CN112749347A - Social content processing method and device, computing equipment and storage medium - Google Patents
Social content processing method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN112749347A CN112749347A CN202010505169.8A CN202010505169A CN112749347A CN 112749347 A CN112749347 A CN 112749347A CN 202010505169 A CN202010505169 A CN 202010505169A CN 112749347 A CN112749347 A CN 112749347A
- Authority
- CN
- China
- Prior art keywords
- content
- social
- published
- social content
- drama
- 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.)
- Granted
Links
- 238000003860 storage Methods 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 56
- 230000001960 triggered effect Effects 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 52
- 238000004891 communication Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 14
- 239000013598 vector Substances 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 230000000903 blocking effect Effects 0.000 description 11
- 230000004888 barrier function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000000873 masking effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 229920001621 AMOLED Polymers 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 238000012546 transfer 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a social content processing method, a social content processing device, a computing device and a storage medium, which are used for carrying out pivot identification and shielding on social content on a social platform and improving the accuracy of the pivot identification and shielding. The method comprises the following steps: receiving a pivot shielding request triggered through an interface of a target account in a social platform, and acquiring corresponding published pivot content according to pivot key information in the pivot shielding request; when target social content published to the social platform is obtained, determining semantic similarity between the target social content and the published pivot content; and pushing the target social content to the target account when the semantic similarity meets the set condition.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a social content processing method and apparatus, a computing device, and a storage medium.
Background
Currently, along with the playing of a part of drama, when a user chase a drama in a dispute, various social media and short video platforms are also accompanied with various drama introductions, movie and drama fragment cutting and drama content. For a user who traces a later episode, it may not be desirable to see the relevant introduction of the not yet viewed episode part on various social platforms, i.e. the user may not wish to be drew through, for which reason it is necessary to consider the need that the user does not want to see the "drew through" information in the social scenario.
Therefore, how to identify and mask the drama content in the social platform is a problem to be solved.
Disclosure of Invention
The embodiment of the application provides a social content processing method and device, a computing device and a storage medium, which are used for performing pivot identification and shielding on social content on a social platform, and improving the accuracy of the pivot identification and shielding.
In one aspect, a method for social content processing is provided, the method comprising:
receiving a pivot shielding request triggered through an interface of a target account in a social platform, and acquiring corresponding published pivot content according to pivot key information in the pivot shielding request;
when target social content published to the social platform is obtained, determining semantic similarity between the target social content and the published pivot content;
and pushing the target social content to the target account when the semantic similarity meets the set condition.
In one aspect, a method for social content processing is provided, the method comprising:
responding to a spoiler shielding operation triggered by spoiler key information input in an interface of a target account in a social platform, and sending a spoiler shielding request to a server, wherein the spoiler shielding request comprises the spoiler key information;
obtaining social content pushed by the server, wherein the social content at least comprises pivot social content, and semantic similarity between the pivot social content and published pivot content corresponding to the pivot key information meets a set condition;
and displaying the social content in a set display mode.
In one aspect, a social content processing apparatus is provided, the apparatus comprising:
a receiving module, configured to receive a spoiler shielding request triggered through an interface of a target account in a social platform;
an obtaining module, configured to obtain the published pivot content according to the pivot key information in the pivot shielding request;
the determining module is used for determining semantic similarity between the target social content and the published drama content when the target social content published to the social platform is obtained;
and the processing module is used for pushing the target social content to the target account when the semantic similarity meets the set condition.
Optionally, the determining module is further configured to:
before determining semantic similarity between the target social content and the published drama-through content, obtaining a drama-through potential keyword associated with the drama-through key information, and determining that the target social content contains the drama-through potential keyword.
Optionally, the disclosed pivot content includes a plurality of pieces, each piece of the disclosed pivot content corresponds to a first similarity threshold, and the similarity threshold corresponding to each piece of the disclosed pivot content is determined according to the pivot degree of the disclosed pivot content; the determination module is to: respectively determining semantic similarity between the target social content and each piece of published drama content;
the processing module is used for: and determining that the semantic similarity between each piece of the published dramatic-through content and the target social content is lower than a first similarity threshold corresponding to the published dramatic-through content.
Optionally, the processing module is further configured to: if the published drama-through content exists, wherein the semantic similarity between the published drama-through content and the target social content is larger than the corresponding first similarity threshold, determining the weight of each piece of published drama-through content according to the association degree of each piece of published drama-through content and the drama-through key information, and determining that the comprehensive similarity determined according to the semantic similarity of each piece of published drama-through content and the corresponding weight is smaller than a second similarity threshold.
Optionally, the processing module is further configured to:
when the semantic similarity does not meet the set condition, the target social content is prohibited from being pushed to the target account; or,
and when the semantic similarity does not meet the set condition, pushing the target social content to the target account so that the target account displays the target social content according to a set display mode.
In one aspect, a social content processing apparatus is provided, the apparatus comprising:
the response module is used for responding to a spoiler shielding operation triggered by spoiler key information input in an interface of a target account in the social platform and sending a spoiler shielding request to the server, wherein the spoiler shielding request comprises the spoiler key information;
an obtaining module, configured to obtain social content pushed by the server, where the social content includes at least one of a cut-through social content and a non-cut-through social content, and a semantic similarity between the cut-through social content and a published cut-through content corresponding to the cut-through key information satisfies a set condition;
the display module is used for displaying the social content in a set display mode, wherein when the social content comprises the pivot social content, the display effect of the pivot social content is different from that of the non-pivot social content.
In one aspect, a computing device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the method for processing social content described in the above various possible implementations includes the steps.
In one aspect, a storage medium is provided, which stores computer-executable instructions for causing a computer to perform the steps included in the social content processing method described in the above-mentioned various possible implementations.
In one aspect, a computer program product containing instructions is provided, which when run on a computer causes the computer to perform the steps included in the social content processing method described in the above various possible implementations.
In the embodiment of the application, the semantic similarity between the social content published in real time and the published drama content can be used as a judgment basis for judging whether the published social content is the drama content or not, because the published drama content is definitely the drama content, the probability that the content with the semantic similarity is the drama content is also higher, the judgment of the drama content is more accurate in a semantic similarity comparison mode, the actual semantic meaning of the target social content can be accurately obtained in the semantic similarity comparison mode, the actual semantic meaning comprises literal semantic meaning and potential semantic meaning, the literal semantic meaning is generally embodied by words included in the target social content, the potential semantic meaning can further embody the semantic relation among the words, and therefore, the drama content comprising the explicit drama key word can be effectively identified, and the implicit perspective content which does not comprise the explicit perspective key words can be effectively identified, so that the effectiveness and the accuracy of identifying the perspective content are improved, the effectiveness of the perspective shielding is further improved, and the effect of the perspective shielding is enhanced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only the embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic diagram of an application scenario applicable to the embodiment of the present application;
FIG. 2 is a flow chart of a social content processing method in an embodiment of the present application;
fig. 3 is a schematic diagram illustrating mining of pivot keywords in an embodiment of the present application;
fig. 4 is a schematic diagram of a short video scenario of a movie;
FIG. 5 is another flow chart of a social content processing method in an embodiment of the present application;
FIG. 6 is another flow diagram of a social content processing method in an embodiment of the present application;
FIG. 7 is a block diagram illustrating a social content processing apparatus according to an embodiment of the present disclosure;
FIG. 8 is another block diagram of a social content processing apparatus in an embodiment of the present application;
FIG. 9 is a schematic structural diagram of a computing device in an embodiment of the present application;
fig. 10 is another schematic structural diagram of a computing device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by one of ordinary skill in the art from the embodiments given herein without making any creative effort, shall fall within the scope of the claimed protection. In the present application, the embodiments and features of the embodiments may be arbitrarily combined with each other without conflict. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.
The terms "first" and "second" in the description and claims of the present application and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the term "comprises" and any variations thereof, which are intended to cover non-exclusive protection. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. The "plurality" in the present application may mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document generally indicates that the preceding and following related objects are in an "or" relationship unless otherwise specified.
Some technical terms referred to herein are explained below to facilitate understanding by those skilled in the art.
1. The social platform can be understood as a content production and exchange platform based on user relationships on the internet, and users can publish information on the social platform to realize information sharing. For example, may include an instant messaging platform, a short video platform, a movie screenplay platform, and the like.
2. The social content may be understood as information published on the social platform, and the user may apply for an account on each social platform, and further publish the social content in the social platform through each account, so as to implement information sharing among each social account. Social content may include personal information posted by a user (e.g., life dynamics), content of comments made by the user with respect to certain information, and so forth.
3. For drama, for already played movie or multimedia information such as a released fiction, a user who traces a later episode may not see the latest played part, and the part of the drama that the user has not watched forms a "drama" for the user, especially some key dramas, and if the user is drama, the novelty of watching is reduced, and the motivation for continuing watching may be lost.
4. Word2Vec, a Word vector computation model proposed by Google. The computational model is a shallow, two-layer neural network that is trained to reconstruct linguistic word text. The network is represented by words and the input words in adjacent positions are guessed, and the order of the words is unimportant under the assumption of the bag-of-words model in word2 vec. After training is completed, the word2vec model can be used to map each word to a vector, which can be used to represent the word-to-word relationship, and the vector is a hidden layer of the neural network. The significance of word vectors is to convert natural language into a vector that can be understood by a computer.
As described above, in order to avoid being "series-broken", the user's requirement for blocking series-broken content in a social scenario is strong, for example, "series a" has been played to the 10 th episode on the internet, but a user sees the 1 st episode later in the series, but the user does not want to be "series-broken", so the user wants the social platform to block the related series-broken content of "series a", so the user can watch "series a" at any time according to his own watching schedule, keep a new series mood, and continuously watch "series a". Therefore, there is a need for effective identification and screening of the pivot content in the social platform to meet the viewing needs of the user as much as possible. Two processing modes for the drama-through content are provided in the related art.
The first way is to type a word similar to "XXX series" in the social content, where "XXX" represents, for example, a movie title, i.e., "series" is marked as an explicit keyword for identifying the series, and the user needs to skip quickly to avoid being "series" if seeing the explicit word when browsing the social content. In this way, the explicit "pivot" words are presented in the same way as other non-pivot content, and the user needs to see the two words "pivot" to know that the words are pivot content, so that the pivot content is still seen to a large extent, so the pivot masking method is poor in effect.
Second, the system may filter the perspective content based on the perspective keywords included in the perspective content, i.e., provide functionality to block content including certain perspective keywords from view. However, in this approach, explicit filtering is performed according to the perspective keywords explicitly existing in the social content, and only the explicit inclusion of the perspective keywords in the social content masks the social content, however, in practice, some social content may not explicitly include the perspective keywords, but actually implicitly indicates the social content, or some social content may not actually be true perspective content even if the explicit inclusion of the perspective keywords is performed. Therefore, the accuracy of the perspective identification by using the method is low, some non-perspective contents may be mistakenly shielded, some perspective contents may be missed and not shielded, the accuracy and the effectiveness of shielding the perspective contents are also low, and the perspective shielding effect is poor.
In view of this, the embodiment of the present application provides a technical solution for effectively identifying and shielding the pivot content in the social context, and specifically, the social content (for example, referred to as target social content) published to the social platform and the pivot content (for example, referred to as published pivot content) published and published on the network are subjected to semantic similarity calculation to obtain semantic similarity between the two, and then the obtained semantic similarity is measured to determine whether the target social content published in real time is the pivot content, for example, when the semantic similarity satisfies a set condition, it indicates that the target social content is not the pivot content, so that the target social content can be pushed to the user, and when the semantic similarity does not satisfy the set condition, it can be considered as the pivot content, and further, the pivot shielding processing can be performed on the pivot content.
That is to say, the semantic similarity between the social content published in real time and the published drama content can be used as a basis for determining whether the published social content is the drama content, because the published drama content is definitely the drama content, the probability that the content with the semantic similarity is the drama content is also higher, the determination of the drama content is more accurate by comparing the semantic similarities, the actual semantic similarity can accurately obtain the actual semantic meaning of the target social content, the actual semantic meaning includes literal semantic meaning and potential semantic meaning, the literal semantic meaning is generally embodied by words included in the target social content, and the potential semantic meaning can embody the semantic relationship between the words, so that not only the drama content including the explicit drama keyword can be effectively identified, but also the implicit drama content not including the explicit drama keyword can be effectively identified, therefore, the effectiveness and the accuracy of identifying the perspective content are improved, the effectiveness of the perspective shielding is further improved, and the effect of the perspective shielding is enhanced.
In order to better understand the technical solution provided by the embodiment of the present application, some brief descriptions are provided below for application scenarios to which the technical solution provided by the embodiment of the present application is applicable, and it should be noted that the application scenarios described below are only used for illustrating the embodiment of the present application and are not limited. In specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.
Referring to fig. 1, fig. 1 is an application scenario applicable to the embodiment of the present application, where the application scenario includes a plurality of terminal devices (i.e., a terminal device 101, a terminal device 102, and a terminal device 103) and a server 104, and each terminal device may communicate with the server 104, for example, directly or indirectly connect through a wired or wireless communication manner, which is not limited in the present application. The terminal device 101, the terminal device 102, and the terminal device 103 have clients corresponding to the same social application installed therein, and the server 104 is a service device providing a background service for the social application. Each of the terminal device 101, the terminal device 102, and the terminal device 103 has a social account allocated in a social platform corresponding to the social application, and users of the terminal device 101, the terminal device 102, and the terminal device 103 may log in the respective social account to publish social content, and assume that the social accounts in the terminal device 101, the terminal device 102, and the terminal device 103 are social friends. For example, the user 1 of the terminal device 101 may log in to his own account 1 to publish social content on the social platform, and the server 104 may push the social content published by the user 1 to the account 2 corresponding to the terminal device 102 and the account 3 corresponding to the terminal device 103, so that the user 2 of the terminal device 102 may view the social content published by the user 1 through the account 2, and the user 3 of the terminal device 103 may also view the social content published by the user 1 through the account 3.
In this scenario, the user of each terminal device may input the spoiler key information on the interface of the respective social account to perform a spoiler operation, so as to trigger sending of a spoiler request to the server 104, where the spoiler request may be requested by the spoiler operation, for example, a toggle button of the spoiler may be set in the interface of the social account, and the user may request the spoiler or cancel the spoiler by turning on or off the toggle button. Taking the terminal device 101 as an example, the user 1 sends a drama perspective shielding request triggered by the account 1 in the terminal device 101 to the server 104, after receiving the drama perspective shielding request sent by the terminal device 101, the server 104 may identify whether the social content published by the account 2 in the terminal device 102 and the account 3 in the terminal device 103 is drama perspective content by using the social content processing method provided in the embodiment of the present application, and when it is determined that the published social content is drama perspective content associated with the drama perspective key information input by the user 1, it may perform shielding processing on the published social content to achieve effective shielding of drama perspective, and when it is determined that the published social content is non-drama perspective social content that is not associated with the drama perspective key information input by the user 1, it may be normally pushed to the account 1.
The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. The terminal devices 101, 102, 103 may be, but are not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart television, a smart wearable device, and the like.
To further illustrate the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operation steps as shown in the following embodiments or figures, more or less operation steps may be included in the method based on the conventional or non-inventive labor. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application. The method can be executed in sequence or in parallel according to the method shown in the embodiment or the figure when the method is executed in an actual processing procedure or a device.
The embodiment of the present application provides a social content processing method, which may be performed by a server, for example, the server 104 in fig. 1. The social content processing method provided by the embodiment of the application is shown in fig. 2, and the flowchart shown in fig. 2 is described as follows.
Step 201: a pivot mask request triggered through an interface of a target account in a social platform is received.
When a user wishes to system block a series, the series key information may be input in an interface (i.e. a client interface) of an account (e.g. called a target account) in the social platform, the operation of inputting the series key information may be regarded as a series blocking operation, according to the series blocking operation, the terminal device may generate a series blocking request including the series key information, that is, the series blocking request may be triggered in the interface of the target account in the social platform, and the series blocking request may include series-related key information that needs to be blocked.
In a specific implementation, a "barrier movie" button or control may be set in the client interface, and may be referred to as a "movie show switch", and when the user wishes to have the movie show blocked, the "movie show switch" may be turned on, and after the "movie show switch" is turned on, an input box for receiving the content to be blocked may be displayed, and the user may input the related information of the movie show to be blocked in the input box, which is referred to as "movie show key information" in this embodiment, and the movie show key information may include, for example, one or a combination of movie show names, movie angle names, actor names, movie scenes, and the playing schedules of the movie shows, where the movie show scenes are scenarios such as "XX and YY are together", "XX dies", "XX first-time YY", and the like, where "XX" and "YY" may be the names of the roles in the movie.
Further, the terminal device may send the obtained spoiler shielding request to a server corresponding to the social platform, and the server may receive the spoiler shielding request sent by the terminal device and analyze the spoiler key information in the spoiler shielding request.
Step 202: and acquiring the published drama content according to the drama key information in the drama shield request.
The system may crawl information such as an actor list, scenario information, and cast of an existing movie and television play on platforms such as mainstream video websites or movie review websites, for example, as shown in fig. 3, through an open-source crawler tool (such as script), so that keywords such as an actor list, a role list, a place name in a play, a movie and television play scene of an existing movie and television play may be obtained, and in summary, the method includes:
a) the contents of two fields, "lead actor" and "diversity scenario" as in fig. 3 are extracted using an open source structured extraction tool. Where the names of people in the lead actor field may directly become part of the potential perspective key.
b) Another part of the keywords are character names in the scenarios, and can be mined from texts introduced by the diversity scenarios or the characters, which is equivalent to a human name Recognition task in Named Entity Recognition (NER), namely, the Named Entity Recognition is carried out on the texts introduced by the diversity scenarios or the characters to obtain the characters (namely, the character names) and the place names. For example, a scenario text corresponding to a episode of the episode may be subjected to word segmentation and name recognition by using a word segmentation device ictc of a chinese academy open source, where a name and a place name may be recognized by using a currently general named entity recognition technology, which is not limited in the embodiment of the present application.
The already published series content of each movie series may be crawled in advance from the network, for example, the already published series content may be referred to as published series content, for example, for movie series a and movie series B, the already published series content corresponding to movie series a and the already published series content corresponding to movie series B may be obtained in advance, that is, the already published series content corresponding to each movie series may be crawled in advance from the network, so that, after the server obtains the series blocking request, the already published series content directly including the series key information may be matched to the corresponding already published series content according to the series key information included therein, for example, the already published series content directly including the series key information may be determined as the already published series content associated with the series key information, or, more series key words may be obtained according to the series key information matching, for example, the series key information is a color name in a certain movie series, the matched pivot keywords may include names of movies, scenes of movies, names of places in movies, and the like, and thus, the published pivot contents including the matched pivot keywords are determined as the published pivot information associated with the pivot key information. In this way, the published drama content of each movie (or currently hot movie) can be obtained in advance to form a static published drama content library, and then the published drama content matching the key drama information can be directly searched from the static library, which is relatively efficient.
In another embodiment, after obtaining the pivot shielding request, the server may further crawl, in real time, the published pivot content associated with the pivot key information from the network according to the pivot key information included in the pivot shielding request, and the matching manner is the same as that described in the foregoing manner, which is not described herein again.
In a specific implementation, the disclosed episode content is, for example, a title of a short video episode of a movie, the short video episode generally being a key episode in the movie, the title of which can also roughly describe the content of the key episode. For example, as shown in fig. 4, fig. 4 shows three short video scenarios (i.e., short video scenario 1, short video scenario 2, and short video scenario 3 shown in fig. 4) of a movie series a, each short video scenario corresponding to a title, for example, the title of short video scenario 2 is "too abusive," XX is whited out, "XX, YY in fig. 4 may represent angular names in movie series a, or may also be actor names.
Step 203: and when the target social content published to the social platform is obtained, determining semantic similarity between the target social content and the published drama content.
After receiving the movie screening request, it may be determined that the user has a need to screen a movie, for example, related content of a movie, or related content of a character in the movie, or related content after a specified playing schedule (e.g., episode 2) of the movie, needs to be screened. In order to meet the spoilt shielding requirement of the user, after the social content (for example, social content published by other users) published on the social platform is obtained, the server may first determine whether the social content is spoilt content, if the spoilt content is determined, the server may perform shielding processing, and if the spoilt content is determined not, the server may normally push the spoilt content, that is, when the published social content is non-spoilt social content, the server normally pushes the spoilt content to the user.
After the drama barrier is determined to be performed, the drama barrier may be stopped when a trigger condition for canceling the drama barrier is met, and the trigger condition for not performing the drama barrier may be that a user performs an operation for canceling the drama barrier at the client, for example, the aforementioned "drama barrier switch" is turned off, or a preset time of the drama barrier is reached, or another trigger condition for triggering the stop of the drama barrier is also possible, which is not limited in the embodiment of the present application.
Once it is determined that the cut-through shielding needs to be performed, for all the social content posted on the social platform and possibly pushed to the target account, identification processing on whether the social content is cut-through social content is required, taking a piece of social content posted on the social platform as an example, assuming that the social content is referred to as target social content, semantic similarity between the target social content and the published cut-through content associated with the cut-through key information may be calculated, that is, semantic similarity between the two pieces of content, namely the target social content and the published cut-through content, may be determined. Since the published drama content is known and published drama content, the probability that the target social content is also the drama content is higher when the semantic similarity of the published drama content and the known drama content is higher, and whether the target social content is the drama content or not can be judged more accurately by calculating the similarity between the semantics of the published drama content and the target social content no matter whether the target social content explicitly comprises the drama keyword or not.
Before calculating the semantic similarity between the target social content and the published content, the perspective potential keywords associated with the perspective key information can be obtained, then whether the target social content contains the perspective potential keywords or not is judged, and the semantic similarity between the target social content and the published perspective content is further calculated when the target social content contains the perspective potential keywords. That is, before semantic similarity is performed, explicit perspective keywords may be used for determination, because according to the perspective identification method in the related art, as long as the target social content explicitly includes the perspective keywords, that is, the target social content explicitly includes the perspective keywords, the target social content is directly identified as the perspective content, but in practice, even if the target social content explicitly includes the perspective keywords, the target social content is not necessarily true perspective content, and for this situation, based on the comparison method of semantic similarity, a conclusion that the target social content is exactly whether the target social content is the perspective content or not can be obtained through double screening.
That is to say, whether the target social content is the pivot content or not may be roughly determined for the first time by determining whether the target social content explicitly includes the pivot keyword or not, and if so, the target social content may be indicated to a certain extent as the pivot content.
To calculate the semantic similarity of short texts, firstly, the word segmentation processing needs to be performed on the published drama content and the target social content respectively, and then a word2vec dictionary which is used for realizing the training of the full-scale drama content and all short video title contents and is related to the drama is used for vector representation. The similarity between two vectors can be calculated by using a currently general calculation method, for example, a commonly used calculation method is cosine similarity, which is measured by cosine similarity, and is introduced as follows:
cosine similarity, also called cosine similarity, is to evaluate the similarity of two vectors by calculating the cosine value of their included angle. Cosine similarity maps vectors into a vector space, such as the most common two-dimensional space, according to coordinate values. The cosine values range between [ -1,1], the closer the value is to 1, the closer the directions of the two vectors are represented; the closer they approach-1, the more opposite their direction; close to 0 means that the two vectors are nearly orthogonal, the most common application being to calculate text similarity. For two texts, two vectors can be established according to the words respectively included in the texts, and the similarity condition of the two texts in a statistical method, namely semantic similarity, can be known by calculating cosine values of the two vectors.
Step 204: and judging whether the semantic similarity meets a set condition.
Step 205: and when the semantic similarity meets the set conditions, pushing the target social content to the target account.
Step 206: and when the semantic similarity does not meet the set conditions, shielding the target social content against the target account.
In a specific implementation process, for example, when the semantic similarity between the target social content and the published drama content meets a set condition, it may be considered that the probability that the target social content is the drama content is low, and the target social content may be normally pushed to the target account as the non-drama social content, and certainly may be pushed to other accounts at the same time, or whether to push the target social content or not may be selected according to the shielding content of other accounts. When the semantic similarity between the target social content and the published drama content does not meet the set condition, the probability that the target social content is the drama content is high, at this time, the target social content can be determined to be the drama content, specifically, the drama content relative to the target account, because other accounts may not be the drama content, the target social content can be shielded, specifically, due to a shielding request initiated by the target account, the drama shielding processing can be performed only on the target account, that is, the target social content is shielded on the target account.
In the specific implementation, the processing manner of the penetration mask includes various ways, which are exemplified here. The first way of processing the penetration shielding is as follows: the situation that the play-through social content is pushed to the target account is forbidden, so that the target account cannot acquire the play-through social content and cannot display the play-through social content; the second way of the dramatic-penetration shielding processing is as follows: the spoiled social content is pushed to the target account, but the terminal corresponding to the target account needs to differently display the spoiled social content and the non-spoiled social content according to a set display mode, that is, the spoiled social content and the non-spoiled social content are required to be displayed differently.
In a specific implementation process, the semantic similarity between the target social content and the published drama content satisfies a set condition, which may mean that the semantic similarity between the two is smaller than a set similarity threshold, since the published drama content is already definitely the drama content, when the semantic similarity between the two is smaller than the similarity threshold, the probability that the target social content is the drama content is also small, therefore, the social content can be determined to be non-dramatic social content, and then pushed to the target account according to a normal pushing flow, and when the semantic similarity between the two is greater than or equal to the similarity threshold, that is, it can be considered that the aforementioned setting condition is not satisfied, indicating that the probability that the target social content is the pivot content is large, therefore, the target social content can be determined to be the pivot content at this time, and the pivot shielding processing can be further performed on the pivot content.
In general, the disclosed series of series.
Case 1: when the piece of published drama content associated with the drama perspective key information only includes one piece, for example, the piece of published drama perspective content is referred to as drama perspective content 1, the semantic similarity between the target social content and the drama perspective content 1 is S1, if the similarity threshold is K, if S1 < K, it is assumed that the set condition is satisfied, and the target social content is determined to be non-drama perspective social content and is pushed to the target account; if S1 is equal to or greater than K, it is considered that the setting condition is not satisfied, and the target social content is determined to be the pivot content and the masking process is performed.
Case 2: when the disclosed drama-through content associated with the drama-through key information includes a plurality of pieces, for example, three pieces of disclosed drama-through content, which are referred to as drama-through content 1, drama-through content 2, and drama-through content 3, respectively, the semantic similarity correspondence between the target social content and the drama-through content 1, 2, and 3 is S1, S2, S3. In case 2, there are two processing methods, which will be described in detail below.
First treatment method
Uniformly setting a same similarity threshold value for all the published drama content, for example, P, if the semantic similarity between the target social content and each piece of published drama content is smaller than the uniform similarity value, i.e., if S1 < P, S2 < P, and S3 < P, the set condition may be considered to be satisfied, and determining the target social content as non-drama social content and pushing the non-drama social content to the target account; if at least one of the semantic similarities between the target social content and the pieces of public pivot content is not less than the unified similarity value P, that is, at least one of S1, S2, and S3 is greater than or equal to P, the target social content is determined to be the pivot content and the masking process is performed assuming that the setting condition is not satisfied.
Generally, each piece of published drama-through content is semantically clear to be the drama-through content, and the same similarity threshold is set for all the published drama-through contents, so that the same similarity threshold is set for all the published drama-through contents, the similarity of the target social content and the plurality of pieces of published drama-through contents can be conveniently and rapidly compared in batches, and the comparison efficiency of the similarity is improved.
Second treatment method
Setting a differentiated similarity threshold for each piece of disclosed pivot content, specifically, configuring a first similarity threshold for each piece of disclosed pivot content, where the first similarity thresholds configured for each piece of disclosed pivot content are all different or may be partially the same, for example, the similarity threshold set for the pivot content 1 is Q1, the similarity threshold set for the pivot content 2 is Q2, and the similarity threshold set for the pivot content 3 is Q3, where Q1 is 0.9, Q2 is 0.8, and Q3 is 0.93, that is, the first similarity thresholds corresponding to each piece of disclosed pivot content are all different.
Wherein, the first similarity threshold corresponding to each piece of disclosed perspective content is determined according to the perspective degree of the disclosed perspective content, and the perspective degree of the disclosed perspective content can be determined by the condition of the explicit perspective keywords included therein, for example, according to the number and types of the included explicit perspective keywords, for example, a greater number of included explicit perspective keywords indicates a greater perspective degree; in another embodiment, for example, the degree of the disclosed drama-through content may be determined according to a tag of the disclosed drama-through content, and the tag may be a tag manually labeled by a user, or may be a tag extracted from evaluation information corresponding to the disclosed drama-through content; in still another embodiment, the degree of the disclosed drama-through content may be determined directly from the evaluation content of the already-disclosed drama-through content, or the like.
The higher the degree of the disclosed drama-through content is, indicating that the more the disclosed drama-through content is disclosed, the smaller the first similarity threshold value configured for the disclosed drama-through content may be, that is, the relationship between the first similarity threshold value and the degree of the disclosed drama-through content may be negatively correlated. For example, the degree of the drama-through content 2 described above is higher than the degree of the drama-through content 1, the similarity threshold Q2 (i.e., 0.8) of the drama-through content 2 is set smaller than the similarity threshold Q1 (i.e., 0.9) of the drama-through content 1, and thus, for social content that subsequently needs to be determined whether it is a drama content by semantic similarity, when semantic similarity comparisons are made with the perspective contents 1, 2 with corresponding first similarity thresholds respectively, the semantic similarity to the drama-through content 1 is considered slightly lower than the semantic similarity to the drama-through content 2, this is because the semantic similarity required to the drama-through content 1 with a higher degree of drama-through may be slightly lower than the drama-through content 2 with a lower degree of drama-through, and thus, the method can ensure the reference consistency when semantic similarity is compared, and ensure accurate comparison as much as possible so as to improve the accuracy of identifying the pivot content.
In another possible implementation manner, after all the published drama content is acquired, according to the actual drama content thereof, a corresponding first similarity threshold may be manually configured for the published drama content, and the accuracy is high.
In a second processing manner, how to determine whether the target social content is the pivot content by using the first similarity threshold configured corresponding to the plurality of pieces of published pivot content is described in detail below with reference to fig. 5.
Step 501: semantic similarity between the target social content and each piece of published pivot content is determined separately.
Continuing with the three pieces of published drama content 1, 2, and 3 as an example, the first similarity thresholds respectively set for the three pieces of published drama content are Q1, Q2, and Q3, and the semantic similarities between the target social content and the three pieces of published drama content are respectively represented by S1, S2, and S3.
Step 502: determining whether semantic similarity between each piece of published dramatic through content and the target social content is lower than a first similarity threshold corresponding to the published dramatic through content.
Continuing with the above example, it is judged: whether S1 is less than Q1 and S2 is less than Q2 and S3 is less than Q3, determine: whether S1 < Q1, S2 < Q2, S3 < Q3 are simultaneously established or not.
Step 503: and when the semantic similarity between each piece of published drama content and the target social content is lower than a first similarity threshold corresponding to the published drama content, determining that the set conditions are met, determining the target social content as non-drama social content, and pushing the target social content to the target account.
If the semantic similarity between each piece of published drama content and the target social content is lower than the first similarity threshold corresponding to the published drama content, that is, if the above-mentioned S1 < Q1, S2 < Q2, and S3 < Q3 are simultaneously established, it indicates that the semantic similarity between the target social content and any piece of published drama content is small, so that the probability that the target social content is the drama content is considered to be small, the target social content may be determined to be the non-drama social content and pushed to the target account, and the user may normally receive the non-drama social content.
The semantic similarity between each piece of public pivot content and the target social content is lower than the first similarity threshold corresponding to the piece of public pivot content, that is, among all the obtained semantic similarities between each piece of public pivot content and the target social content, at least one semantic similarity is greater than the first similarity threshold configured corresponding to the corresponding piece of public pivot content, that is, at least one of the three expressions S1 < Q1, S2 < Q2, and S3 < Q3 does not hold, which indicates that the setting condition is not satisfied.
When the above setting condition is not satisfied, that is, when the determination result of step 502 is negative, a possible embodiment may be implemented by executing step 504.
Step 504: and when the semantic similarity between each piece of published dramatic-transparent content and the target social content is not all lower than a first similarity threshold corresponding to the published dramatic-transparent content, determining that the set condition is not met, determining the target social content as the dramatic-transparent social content, and shielding the target social content against the target account.
When the above setting condition is not satisfied, that is, when the determination result in step 502 is negative, another possible embodiment may be implemented by performing steps 505 to 506, that is, further performing a double determination by using the second similarity threshold, which will be described in detail below.
Step 505: when the semantic similarity between each piece of published pivot content and the target social content is not all lower than a first similarity threshold corresponding to the published pivot content, determining the weight of each piece of published pivot content according to the association degree of each piece of published pivot content and pivot key information, and determining the comprehensive similarity according to the semantic similarity and the corresponding weight of each piece of published pivot content.
Therein, has been disclosedThe degree of association between the opening perspective content and the perspective key information can be determined by the content contact degree between the opening perspective content and the perspective key information, for example, a higher content contact degree indicates a greater degree of association, or a semantic similarity between the disclosed opening perspective content and the perspective key information can be calculated, a greater semantic similarity indicates a greater degree of association, or other ways can be used to measure the degree of association between the disclosed opening perspective content and the perspective key information. Further, the greater the degree of association, the closer the published drama content is to the drama key information submitted by the user, and the greater the corresponding weight may be. For example, the corresponding weights of the three pieces of published dramatic transparent content are a1、a2、a3,a1、a2、a3The sum of the three is 1, and then the comprehensive similarity S can be calculated according to the following formula: S-S1 × a1+S2×a2+S2×a3。
Step 506: and judging whether the comprehensive similarity is smaller than a second similarity threshold value.
The second similarity threshold may be an average of semantic similarities between each piece of published dramatic-transparent content and the target social content, or may be an average of semantic similarities of published dramatic-transparent contents, where the semantic similarities with the target social content are not lower than the corresponding first similarity threshold, or may be other values, and there is no inevitable size relationship between the second similarity threshold and the first similarity threshold, and the first similarity threshold and the second similarity threshold may be the same or different, which is not limited in this embodiment of the present application.
When the integrated similarity is smaller than the second similarity threshold, it may be determined that the setting condition is satisfied, and then the target social content is determined to be non-pivot social content, and the target social content is pushed to the target account, that is, the foregoing step 503 is executed.
When the integrated similarity is not less than (i.e., greater than or equal to) the second similarity threshold, it may be determined that the setting condition is not met, and then the target social content is determined to be the pivot social content, and the target social content is subjected to the masking process with respect to the target account, that is, the foregoing step 504 is performed.
That is, in the case of including a plurality of pieces of disclosed drama-through content, in the second processing manner, one possible setting condition is: semantic similarity between each piece of published dramatic-show content and the target social content is lower than a first similarity threshold corresponding to the published dramatic-show content; another possible setting condition is: the semantic similarity between at least one piece of published dramatic-transparent content and the target social content is not lower than a first similarity threshold corresponding to the published dramatic-transparent content, and the comprehensive similarity determined according to the semantic similarity and the corresponding weight of each piece of published content is larger than a second similarity threshold.
In the above embodiment, two different setting conditions are provided, which may increase the flexibility of the transparent recognition mode. In the second setting condition, through double judgment of the first similarity threshold and the second similarity threshold, the situation that the perspective content is missed to be identified can be avoided as much as possible, and the accuracy of the perspective content identification is improved.
In the embodiment of the application, not only can the pivot content comprising the dominant pivot keyword be effectively identified, but also the implicit pivot content not comprising the dominant pivot keyword can be effectively identified, so that the effectiveness and the accuracy of identifying the pivot content are improved, the effectiveness of pivot shielding is further improved, and the effect of pivot shielding is enhanced.
Based on the same inventive concept, please refer to fig. 6, an embodiment of the present application further provides a social content processing method, which may be executed by a client side, for example, by the terminal device 101, the terminal device 102, or the terminal device 103 in fig. 1, and a flowchart shown in fig. 6 is described as follows.
Step 601: a spoiler masking operation triggered by spoiler key information entered in an interface of a target account in a social platform is detected.
Step 602: in response to the spoiler operation, a spoiler request including spoiler key information is generated.
Step 603: and sending a perspective shielding request to the server.
And sending a drama mask request to the server so that the server screens whether the social content published to the social platform is dramatized or not according to the drama mask request.
Step 604: and acquiring social content pushed by the server.
After receiving the drama blocking request sent by the target account, the server may determine, according to the drama key information carried in the drama blocking request, whether the social content posted on the social platform is the drama social content in the manner described in fig. 2 to 4, specifically, determine whether semantic similarity between the posted social content and the published drama content corresponding to the drama key information satisfies a set condition. If the semantic similarity between the published social content and the published pivot content corresponding to the pivot key information meets a set condition, the published social content can be determined as non-pivot social content, and the server can push the non-pivot social content to a target account; if the semantic similarity between the published social content and the published drama content corresponding to the drama key information does not meet the set condition, the published social content can be determined to be the drama social content, and the server can perform shielding processing aiming at the target account. The detailed judgment process can be referred to the description of the foregoing embodiments, and will not be repeated here.
For the social content published to the social platform, the social content can be divided into the spoiled social content associated with the spoiled key information and the non-spoiled social content not associated with the spoiled key information through the spoiled key information, the non-spoiled social content can be pushed to the target account normally, so that the user can view the content normally, and the spoiled social content can be subjected to spoiled shielding processing. The first perspective shielding processing mode is as follows: the situation that the play-through social content is pushed to the target account is forbidden, so that the target account cannot acquire the play-through social content and cannot display the play-through social content; the second way of the dramatic-penetration shielding processing is as follows: the spoiled social content is pushed to the target account, but a terminal corresponding to the target account needs to differently display the spoiled social content and the non-spoiled social content according to a set display mode, for example, the spoiled social content and the non-spoiled social content are displayed with different display effects, so that the spoiled social content and the non-spoiled social content have different display effects.
Step 605: and displaying the acquired social content in a set display mode.
According to different modes of the perspective shielding processing of the server, the social content pushed by the server and acquired by the terminal may be different.
When the shielding processing mode of the server is the first spoiler shielding processing mode, the terminal device can only obtain the non-spoiler social content, and then the non-spoiler social content is displayed according to a normal display mode.
When the blocking processing mode of the server is the second spoiler blocking processing mode, the terminal device may acquire the non-spoiler social content and the spoiler social content at the same time, but may present the non-spoiler social content and the spoiler social content differently. One possible implementation manner is that non-perspective social content is normally displayed, and perspective social content is shielded or weakly displayed, for example, a shielding frame is marked on the perspective social content or a dark shading is added, so that a user generally cannot visually see the specific content included in the perspective social content, and further can view and shield the perspective content to a certain degree, or can perform differential display with certain transparency or obvious color, so that the user can clearly know which part is the perspective content when roughly browsing, and further can actively avoid the perspective content, and can remind and shield the sight of the user to a certain degree; another possible implementation is to present the non-spoilt social content normally, to prohibit the spoilt content from being presented, and not to display the spoilt content.
In the embodiment of the application, a user initiates a request for shielding the play through a target account, a server judges whether the social content published to a social platform is the play through social content or not based on the request, and judges whether the social content is the play through social content or not by comparing semantic similarity with the published play through content, so that the play through content comprising an explicit play through keyword can be effectively identified, the implicit play through content not comprising the explicit play through keyword can be effectively identified, the effectiveness and accuracy of identifying the play through content are improved, and therefore, the terminal can shield or strongly remind the user to a certain extent according to the effective identification of the play through social content by the server, and the user is prevented from being played through as much as possible.
Based on the same inventive concept, embodiments of the present application provide a social content processing apparatus, which may be a hardware structure, a software module, or a hardware structure plus a software module. The social content processing device is, for example, the server 104 in fig. 1 described above, or may be a functional device provided in the server 104. Referring to fig. 7, the social content processing apparatus in the embodiment of the present application includes a receiving module 701, an obtaining module 702, a determining module 703, and a processing module 704, where:
a receiving module 701, configured to receive a spoiler shielding request triggered through an interface of a target account in a social platform;
an obtaining module 702, configured to obtain the published drama content according to the drama key information in the drama shield request;
a determining module 703, configured to determine semantic similarity between a target social content and an already-published drama content when the target social content published to a social platform is obtained;
and the processing module 704 is configured to, when it is determined that the semantic similarity satisfies the set condition, push the target social content to the target account.
In a possible implementation, the determining module 703 is further configured to:
before determining semantic similarity between the target social content and the published drama-through content, obtaining the drama-through potential keywords associated with the drama-through key information, and determining that the target social content contains the drama-through potential keywords.
In one possible embodiment, the disclosed series content includes a plurality of pieces, each piece of the disclosed series content corresponds to a first similarity threshold, and the similarity threshold corresponding to each piece of the disclosed series content is determined according to the series degree of the disclosed series content; the determining module 703 is configured to: respectively determining semantic similarity between the target social content and each piece of published drama content;
the processing module 704 is configured to: and determining that the semantic similarity between each piece of the published dramatic-show content and the target social content is lower than a first similarity threshold corresponding to the published dramatic-show content.
In one possible implementation, the processing module 704 is further configured to: if the published drama-through content exists, wherein the semantic similarity between the published drama-through content and the target social content is larger than the corresponding first similarity threshold value, the weight of each piece of published drama-through content is determined according to the association degree of each piece of published drama-through content and the drama-through key information, and the comprehensive similarity determined according to the semantic similarity of each piece of published drama-through content and the corresponding weight is determined to be smaller than the second similarity threshold value.
In one possible implementation, the processing module 704 is further configured to:
when the semantic similarity does not meet the set conditions, the target social content is prohibited from being pushed to the target account; or when the semantic similarity does not meet the set condition, pushing the target social content to the target account so that the target account displays the target social content according to the set display mode.
All relevant contents of each step executed by the server in the embodiment of the social content processing method may be referred to in the functional description of the functional module corresponding to the social content processing apparatus in the embodiment of the present application, and are not described herein again.
Based on the same inventive concept, embodiments of the present application provide a social content processing apparatus, which may be a hardware structure, a software module, or a hardware structure plus a software module. The social content processing apparatus is, for example, the terminal device in fig. 1 described above, or may be a function apparatus provided in the terminal device. Referring to fig. 8, the social content processing apparatus in the embodiment of the present application includes a response module 801, an obtaining module 802, and a display module 803, where:
a response module 801, configured to send a spoiler shielding request to a server in response to a spoiler shielding operation triggered by spoiler key information input in an interface of a target account in a social platform, where the spoiler shielding request includes the spoiler key information;
an obtaining module 802, configured to obtain social content pushed by a server, where the social content at least includes a pivot social content, and a semantic similarity between the pivot social content and a published pivot content corresponding to the pivot key information satisfies a set condition;
the display module 803 is configured to display the social content in the set display mode.
All relevant contents of each step executed by the terminal device in the embodiment of the social content processing method may be referred to as a functional description of a functional module corresponding to the social content processing apparatus in the embodiment of the present application, and are not described herein again.
The division of the modules in the embodiments of the present application is schematic, and only one logical function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present application may be integrated in one processor, may also exist alone physically, or may also be integrated in one module by two or more modules. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Based on the same inventive concept, an embodiment of the present application provides a computing device, which may be, for example, the server 104 in fig. 1, as shown in fig. 9, where the computing device in the embodiment of the present application includes at least one processor 901, a memory 902 and a communication interface 903, where the memory 902 and the communication interface 903 are connected to the at least one processor 901, and a specific connection medium between the processor 901 and the memory 902 is not limited in the embodiment of the present application, and in fig. 9, the processor 901 and the memory 902 are connected by a bus 900 as an example, the bus 900 is represented by a thick line in fig. 9, and a connection manner between other components is merely schematically illustrated and is not limited. The bus 900 may be divided into an address bus, a data bus, a control bus, etc., and is shown with only one thick line in fig. 9 for ease of illustration, but does not represent only one bus or type of bus.
In the embodiment of the present application, the memory 902 stores instructions executable by the at least one processor 901, and the at least one processor 901 may execute the steps included in the foregoing method for recommending multimedia content by executing the instructions stored in the memory 902.
The processor 901 is a control center of the computing device, and may connect various parts of the entire computing device by using various interfaces and lines, and perform various functions and process data of the computing device by executing or executing instructions stored in the memory 902 and calling data stored in the memory 902, thereby performing overall monitoring on the computing device. Optionally, the processor 901 may include one or more processing units, and the processor 901 may integrate an application processor and a modem processor, where the processor 901 mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 901. In some embodiments, the processor 901 and the memory 902 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.
The processor 901 may be a general-purpose processor, such as a Central Processing Unit (CPU), a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, that may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method applied in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
The communication interface 903 is a transmission interface that can be used for communication, and can receive data or transmit data via the communication interface 903, for example.
With continued reference to FIG. 9, the computing device also includes a basic input/output system (I/O system) 904 for facilitating information transfer between various devices within the computing device, and a mass storage device 908 for storing an operating system 905, application programs 906, and other program modules 907.
The basic input/output system 904 includes a display 909 for displaying information and an input device 910 such as a mouse, keyboard, etc. for user input of information. Wherein a display 909 and an input device 910 are connected to the processor 901 via a basic input/output system 904 connected to the system bus 900. The basic input/output system 904 may also include an input/output controller for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, an input-output controller may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 909 is connected to the processor 901 through a mass storage controller (not shown) connected to the system bus 900. The mass storage device 908 and its associated computer-readable media provide non-volatile storage for the server package. That is, the mass storage device 908 may include a computer-readable medium (not shown), such as a hard disk or CD-ROM drive.
According to various embodiments of the invention, the computing device package may also be operated by a remote computer connected to the network through a network, such as the Internet. That is, the computing device may be connected to the network 911 via the communication interface 903 coupled to the system bus 900, or may be connected to another type of network or remote computer system (not shown) using the communication interface 903.
Based on the same inventive concept, the embodiment of the present application further provides a computing device, which is, for example, any one of the aforementioned terminal devices in fig. 1, such as terminal device 101, terminal device 102, or terminal device 103 in fig. 1. Referring to fig. 10, a computing device in this embodiment of the application includes at least one processor 1001 and a memory 1002 connected to the at least one processor, and a specific connection medium between the processor 1001 and the memory 1002 is not limited in this embodiment of the application, for example, the processor 1001 and the memory 1002 may be connected by a bus, and the bus may be divided into an address bus, a data bus, a control bus, and the like.
In the embodiment of the present application, the memory 1002 stores instructions executable by the at least one processor 1001, and the at least one processor 1001 may execute the steps included in the foregoing video processing method by executing the instructions stored in the memory 1002.
The Processor 1001 may be a general-purpose Processor, such as a Central Processing Unit (CPU), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic blocks disclosed in the embodiments of the present Application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor.
The processor 1001 is a control center of the computing device, and may connect various parts of the entire computing device by using various interfaces and lines, and perform various functions of the computing device and process data by executing or executing instructions stored in the memory 1002 and calling data stored in the memory 1002, thereby performing overall monitoring of the computing device. Alternatively, the processor 1001 may include one or more processing units, and the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 1001. In some embodiments, the processor 1001 and the memory 1002 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.
Further, the computing device in this embodiment of the application may further include an input unit 1003, a display unit 1004, a radio frequency unit 1005, an audio circuit 1006, a speaker 1007, a microphone 1008, a Wireless Fidelity (WiFi) module 1009, a bluetooth module 1010, a power source 1011, an external interface 1012, an earphone jack 1013, and the like. Those skilled in the art will appreciate that FIG. 10 is merely exemplary of a computing device and is not intended to limit the computing device, which may include more or fewer components than those shown, or may combine certain components, or different components.
The input unit 1003 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computing device. For example, the input unit 1003 may include a touch screen 1014 and other input devices 1015. The touch screen 1014 may collect touch operations by a user (e.g., operations by a user on or near the touch screen 1014 using any suitable object such as a finger, a joint, a stylus, etc.), i.e., the touch screen 1014 may be used to detect touch pressure and touch input position and touch input area, and drive the corresponding connection device according to a preset program. The touch screen 1014 can detect a touch operation of the touch screen 1014 by a user, convert the touch operation into a touch signal and send the touch signal to the processor 1001, or understand that touch information of the touch operation can be sent to the processor 1001 and can receive and execute a command sent by the processor 1001. The touch information may include at least one of pressure magnitude information and pressure duration information. The touch screen 1014 may provide an input interface and an output interface between the computing device and the user. In addition, the touch screen 1014 can be implemented using various types, such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 1003 may include other input devices 1015 in addition to the touch screen 1014. For example, other input devices 1015 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 904 may be used to display information input by or provided to the user as well as various menus of the computing device. Further, the touch screen 1014 may overlay the display unit 1004 and, when the touch screen 1014 detects a touch operation thereon or nearby, transmit to the processor 1001 pressure information of the touch operation determined. In the present embodiment, the touch screen 1014 and the display unit 1004 may be integrated into one component to implement the input, output, and display functions of the computing device. For convenience of description, the embodiment of the present application is schematically illustrated by taking the touch screen 1014 as an example of the functional set of the touch screen 1014 and the display unit 1004, but of course, in some embodiments, the touch screen 1014 and the display unit 1004 may be taken as two separate components.
When the display unit 1004 and the touch panel are superimposed on each other in the form of layers to form the touch screen 1014, the display unit 1004 can function as an input device and an output device, and when functioning as an output device, can be used to display images, for example, to enable playing of various videos. The Display unit 1004 may include at least one of a Liquid Crystal Display (LCD), a Thin Film Transistor Liquid Crystal Display (TFT-LCD), an Organic Light Emitting Diode (OLED) Display, an Active Matrix Organic Light Emitting Diode (AMOLED) Display, an In-Plane Switching (IPS) Display, a flexible Display, a 3D Display, and the like. Some of these displays may be configured to be transparent to allow a user to view from the outside, which may be referred to as transparent displays, and according to certain desired embodiments, the computing device may include two or more display units (or other display devices), e.g., the computing device may include an external display unit (not shown in fig. 10) and an internal display unit (not shown in fig. 10).
The rf unit 1005 may be used for transceiving information or receiving and transmitting signals during a call. Typically, the radio frequency circuitry includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. Further, the radio frequency unit 1005 may also communicate with a network device and other devices through wireless communication.
The audio circuitry 1006, speaker 1007, microphone 1008 can provide an audio interface between a user and a computing device. The audio circuit 1006 may transmit the converted electrical signal of the received audio data to the speaker 1007, and the converted electrical signal is converted into a sound signal by the speaker 1007 and output. On the other hand, the microphone 1008 converts the collected sound signals into electrical signals, which are received by the audio circuit 1006 and then converted into audio data, which are then processed by the audio data output processor 1001 and then transmitted to another computing device via the radio frequency unit 1005, or output to the memory 1002 for further processing, and the audio circuit may also include a headphone jack 1013 for providing a connection interface between the audio circuit and a headphone.
WiFi belongs to short-range wireless transmission technology, and the computing device can help the user send and receive e-mails, browse webpages, access streaming media, and the like through the WiFi module 1009, which provides wireless broadband internet access for the user. Although fig. 10 shows the WiFi module 1009, it is understood that it does not belong to the essential constitution of the computing device, and may be omitted entirely as needed within the scope not changing the essence of the invention.
Bluetooth is a short-range wireless communication technology. By using the bluetooth technology, the communication between mobile communication devices such as a palm computer, a notebook computer and a mobile phone can be effectively simplified, the communication between the devices and the Internet (Internet) can also be successfully simplified, the data transmission between the computing device and the Internet becomes faster and more efficient through the bluetooth module 1010 of the computing device, and the way is widened for wireless communication. Bluetooth technology is an open solution that enables wireless transmission of voice and data. Although fig. 10 shows the bluetooth module 1010, it is understood that it does not belong to the essential constitution of the computing device and may be omitted entirely as needed within the scope not changing the essence of the invention.
The computing device may also include a power source 1011 (such as a battery) for receiving external power or powering various components within the computing device. Preferably, the power source 1011 may be logically connected to the processor 1001 through a power management system, so that functions of managing charging, discharging, and power consumption are implemented through the power management system.
The computing device may also include an external interface 1012, where the external interface 1012 may include a standard Micro USB interface, may also include a multi-pin connector, may be used to connect the computing device to communicate with other devices, and may also be used to connect a charger to charge the computing device.
Although not shown, the computing device in the embodiment of the present application may further include a camera, a flash, and other possible functional modules, which are not described herein again.
Based on the same inventive concept, the present application also provides a storage medium, which may be a computer-readable storage medium, and the storage medium stores computer instructions, which, when executed on a computer, cause the computer to perform the steps of the social content processing method as described above.
Based on the same inventive concept, the present application also provides a storage medium, which may be a computer-readable storage medium, and the storage medium stores computer instructions, which, when executed on a computer, cause the computer to perform the steps of the social content processing method as described above.
Based on the same inventive concept, embodiments of the present application further provide a chip system, where the chip system includes a processor and may further include a memory, and is configured to implement the steps of the social content processing method as described above, or implement the steps of the social content processing method as described above. The chip system may be formed by a chip, and may also include a chip and other discrete devices.
In some possible implementations, various aspects of the social content processing method provided in the embodiments of the present application may also be implemented in the form of a program product including program code for causing a computer to perform the steps of the social content processing method according to various exemplary implementations of the present application described above when the program product runs on the computer.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A method for social content processing, the method comprising:
receiving a pivot shielding request triggered through an interface of a target account in a social platform, and acquiring published pivot content according to pivot key information in the pivot shielding request;
when target social content published to the social platform is obtained, determining semantic similarity between the target social content and the published pivot content;
and pushing the target social content to the target account when the semantic similarity meets the set condition.
2. The method of claim 1, wherein prior to determining the semantic similarity between the target social content and the published pivot content, the method further comprises:
and acquiring a perspective potential keyword associated with the perspective key information, and determining that the target social content comprises the perspective potential keyword.
3. The method of claim 1, wherein the disclosed series of; determining semantic similarity between the target social content and the published pivot content, comprising:
respectively determining semantic similarity between the target social content and each piece of published drama content;
correspondingly, determining that the semantic similarity meets a set condition includes:
and determining that the semantic similarity between each piece of the published dramatic-through content and the target social content is lower than a first similarity threshold corresponding to the published dramatic-through content.
4. The method of claim 3, wherein determining that the semantic similarity satisfies a set condition further comprises:
if the published drama-through content exists, wherein the semantic similarity between the published drama-through content and the target social content is larger than the corresponding first similarity threshold, determining the weight of each piece of published drama-through content according to the association degree of each piece of published drama-through content and the drama-through key information, and determining that the comprehensive similarity determined according to the semantic similarity of each piece of published drama-through content and the corresponding weight is smaller than a second similarity threshold.
5. The method of any of claims 1-4, wherein the method further comprises:
when the semantic similarity does not meet the set condition, the target social content is prohibited from being pushed to the target account; or,
and when the semantic similarity does not meet the set condition, pushing the target social content to the target account so that the target account displays the target social content according to a set display mode.
6. A method for social content processing, the method comprising:
responding to a spoiler shielding operation triggered by spoiler key information input in an interface of a target account in a social platform, and sending a spoiler shielding request to a server, wherein the spoiler shielding request comprises the spoiler key information;
obtaining social content pushed by the server, wherein the social content at least comprises pivot social content, and semantic similarity between the pivot social content and published pivot content corresponding to the pivot key information meets a set condition;
and displaying the social content in a set display mode.
7. An apparatus for social content processing, the apparatus comprising:
a receiving module, configured to receive a spoiler shielding request triggered through an interface of a target account in a social platform;
an obtaining module, configured to obtain the published pivot content according to the pivot key information in the pivot shielding request;
the determining module is used for determining semantic similarity between the target social content and the published drama content when the target social content published to the social platform is obtained;
and the processing module is used for pushing the target social content to the target account when the semantic similarity meets the set condition.
8. An apparatus for social content processing, the apparatus comprising:
the response module is used for responding to a spoiler shielding operation triggered by spoiler key information input in an interface of a target account in the social platform and sending a spoiler shielding request to the server, wherein the spoiler shielding request comprises the spoiler key information;
the obtaining module is used for obtaining social content pushed by the server, wherein the social content at least comprises a cut social content, and the semantic similarity between the cut social content and the published cut content corresponding to the cut key information meets a set condition;
and the display module is used for displaying the social content in a set display mode.
9. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps comprised by the method of any one of claims 1 to 5 or the steps comprised by the method of claim 6 when executing the computer program.
10. A storage medium storing computer-executable instructions for causing a computer to perform the steps comprised in the method of any one of claims 1 to 5 or to perform the steps comprised in the method of claim 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010505169.8A CN112749347B (en) | 2020-06-05 | 2020-06-05 | Social content processing method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010505169.8A CN112749347B (en) | 2020-06-05 | 2020-06-05 | Social content processing method and device, computing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112749347A true CN112749347A (en) | 2021-05-04 |
CN112749347B CN112749347B (en) | 2023-12-22 |
Family
ID=75645236
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010505169.8A Active CN112749347B (en) | 2020-06-05 | 2020-06-05 | Social content processing method and device, computing equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112749347B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930401A (en) * | 2016-04-15 | 2016-09-07 | 乐视控股(北京)有限公司 | Episode comment information screening method and apparatus |
CN105930403A (en) * | 2016-04-18 | 2016-09-07 | 苏州寅初信息科技有限公司 | Big data based film comment screening method |
CN106210770A (en) * | 2016-07-11 | 2016-12-07 | 北京小米移动软件有限公司 | A kind of method and apparatus showing barrage information |
CN108471541A (en) * | 2018-02-01 | 2018-08-31 | 北京奇艺世纪科技有限公司 | A kind of method and device that video barrage is shown |
CN110099306A (en) * | 2018-01-29 | 2019-08-06 | 优酷网络技术(北京)有限公司 | A kind of processing of comment information, display methods, client and server |
CN110166802A (en) * | 2019-05-06 | 2019-08-23 | 腾讯科技(深圳)有限公司 | Barrage processing method, device and storage medium |
CN110460899A (en) * | 2019-06-28 | 2019-11-15 | 咪咕视讯科技有限公司 | Methods of exhibiting, terminal device and the computer readable storage medium of barrage content |
CN110536163A (en) * | 2019-05-13 | 2019-12-03 | 韶关市启之信息技术有限公司 | A kind of intelligent display method and system of barrage |
-
2020
- 2020-06-05 CN CN202010505169.8A patent/CN112749347B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930401A (en) * | 2016-04-15 | 2016-09-07 | 乐视控股(北京)有限公司 | Episode comment information screening method and apparatus |
CN105930403A (en) * | 2016-04-18 | 2016-09-07 | 苏州寅初信息科技有限公司 | Big data based film comment screening method |
CN106210770A (en) * | 2016-07-11 | 2016-12-07 | 北京小米移动软件有限公司 | A kind of method and apparatus showing barrage information |
CN110099306A (en) * | 2018-01-29 | 2019-08-06 | 优酷网络技术(北京)有限公司 | A kind of processing of comment information, display methods, client and server |
CN108471541A (en) * | 2018-02-01 | 2018-08-31 | 北京奇艺世纪科技有限公司 | A kind of method and device that video barrage is shown |
CN110166802A (en) * | 2019-05-06 | 2019-08-23 | 腾讯科技(深圳)有限公司 | Barrage processing method, device and storage medium |
CN110536163A (en) * | 2019-05-13 | 2019-12-03 | 韶关市启之信息技术有限公司 | A kind of intelligent display method and system of barrage |
CN110460899A (en) * | 2019-06-28 | 2019-11-15 | 咪咕视讯科技有限公司 | Methods of exhibiting, terminal device and the computer readable storage medium of barrage content |
Also Published As
Publication number | Publication date |
---|---|
CN112749347B (en) | 2023-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109544396B (en) | Account recommendation method and device, server, terminal and storage medium | |
US11086873B2 (en) | Query-time analytics on graph queries spanning subgraphs | |
JP7261827B2 (en) | Information processing method, device, electronic device and storage medium | |
US10028116B2 (en) | De-siloing applications for personalization and task completion services | |
US9569536B2 (en) | Identifying similar applications | |
US20140244388A1 (en) | Social Content Synchronization | |
US10110622B2 (en) | Security scanner | |
US20170249388A1 (en) | Expert Detection in Social Networks | |
WO2021120875A1 (en) | Search method and apparatus, terminal device and storage medium | |
CN107621886B (en) | Input recommendation method and device and electronic equipment | |
CN109872362B (en) | Target detection method and device | |
CN110391966B (en) | Message processing method and device and message processing device | |
CN110309357B (en) | Application data recommendation method, model training method, device and storage medium | |
US20170180805A1 (en) | Method and electronic device for video follow-play | |
CN112464052A (en) | Feedback information processing method, feedback information display device and electronic equipment | |
US10229212B2 (en) | Identifying Abandonment Using Gesture Movement | |
US11620327B2 (en) | System and method for determining a contextual insight and generating an interface with recommendations based thereon | |
CN114281936A (en) | Classification method and device, computer equipment and storage medium | |
US20140081973A1 (en) | Spike classification | |
US20170344170A1 (en) | Sequential Two-handed Touch Typing on a Mobile Device | |
CN112749347B (en) | Social content processing method and device, computing equipment and storage medium | |
CN111045560A (en) | Method for sending picture and electronic equipment | |
CN113312554B (en) | Method and device for evaluating recommendation system, electronic equipment and medium | |
CN114398128A (en) | Information display method and device | |
CN112732542A (en) | Information processing method, information processing device and terminal equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40043843 Country of ref document: HK |
|
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |