CN113722540A - Knowledge graph construction method and device based on video subtitles and computing equipment - Google Patents
Knowledge graph construction method and device based on video subtitles and computing equipment Download PDFInfo
- Publication number
- CN113722540A CN113722540A CN202010450442.1A CN202010450442A CN113722540A CN 113722540 A CN113722540 A CN 113722540A CN 202010450442 A CN202010450442 A CN 202010450442A CN 113722540 A CN113722540 A CN 113722540A
- Authority
- CN
- China
- Prior art keywords
- video
- entity
- knowledge graph
- video entity
- keyword
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 17
- 230000002457 bidirectional effect Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 239000000284 extract Substances 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000008447 perception Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000011022 operating instruction Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000001228 spectrum Methods 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
- G06F16/75—Clustering; Classification
-
- 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
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using original textual content or text extracted from visual content or transcript of audio data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/278—Subtitling
Abstract
The embodiment of the invention relates to the technical field of video processing, and discloses a knowledge graph construction method, a knowledge graph construction device and a calculation device based on video subtitles, wherein the method comprises the following steps: acquiring a video entity uploaded by a user, and extracting video subtitles according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph. Through the mode, the video classification and theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
Description
Technical Field
The embodiment of the invention relates to the technical field of video processing, in particular to a knowledge graph construction method and device based on video subtitles and computing equipment.
Background
The existing video relation methods commonly used by services such as video recommendation, public opinion analysis and the like have three types: 1) the method comprises the steps that information such as keywords, video titles and the like provided by a video submitter is classified, when a user browses, searches, watches or collects videos similar to the keywords and the video titles, the preference weight of a certain user is adjusted, and then a user preference model is updated, or a public opinion model is updated according to information such as real-time hot spots or real-time rising hot spot videos. When video recommendation is performed on a user, a user preference model and a public opinion model are adopted to calculate the classification/keyword which is most interesting to the user at present, and the classification/keyword is displayed according to the factors such as popularity, playing amount, whether the user watches the video or the user-defined sequence. When monitoring public sentiment, the classification and title of recently played volume/played video and the preference user characteristics need to be counted and input into a corresponding model for analysis. 2) And analyzing according to the video comment and the heat, and extracting keywords in the comment according to a certain NLP (natural language processing) algorithm to perform subsequent steps. 3) The judgment is carried out by adopting the video titles, the video classifications and the video comments together, and the method is the integration of the two methods.
For the method for classifying and recommending videos by using the video keywords and the video titles, the video titles and other contents are customized by a user and are influenced by artificial subjective factors, dirty data can appear, and the result cannot truly reflect the video contents; when a malicious video appears, an uploader only needs to avoid malicious keywords, select other classifications or adopt methods without malicious titles and the like, and then the video can be uploaded safely. For the method of classifying and recommending by using video comments, the comments are actively commented by viewers of the video, the content is decided by a publisher, and the core viewpoint and the content of the comment are different from the video or are deviated by artificial guidance. Due to the data problem, the subsequent results have deviation or errors, unpredictable results can be caused in the actual use situation, for example, inappropriate content is pushed to children, associated videos cannot cause user interest to cause user loss, social problems are caused by errors in understanding public opinion hotspots, and the like.
In addition, in the prior art, all operation processes are performed at the server side, when a large amount of high-concurrency user behaviors are generated, a large amount of operation pressure is brought to the background, the operation capability of the background server needs to be tested, the expense of a user is increased, and the user perception is influenced with great possibility.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a method, an apparatus, and a computing device for constructing a knowledge graph based on video subtitles, which overcome or at least partially solve the above problems.
According to an aspect of the embodiments of the present invention, there is provided a method for constructing a knowledge graph based on video subtitles, the method including: acquiring a video entity uploaded by a user, and extracting video subtitles according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
In an optional manner, the obtaining the keywords of the video entity according to the video entity and the video subtitle to form a keyword group includes: forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set; performing word segmentation operation on the distributed data set to obtain word data after word segmentation; performing secondary interference processing on the acquired word data; and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
In an optional manner, the extracting the keywords of the video entity from the term data after the secondary interference processing to form the keyword group includes: extracting first keyword data from the word data by adopting a first algorithm; extracting second keyword data from the word data by adopting a second algorithm; and combining the first keyword data and the second keyword data to form the keyword group.
According to another aspect of the embodiments of the present invention, there is provided a method for constructing a knowledge graph based on video subtitles, the method including: receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
In an optional manner, the calculating a similarity between the first keyword group and a second keyword group corresponding to a second video entity in the original knowledge-graph includes: calculating semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword groupi(ii) a According to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
In an alternative manner, the determining the entity relationship between the first video entity and the second video entity according to the similarity and constructing a new knowledge graph includes: if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association; if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association; if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related; and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
According to another aspect of the embodiments of the present invention, there is provided a video subtitle-based knowledge graph constructing apparatus, including: the caption extracting unit is used for acquiring a video entity uploaded by a user and extracting video captions according to the video; the keyword acquisition unit is used for acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and the sending unit is used for transmitting the data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
According to another aspect of the embodiments of the present invention, there is provided a video subtitle-based knowledge graph constructing apparatus, including: the receiving unit is used for receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; the calculating unit is used for calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge graph; the map construction unit is used for determining the entity relationship between the first video entity and the second video entity according to the similarity and constructing a knowledge map; and the interface service unit is used for providing an external service interface for the knowledge graph so as to facilitate video recommendation service.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the steps of the video caption-based knowledge map construction method.
According to still another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing the processor to execute the steps of the above-mentioned video subtitle-based knowledge graph building method.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram of a video caption-based knowledge-graph building system according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for constructing a video subtitle-based knowledge graph according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating key phrase acquisition in a video subtitle-based knowledge graph construction method according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for constructing a video subtitle-based knowledge graph according to another embodiment of the present invention;
fig. 5 is a schematic diagram illustrating semantic similarity obtaining of a video subtitle-based knowledge graph construction method according to yet another embodiment of the present invention;
fig. 6 is a schematic structural diagram illustrating a video subtitle-based knowledge graph constructing apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram illustrating a video subtitle-based knowledge graph constructing apparatus according to yet another embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a computing device provided by an embodiment of the invention;
fig. 9 shows a schematic structural diagram of a computing device according to a further embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The system for constructing the knowledge graph based on the video subtitles comprises a user side and a server side, specifically, as shown in fig. 1, a user uploads a video entity to the user side, the user side extracts the video subtitles corresponding to the video entity, natural language processing is performed based on the video subtitles, a keyword group is obtained, a video subject and content are accurately grasped, and a data set consisting of video entity identification, video entity names and the keyword group is transmitted to the server side. The server side obtains the similarity of the key phrase corresponding to the video entity and the key phrases corresponding to other video entities in the original knowledge graph, obtains a bidirectional entity relationship between the two key phrases based on the similarity, adds a new node in the original knowledge graph, establishes the bidirectional relationship between the video entity and other video entities in the original knowledge graph, and constructs a video relationship model to form a new knowledge graph. The server side also provides an external service interface for the knowledge graph and supports various services, so that a user can conveniently perform video recommendation service according to the knowledge graph, concise and accurate video relation data are provided for the user, and help is provided for subsequent data application.
Fig. 2 is a flowchart illustrating a method for constructing a knowledge graph based on video subtitles according to an embodiment of the present invention. The knowledge graph construction method based on the video subtitles is mainly applied to a user side. As shown in fig. 2, the method for constructing a knowledge graph based on video subtitles includes:
step S11: and acquiring a video entity uploaded by a user, and extracting video subtitles according to the video.
Specifically, if the video entity has the plug-in subtitle, reading a plug-in subtitle file, and performing text processing to obtain the video subtitle; and if the video entity has the embedded subtitle, extracting the video subtitle by using a subtitle extraction tool. Specifically, the subtitles may be extracted by image recognition, or by voice recognition. Many existing tools and open source packages exist for subtitle extraction, and are not described herein.
Step S12: and obtaining the keywords of the video entity according to the video entity and the video caption to form a keyword group.
Specifically, as shown in fig. 3, the video entity Identification (ID), the video entity name, and the video subtitle are combined into a distributed data set (dataframe), and the distributed data set is preprocessed. The preprocessing of the distributed data set is mainly data cleaning, and comprises the following steps: removing invalid words and stop words such as time marks possibly remaining in subtitles; removing invalid delimiters, such as punctuation marks; the case and case are unified to avoid misreading of the same English word due to the case and case problem; the full name and the abbreviation are unified, and misreading is avoided.
And then performing word segmentation operation on the distributed data set to obtain word data after word segmentation. Specifically, data are imported into a word segmentation system to perform word segmentation operation in a full mode, word segmentation basic data are divided into a semantic knowledge base, a field word base, a field corpus word base, an evaluation corpus and the like, and the part of speech is determined while words are segmented.
And further carrying out secondary interference processing on the acquired word data, such as removing word interference items, such as invalid word words, auxiliary words and the like, and eliminating the expression and the like, brought by the previous step. And finally, extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group. Specifically, a first algorithm is adopted to extract first keyword data from the word data; extracting second keyword data from the word data by adopting a second algorithm; and combining the first keyword data and the second keyword data to form the keyword group. In the embodiment of the invention, a Term Frequency-Inverse Document Frequency (TF-IDF) algorithm is adopted to extract the first keyword data, and the importance of a word is increased in proportion to the occurrence Frequency of the word in a dataframe, but is reduced in Inverse proportion to the occurrence Frequency of the word in a corpus. Wherein the corpus is a set of keywords that already exist in the knowledge graph. And extracting the second keyword data by adopting a Latent Semantic Analysis (LSA) algorithm, and then merging the obtained first keyword data and the second keyword data to obtain a keyword group.
Step S13: and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server side so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the video entity and construct a new knowledge graph.
And after the key phrase is obtained, the key phrase, the video entity identification and the video entity name form a data set. For example, the resulting data set is as follows:
and then uploading the data set to a server side, so that the server side can acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and further construct a new knowledge graph.
The embodiment of the invention utilizes the video captions, adopts the mixed use of the TF/IDF algorithm and the LSA algorithm in the natural language processing, can accurately capture the keywords of the video content, is not influenced by human reasons and guided by public opinion comments, truly reflects the video content, provides accurate video classification data, can accurately position the video category and theme according to the data, provides help for subsequent processing and provides accurate video classification data. The embodiment of the invention also adopts an edge calculation method, part of high calculation is transferred to the user side, and video classification processing is carried out when the user side uploads the video, so that server resources can be saved.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
Fig. 4 shows a flowchart of a method for constructing a knowledge graph based on video subtitles according to an embodiment of the present invention. The knowledge graph construction method based on the video subtitles is mainly applied to a server side. As shown in fig. 4, the method for constructing a knowledge graph based on video subtitles includes:
step S21: receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity.
The knowledge graph in the embodiment of the invention is a data expression form reflecting the relationship between the entities, and expresses the transaction relationship by unstructured data. Three elements are required in the knowledge-graph: entity, entity attribute, entity relationship. The entity is a video entity, and the entity attribute data is a keyword in a keyword group corresponding to the video entity. The entity relationship is a bidirectional relationship between two video entities, and the embodiment of the invention needs to extract the entity relationship between the two video entities for constructing the knowledge graph. In step S21, a data set of a first video entity uploaded by a user side is received, where the data set includes a first video entity identifier, a first video entity name, and a first keyword group extracted according to the first video entity, so as to obtain an entity relationship of other video entities in the original knowledge graph according to the first keyword group.
Step S22: and calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge graph.
In the embodiment of the present invention, the semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword group is calculatedi. For example, as shown in fig. 5, word2vec is used to calculate semantic similarity between n keywords in the keyword group of video entity a and m keywords in the keyword group of video entity B, and for video entity a, n × m semantic similarities P are obtainediThe value ranges from-1 to 1. Wherein, the video entity B is a graph obtained from the original knowledgeA selected video entity in the spectrum. In the embodiment of the present invention, a video entity with a larger number of repeated keywords corresponding to the first video entity may be selected as the video entity B in the original knowledge graph.
Further according to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
wherein i is a positive integer, n is the number of the keywords in the first keyword group, and m is the number of the keywords in the second keyword group. The effect of each keyword on the final result is considered to be the same here.
Step S23: and determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph.
In the embodiment of the present invention, if the similarity between the first keyword group and the second keyword group is greater than or equal to a first threshold, it is determined that the entity relationship between the first video entity and the second video entity is strong association; if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association; and if the similarity between the first key phrase and the second key phrase is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related. The first threshold is greater than the second threshold, and the first threshold and the second threshold may be set as needed, and preferably, the first threshold is 0.5, and the second threshold is 0.2.
And after the entity relationship judgment of the first video entity and the second video entity is completed, adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity. For example, the build statement is as follows (taking the neo4j database as an example):
CREATE(videoA:keyWord1::keyWord2:keyWord3)
MATCH(videoA:video_A),(videoB:video_B)
CREATE(videoA:video_A)<-(r:relationship)->(videoB:video_B)
RETURN r
in an embodiment of the present invention, the above steps may be repeated to select a plurality of second video entities, preferably 3, 4 second video entities, from the original knowledge-graph, in the same way as before. And respectively calculating entity relations between the first video entity and the plurality of second video entities, and establishing bidirectional relations between the first video entity and the plurality of second video entities and a new knowledge graph when nodes of the first video entity are added.
Step S24: and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
Specifically, frames such as spring, spring MVC, MyBatis, shiro, redis (ehcache) + Nginix are integrated, and a standard/custom (customized and developed) external service interface is provided, so that, aiming at the application of the video relation knowledge graph, the relation between videos is simplified, the capability of the video knowledge graph is provided for the outside, data and capability are provided for related applications such as video recommendation, sentiment control and the like, concise and accurate video relation data are provided for data users, and help is provided for subsequent data application. The embodiment of the invention simplifies the relation logic among videos, replaces relevance data by concise classification, accurately describes the relation among the videos, constructs the relation value in the knowledge graph, provides video recommendation capability and is beneficial to users in practical application.
The embodiment of the invention receives a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; an external service interface is provided for the new knowledge graph to facilitate video recommendation service, accurate video associated data can be provided, the relation between videos can be accurately described, the relation value in the knowledge graph is constructed, the video recommendation capability is provided, the use of a user is facilitated in practical application, and the user perception is improved.
Fig. 6 is a schematic structural diagram of a video subtitle-based knowledge graph constructing apparatus according to an embodiment of the present invention. As shown in fig. 6, the apparatus for constructing a knowledge graph based on video subtitles is provided at a user end, and includes: a subtitle extraction unit 601, a keyword acquisition unit 602, and a transmission unit 603. Wherein:
the caption extraction unit 601 is configured to obtain a video entity uploaded by a user, and extract a video caption according to the video; the keyword obtaining unit 602 is configured to obtain a keyword of the video entity according to the video entity and the video subtitle to form a keyword group; the sending unit 603 is configured to transmit the video entity identifier, the video entity name, and the data set formed by the keyword to the server, so as to obtain an entity relationship between the video entity and another video entity in the knowledge graph according to the keyword, and construct a new knowledge graph.
In an alternative manner, the keyword obtaining unit 602 is configured to: forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set; performing word segmentation operation on the distributed data set to obtain word data after word segmentation; performing secondary interference processing on the acquired word data; and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
In an alternative manner, the keyword obtaining unit 602 is configured to: extracting first keyword data from the word data by adopting a first algorithm; extracting second keyword data from the word data by adopting a second algorithm; and combining the first keyword data and the second keyword data to form the keyword group.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
Fig. 7 is a schematic structural diagram of a video subtitle-based knowledge graph constructing apparatus according to yet another embodiment of the present invention. As shown in fig. 7, the apparatus for constructing a knowledge graph based on video subtitles is disposed at a server side, and includes: a receiving unit 701, a computing unit 702, a graph building unit 703 and an interface service unit 704. Wherein:
the receiving unit 701 is configured to receive a data set of a first video entity uploaded by a user side, where the data set includes a first video entity identifier, a first video entity name, and a first keyword group extracted according to the first video entity; the calculating unit 702 is configured to calculate a similarity between the first keyword group and a second keyword group corresponding to a second video entity in the original knowledge base; the map construction unit 703 is configured to determine an entity relationship between the first video entity and the second video entity according to the similarity, and construct a knowledge map; the interface service unit 704 is configured to provide an external service interface for the knowledge graph to facilitate video recommendation service.
In an alternative manner, the computing unit 702 is configured to: calculating semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword groupi(ii) a According to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
In an alternative manner, the map construction unit 703 is configured to: if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association; if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association; if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related; and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
The embodiment of the invention receives a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; an external service interface is provided for the new knowledge graph to facilitate video recommendation service, accurate video associated data can be provided, the relation between videos can be accurately described, the relation value in the knowledge graph is constructed, the video recommendation capability is provided, the use of a user is facilitated in practical application, and the user perception is improved.
An embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the method for constructing a knowledge graph based on video subtitles in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring a video entity uploaded by a user, and extracting video subtitles according to the video;
acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group;
and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
In an alternative, the executable instructions cause the processor to:
forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set;
performing word segmentation operation on the distributed data set to obtain word data after word segmentation;
performing secondary interference processing on the acquired word data;
and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
In an alternative, the executable instructions cause the processor to:
extracting first keyword data from the word data by adopting a first algorithm;
extracting second keyword data from the word data by adopting a second algorithm;
and combining the first keyword data and the second keyword data to form the keyword group.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
The embodiment of the present invention provides another non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the method for constructing a knowledge graph based on video subtitles in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity;
calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base;
determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph;
and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
In an alternative, the executable instructions cause the processor to:
calculating semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword groupi；
According to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
wherein i is a positive integer, n is the number of the keywords in the first keyword group, and m is the number of the keywords in the second keyword group.
In an alternative, the executable instructions cause the processor to:
if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association;
if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association;
if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related;
and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
The embodiment of the invention receives a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; an external service interface is provided for the new knowledge graph to facilitate video recommendation service, accurate video associated data can be provided, the relation between videos can be accurately described, the relation value in the knowledge graph is constructed, the video recommendation capability is provided, the use of a user is facilitated in practical application, and the user perception is improved.
An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method for constructing a knowledge graph based on video subtitles in any of the above-mentioned method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring a video entity uploaded by a user, and extracting video subtitles according to the video;
acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group;
and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
In an alternative, the executable instructions cause the processor to:
forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set;
performing word segmentation operation on the distributed data set to obtain word data after word segmentation;
performing secondary interference processing on the acquired word data;
and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
In an alternative, the executable instructions cause the processor to:
extracting first keyword data from the word data by adopting a first algorithm;
extracting second keyword data from the word data by adopting a second algorithm;
and combining the first keyword data and the second keyword data to form the keyword group.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
Yet another computer program product according to an embodiment of the present invention includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method for constructing a video caption-based knowledge graph according to any of the above-mentioned method embodiments.
The executable instructions may be specifically configured to cause the processor to:
receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity;
calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base;
determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph;
and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
In an alternative, the executable instructions cause the processor to:
calculating the first relationSemantic similarity P between any keyword in the keyword group and any keyword in the second keyword groupi；
According to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
wherein i is a positive integer, n is the number of the keywords in the first keyword group, and m is the number of the keywords in the second keyword group.
In an alternative, the executable instructions cause the processor to:
if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association;
if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association;
if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related;
and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
The embodiment of the invention receives a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; an external service interface is provided for the new knowledge graph to facilitate video recommendation service, accurate video associated data can be provided, the relation between videos can be accurately described, the relation value in the knowledge graph is constructed, the video recommendation capability is provided, the use of a user is facilitated in practical application, and the user perception is improved.
Fig. 8 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the device.
As shown in fig. 8, the computing device may include: a processor (processor)802, a Communications Interface 804, a memory 806, and a communication bus 808.
Wherein: the processor 802, communication interface 804, and memory 806 communicate with one another via a communication bus 808. A communication interface 804 for communicating with network elements of other devices, such as clients or other servers. The processor 802 is configured to execute the program 810, and may specifically perform relevant steps in the above-described method for constructing a knowledge graph based on video subtitles.
In particular, the program 810 may include program code comprising computer operating instructions.
The processor 802 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.
The memory 806 stores a program 810. The memory 806 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 810 may be specifically configured to cause the processor 802 to perform the following operations:
acquiring a video entity uploaded by a user, and extracting video subtitles according to the video;
acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group;
and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
In an alternative, the program 810 causes the processor to:
forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set;
performing word segmentation operation on the distributed data set to obtain word data after word segmentation;
performing secondary interference processing on the acquired word data;
and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
In an alternative, the program 810 causes the processor to:
extracting first keyword data from the word data by adopting a first algorithm;
extracting second keyword data from the word data by adopting a second algorithm;
and combining the first keyword data and the second keyword data to form the keyword group.
The embodiment of the invention obtains the video entity uploaded by the user and extracts the video subtitle according to the video; acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group; and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase, and constructing a new knowledge graph, so that the video category and the theme can be accurately positioned, accurate video classification data is provided, accurate video associated data is provided, and video recommendation capability is provided.
Fig. 9 is a schematic structural diagram of another computing device provided in an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the device.
As shown in fig. 9, the computing device may include: a processor 902, a communication interface 904, a memory 906, and a communication bus 908.
Wherein: the processor 902, communication interface 904, and memory 906 communicate with one another via a communication bus 908. A communication interface 904 for communicating with network elements of other devices, such as clients or other servers. The processor 902 is configured to execute the program 910, and may specifically perform relevant steps in the above-described method for constructing a knowledge graph based on video subtitles.
In particular, the program 910 may include program code that includes computer operating instructions.
The processor 902 may be a central processing unit CPU, or a specific integrated circuit ASIC, or one or various integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.
A memory 906 for storing a program 910. The memory 906 may comprise high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.
The program 910 may specifically be configured to cause the processor 902 to perform the following operations:
receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity;
calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base;
determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph;
and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
In an alternative, the program 910 causes the processor to:
calculating semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword groupi；
According to the semantic similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
wherein i is a positive integer, n is the number of the keywords in the first keyword group, and m is the number of the keywords in the second keyword group.
In an alternative, the program 910 causes the processor to:
if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association;
if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association;
if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related;
and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
The embodiment of the invention receives a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity; calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base; determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph; an external service interface is provided for the new knowledge graph to facilitate video recommendation service, accurate video associated data can be provided, the relation between videos can be accurately described, the relation value in the knowledge graph is constructed, the video recommendation capability is provided, the use of a user is facilitated in practical application, and the user perception is improved.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A knowledge graph construction method based on video subtitles is characterized by comprising the following steps:
acquiring a video entity uploaded by a user, and extracting video subtitles according to the video;
acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group;
and transmitting a data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
2. The method according to claim 1, wherein the obtaining the keywords of the video entity according to the video entity and the video caption to form a keyword group comprises:
forming a distributed data set by the video entity identification, the video entity name and the video caption, and preprocessing the distributed data set;
performing word segmentation operation on the distributed data set to obtain word data after word segmentation;
performing secondary interference processing on the acquired word data;
and extracting the key words of the video entity from the word data after the secondary interference processing to form the key word group.
3. The method according to claim 2, wherein said extracting the keywords of the video entity from the word data after the secondary interference processing to form the keyword group comprises:
extracting first keyword data from the word data by adopting a first algorithm;
extracting second keyword data from the word data by adopting a second algorithm;
and combining the first keyword data and the second keyword data to form the keyword group.
4. A knowledge graph construction method based on video subtitles is characterized by comprising the following steps:
receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity;
calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge base;
determining the entity relationship between the first video entity and the second video entity according to the similarity, and constructing a new knowledge graph;
and providing an external service interface for the new knowledge graph to facilitate video recommendation service.
5. The method of claim 4, wherein the calculating the similarity between the first keyword group and a second keyword group corresponding to a second video entity in the original knowledge-graph comprises:
calculating semantic similarity P between any keyword in the first keyword group and any keyword in the second keyword groupi；
According to whatSense similarity PiCalculating the similarity P of the first key phrase and the second key phrase by applying the following relational expression:
wherein i is a positive integer, n is the number of the keywords in the first keyword group, and m is the number of the keywords in the second keyword group.
6. The method of claim 4, wherein determining the entity relationship between the first video entity and the second video entity according to the similarity comprises constructing a new knowledge graph, including:
if the similarity between the first key phrase and the second key phrase is greater than or equal to a first threshold, determining that the entity relationship between the first video entity and the second video entity is strong association;
if the similarity between the first keyword group and the second keyword group is smaller than the first threshold and is larger than or equal to a second threshold, determining that the entity relationship between the first video entity and the second video entity is weak association;
if the similarity between the first keyword group and the second keyword group is smaller than the second threshold, determining that the entity relationship between the first video entity and the second video entity is not related;
and adding a new node in the original knowledge graph, and establishing the bidirectional relationship between the first video entity and the second video entity.
7. A knowledge graph construction apparatus based on video subtitles, the apparatus comprising:
the caption extracting unit is used for acquiring a video entity uploaded by a user and extracting video captions according to the video;
the keyword acquisition unit is used for acquiring keywords of the video entity according to the video entity and the video caption to form a keyword group;
and the sending unit is used for transmitting the data set consisting of the video entity identification, the video entity name and the key phrase to a server end so as to acquire the entity relationship between the video entity and other video entities in the knowledge graph according to the key phrase and construct a new knowledge graph.
8. A knowledge graph construction apparatus based on video subtitles, the apparatus comprising:
the receiving unit is used for receiving a data set of a first video entity uploaded by a user side, wherein the data set comprises a first video entity identifier, a first video entity name and a first keyword group extracted according to the first video entity;
the calculating unit is used for calculating the similarity between the first key phrase and a second key phrase corresponding to a second video entity in the original knowledge graph;
the map construction unit is used for determining the entity relationship between the first video entity and the second video entity according to the similarity and constructing a knowledge map;
and the interface service unit is used for providing an external service interface for the knowledge graph so as to facilitate video recommendation service.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the video caption-based knowledge-graph construction method according to any one of claims 1-3 or 4-6.
10. A computer storage medium having stored therein at least one executable instruction that causes a processor to perform the steps of the video subtitle-based knowledge-graph construction method according to any one of claims 1-3 or 4-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010450442.1A CN113722540A (en) | 2020-05-25 | 2020-05-25 | Knowledge graph construction method and device based on video subtitles and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010450442.1A CN113722540A (en) | 2020-05-25 | 2020-05-25 | Knowledge graph construction method and device based on video subtitles and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113722540A true CN113722540A (en) | 2021-11-30 |
Family
ID=78671676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010450442.1A Pending CN113722540A (en) | 2020-05-25 | 2020-05-25 | Knowledge graph construction method and device based on video subtitles and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113722540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11928145B1 (en) | 2022-12-09 | 2024-03-12 | International Business Machines Corporation | Creating a knowledge graph for a video |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462507A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on movie songs |
| CN108829893A (en) * | 2018-06-29 | 2018-11-16 | 北京百度网讯科技有限公司 | Determine method, apparatus, storage medium and the terminal device of video tab |
| CN109189938A (en) * | 2018-08-31 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Method and apparatus for updating knowledge mapping |
| CN109800431A (en) * | 2019-01-23 | 2019-05-24 | 中国科学院自动化研究所 | Event information keyword extracting method, monitoring method and its system and device |
| CN109804364A (en) * | 2016-10-18 | 2019-05-24 | 浙江核新同花顺网络信息股份有限公司 | Knowledge mapping constructs system and method |
| CN109906611A (en) * | 2016-03-16 | 2019-06-18 | 尼尔森（美国）有限公司 | Characteristic spectrum for content characteristic map is laid out |
| CN110245259A (en) * | 2019-05-21 | 2019-09-17 | 北京百度网讯科技有限公司 | The video of knowledge based map labels method and device, computer-readable medium |
| CN110543574A (en) * | 2019-08-30 | 2019-12-06 | 北京百度网讯科技有限公司 | knowledge graph construction method, device, equipment and medium |
| JP2019212308A (en) * | 2018-06-01 | 2019-12-12 | ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ | Video service providing method and service server using the same |
-
2020
- 2020-05-25 CN CN202010450442.1A patent/CN113722540A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462507A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on movie songs |
| CN109906611A (en) * | 2016-03-16 | 2019-06-18 | 尼尔森（美国）有限公司 | Characteristic spectrum for content characteristic map is laid out |
| CN109804364A (en) * | 2016-10-18 | 2019-05-24 | 浙江核新同花顺网络信息股份有限公司 | Knowledge mapping constructs system and method |
| JP2019212308A (en) * | 2018-06-01 | 2019-12-12 | ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ | Video service providing method and service server using the same |
| CN108829893A (en) * | 2018-06-29 | 2018-11-16 | 北京百度网讯科技有限公司 | Determine method, apparatus, storage medium and the terminal device of video tab |
| CN109189938A (en) * | 2018-08-31 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Method and apparatus for updating knowledge mapping |
| CN109800431A (en) * | 2019-01-23 | 2019-05-24 | 中国科学院自动化研究所 | Event information keyword extracting method, monitoring method and its system and device |
| CN110245259A (en) * | 2019-05-21 | 2019-09-17 | 北京百度网讯科技有限公司 | The video of knowledge based map labels method and device, computer-readable medium |
| CN110543574A (en) * | 2019-08-30 | 2019-12-06 | 北京百度网讯科技有限公司 | knowledge graph construction method, device, equipment and medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11928145B1 (en) | 2022-12-09 | 2024-03-12 | International Business Machines Corporation | Creating a knowledge graph for a video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10559301B2 (en) | Generating topic-specific language models | |
| CN110543574B (en) | Knowledge graph construction method, device, equipment and medium | |
| US10642938B2 (en) | Artificial intelligence based method and apparatus for constructing comment graph | |
| KR102455616B1 (en) | Theme classification method based on multimodality, device, apparatus, and storage medium | |
| US10896212B2 (en) | System and methods for automating trademark and service mark searches | |
| KR101721338B1 (en) | Search engine and implementation method thereof | |
| CN103324665B (en) | Hot spot information extraction method and device based on micro-blog | |
| US7421418B2 (en) | Method and apparatus for fundamental operations on token sequences: computing similarity, extracting term values, and searching efficiently | |
| Al-Kabi et al. | An opinion analysis tool for colloquial and standard Arabic | |
| US20100287162A1 (en) | method and system for text summarization and summary based query answering | |
| US10437894B2 (en) | Method and system for app search engine leveraging user reviews | |
| KR20160057475A (en) | System and method for actively obtaining social data | |
| CN111506831A (en) | Collaborative filtering recommendation module and method, electronic device and storage medium | |
| CN109460499A (en) | Target search word generation method and device, electronic equipment, storage medium | |
| Bergamaschi et al. | Comparing topic models for a movie recommendation system | |
| CN110717038B (en) | Object classification method and device | |
| CN113722540A (en) | Knowledge graph construction method and device based on video subtitles and computing equipment | |
| US20200081923A1 (en) | Data search method and data search system thereof | |
| US9305103B2 (en) | Method or system for semantic categorization | |
| CN114255067A (en) | Data pricing method and device, electronic equipment and storage medium | |
| Aramini et al. | Automatic Illustration of Short Texts via Web Images. | |
| Koorathota et al. | Editing like humans: a contextual, multimodal framework for automated video editing | |
| CN110610001A (en) | Short text integrity identification method and device, storage medium and computer equipment | |
| Muraoka et al. | Visual Concept Naming: Discovering Well-Recognized Textual Expressions of Visual Concepts | |
| CN108664508B (en) | Information pushing method and device |
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 |