirsat et al. | Pattern matching for extraction of core contents from news web pages | |
| Böschen | Software review: The JATSdecoder package—extract metadata, abstract and sectioned text from NISO-JATS coded XML documents; Insights to PubMed central’s open access database | |
| CN112287172A (en) | Video album generating method and device | |
| Hsu et al. | Mining various semantic relationships from unstructured user-generated web data | |
| Yoon et al. | Engineering an image‐browsing environment: re‐purposing existing denotative descriptors | |
| Fung et al. | Discover information and knowledge from websites using an integrated summarization and visualization framework | |
| Belerao et al. | Summarization using mapreduce framework based big data and hybrid algorithm (HMM and DBSCAN) | |
| CN112241463A (en) | Search method based on fusion of text semantics and picture information | |
| Kim et al. | Korean books and FRBR: an investigation | |
| Angrosh et al. | Contextual information retrieval in research articles: Semantic publishing tools for the research community | |
| Baldoni et al. | Sentiment analysis in the planet art: A case study in the social semantic web |
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 |