CN114840477B

CN114840477B - File sensitivity index determining method based on cloud conference and related product

Info

Publication number: CN114840477B
Application number: CN202210762599.7A
Authority: CN
Inventors: 曹佳新
Original assignee: Shenzhen Happycast Technology Co Ltd
Current assignee: Shenzhen Happycast Technology Co Ltd
Priority date: 2022-06-30
Filing date: 2022-06-30
Publication date: 2022-09-27
Anticipated expiration: 2042-06-30
Also published as: CN114840477A

Abstract

The application provides a file sensitivity index determining method based on a cloud conference and a related product, wherein the method is realized by the following steps: acquiring a target cloud conference host grade and a media file display ratio from terminal equipment; determining a target preset display proportion corresponding to the target cloud conference host grade according to the mapping relation between the target cloud conference host grade and the preset display proportion; detecting whether the display proportion of the media file reaches a target preset display proportion or not; and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index. By adopting the method of the embodiment of the application, the target frame sensitivity index of the media file is determined when the display proportion of the media file reaches the target preset display proportion, and the display mode of the terminal equipment for the target frame is indicated according to the target frame sensitivity index, so that the occurrence of cloud conference accidents caused by the fact that the media file comprises sensitive information is avoided.

Description

File sensitivity index determining method based on cloud conference and related product

Technical Field

The application relates to the technical field of computers, in particular to a file sensitivity index determining method based on a cloud conference and a related product.

Background

With the rapid development of internet technology and the rapid increase of commercial activity, online cloud conference via the internet has become an emerging office form.

However, with the rapid rise and popularization of cloud conferences, information security issues also come with it. The cloud conference usually needs a cloud conference host to push media files such as videos, pictures and characters in a live mode, and the cloud conference host can push the media files to other people in real time only through simple information registration, so that the cloud conference has the bad condition that harmful contents violating laws and regulations are pushed maliciously by lawbreakers. Meanwhile, due to the characteristic of instantaneity of the cloud conference, it is seen that at present, when the number of the cloud conference is more and media information is more and more abundant, if a mainstream manual review mode is adopted to perform sensitive review on media files in the cloud conference process, the requirement of the cloud conference on the increasingly higher information safety is more and more difficult to meet.

Disclosure of Invention

The embodiment of the application provides a file sensitivity index determining method based on a cloud conference and a related product.

In a first aspect, an embodiment of the present application provides a file sensitivity index determining method based on a cloud conference, where the method is applied to a server, the server is in communication connection with a terminal device, and the terminal device is a device for performing the cloud conference, and the method includes:

acquiring a target cloud conference host grade and a media file display ratio from terminal equipment;

determining a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion;

detecting whether the display proportion of the media file reaches a target preset display proportion or not;

and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index.

In one possible example, if the frame sensitivity index of the media file is determined frame by frame and the time for the terminal device to display the target frame reaches the preset dwell time, the method further includes:

acquiring a target subsequent frame, wherein the display sequence of the target subsequent frame in the media file is behind the target frame;

determining the proportion of the character information in the target subsequent frame;

if the proportion of the character information is not less than the first preset proportion, matching the character information in the target subsequent frame with a preset keyword library, and determining the character sensitivity index of the target subsequent frame according to the matching result; and/or

Determining the proportion of image information in a target subsequent frame;

if the image information accounts for not less than the second preset proportion, matching the image information in the target subsequent frame with a plurality of sensitive images in the sensitive image library, and determining the complete image sensitivity index of the target subsequent frame according to the matching result;

the determining the target frame sensitivity index of the media file and indicating the display mode of the terminal device to the target frame according to the target frame sensitivity index includes:

determining a target subsequent frame sensitivity index of the media file according to the character sensitivity index of the target subsequent frame and/or the complete image sensitivity index of the target subsequent frame;

and determining the target file sensitivity index of the media file according to the target frame sensitivity index of the media file and the target subsequent frame sensitivity index of the media file, and indicating the display mode of the terminal equipment for the media file according to the target file sensitivity index.

In a second aspect, an embodiment of the present application provides a file sensitivity index determining apparatus based on a cloud conference, which is applied to a server, where the server is in communication connection with a terminal device, and the terminal device is a device for performing the cloud conference, where the apparatus includes:

the acquisition unit is used for acquiring the host grade of the target cloud conference and the display proportion of the media file from the terminal equipment;

the determining unit is used for determining a target preset display proportion corresponding to the target cloud conference host level according to the mapping relation between the target cloud conference host level and the preset display proportion;

the detection unit is used for detecting whether the display proportion of the media file reaches a target preset display proportion or not;

and the indicating unit is used for determining a target frame sensitivity index of the media file if the media file display proportion reaches a target preset display proportion, and indicating the display mode of the terminal equipment for the target frame according to the target frame sensitivity index.

In a third aspect, embodiments of the present application provide an electronic device, which includes a processor, a memory, and computer executable instructions stored on the memory and executable on the processor, and when the computer executable instructions are executed, the electronic device is caused to perform some or all of the steps described in any one of the methods of the first aspect of the embodiments of the present application.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon computer instructions, which, when executed on a communication apparatus, cause the communication apparatus to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application.

In a fifth aspect, the present application provides a computer program product, where the computer program product includes a computer program operable to cause a computer to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

In the embodiment of the application, the host level of the target cloud conference and the display proportion of the media file are obtained from the terminal equipment; determining a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion; detecting whether the display proportion of the media file reaches a target preset display proportion or not; and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index. By adopting the method of the embodiment of the application, the target frame sensitivity index of the media file is determined when the display proportion of the media file reaches the target preset display proportion, and the display mode of the terminal equipment for the target frame is indicated according to the target frame sensitivity index, so that the occurrence of cloud conference accidents caused by the fact that the media file comprises sensitive information is avoided, and the cloud conference is ensured to be carried out safely and smoothly.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic architecture diagram of a cloud conference system applied in an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for determining a document sensitivity index based on a cloud conference according to an embodiment of the present application;

fig. 3 is an exemplary schematic diagram of a file sensitivity index determining method based on a cloud conference according to an embodiment of the present application;

FIG. 4 is a schematic flowchart of an emotion dictionary text matching algorithm based on a cloud conference according to an embodiment of the present application;

fig. 5 is an exemplary schematic diagram of a file sensitivity index determining method based on a cloud conference according to an embodiment of the present application;

fig. 6 is an exemplary schematic diagram of a file sensitivity index determining method based on a cloud conference according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a file sensitivity index determining apparatus based on a cloud conference according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a server in a hardware operating environment of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the 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 a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

The following describes an application scenario related to an embodiment of the present application with reference to the drawings.

Fig. 1 is a schematic architecture diagram of a cloud conference system applied in an embodiment of the present application. As shown in fig. 1, the cloud conference system includes a server and a database, a first end of the server is connected with a first local device and a second local device, a second end of the server is connected with the database,

the first local device is a terminal device used by a cloud conference creator in a cloud conference, and is used for sending a cloud conference creation request to a server when receiving a cloud conference creation instruction initiated by the cloud conference creator, in a specific implementation, the cloud conference creation instruction and the cloud conference creation request may include attribute information of the cloud conference, where the attribute information includes conference subject, conference privacy level, conference participant number, conference participant duty level, and the like, and the first local device includes a terminal device of a user or a screen projection device;

the second local device is a terminal device used by a cloud conference host in a cloud conference, and is used for sending a cloud conference host request to the server when receiving a cloud conference host right acquisition instruction initiated by a target participant, and enabling the target participant to become a cloud conference host after receiving an agreement instruction from the server, so that the cloud conference host acquires a control authority of a cloud conference control desktop through the second local device, and then the cloud conference host can display shared content and explanation information through the second local device, wherein the shared content is content information uploaded to a database of a cloud conference system by the participant in the cloud conference, and the explanation information comprises at least one of the following: editing information, comment information and voice information, wherein an object directly associated with explanation information comprises shared content or an electronic whiteboard established in the explanation process of the shared content, a cloud conference control desktop at least displays at least one shared content of a cloud conference, a single cloud conference host can input explanation information aiming at one or more shared contents, a single shared content can be input by one or more hosts into the explanation information, and second local equipment comprises terminal equipment or screen projection equipment of a user;

the third local device is terminal equipment used by other participants except a cloud conference creator and a cloud conference host in the cloud conference and used for watching the shared content and the explanation information of the cloud conference control desktop, and the third local device comprises terminal equipment of a user;

the server is used for creating a cloud conference group at the cloud end after receiving a cloud conference creation request from the first local device so that participants of the cloud conference can join the cloud conference through the local device, and in a specific implementation, the server can be a cloud server;

the database is used for storing conference data of the cloud conference, the conference data comprises control plane data and data plane data, and in a specific implementation, the database can be a cloud space database;

in a specific implementation, the shared content may be an office document file (including Word, PPT, Excel, and the like), a CAD drawing file, an audio file, a video file, or a split-screen mirror image, a screen recording content, and the like of a local device of a user; the personnel identities of the cloud conference creator, the cloud conference host and other participants can be interchanged, that is, the cloud conference creator can be the cloud conference host at the same time and can also become other participants by transferring the host authority, and similarly, the first local device, the second local device and the third local device can also be switched with each other according to the identity transformation of the user in the cloud conference.

Based on this, an embodiment of the present application provides a method for determining a file sensitivity index based on a cloud conference, which is applied to a server, where the server is in communication connection with a terminal device, and the terminal device is a device for performing the cloud conference, please refer to fig. 2, where fig. 2 is a schematic flowchart of the method for determining a file sensitivity index based on a cloud conference provided in the embodiment of the present application, and as shown in fig. 2, the method includes the following steps:

101: and acquiring the host level of the target cloud conference and the display ratio of the media file from the terminal equipment.

The server, in a specific implementation, may be a cloud server.

The terminal device may be an electronic device such as a smart phone, a tablet computer, a personal digital assistant, a wearable device, or the like.

The target cloud conference host level is directly associated with the current cloud conference host, and in specific implementation, host conference data in all aspects such as the past host total time, the host total frequency, the host accident occurrence frequency, the host evaluation and the like of the current cloud conference host can be comprehensively determined.

In a specific implementation, the media file display proportion may be a size proportion of the media file occupying the cloud conference control desktop. The media files can be office document files (including Word, PPT, Excel and the like), CAD drawing files, audio files and video files, and can also be split-screen mirror images, screen recording contents and the like of local equipment of a user.

102: and determining a target preset display proportion corresponding to the target cloud conference host grade according to the mapping relation between the target cloud conference host grade and the preset display proportion.

In specific implementation, the higher the cloud conference host level is, the higher the reliability of the cloud conference host is, so that the frame sensitivity index of the displayed media file can be determined when the displayed media file has a larger display proportion, and therefore, the positive correlation between the cloud conference host level and the preset display proportion corresponding to the mapping can be presented. The cloud conference hosting level can be divided into a low level, a middle level and a high level, and can also be divided into a level 1, a level 2 … … 5 or other hierarchical modes from low level to high level; the preset display ratio may include 40%, 60%, 80%, or other ratios.

Illustratively, the mapping relationship between the cloud conference hosting level and the preset presentation scale is shown in table 1,

TABLE 1

Cloud conference hosting level	Preset display scale
		Low grade	40%
Middle stage	60%
		Advanced	80%

When the target cloud conference host level of the cloud conference host is low, the corresponding target preset display proportion is 40%, that is, if the media file display proportion of the cloud conference host reaches more than 40%, the target frame sensitivity index of the media file needs to be determined; similarly, when the target cloud conference host level of the cloud conference host is a middle level, the corresponding target preset display proportion is 60%; when the target cloud conference host level of the cloud conference host is high, the corresponding target preset display proportion is 80%.

It should be noted that the mapping relationship between the cloud conference hosting level and the preset presentation ratio shown in table 1 is only an example of one mapping relationship, and in a specific application, the mapping relationship between the cloud conference hosting level and the preset presentation ratio may also exist in a form of other hierarchy components.

103: and detecting whether the display proportion of the media file reaches a target preset display proportion.

The media file display ratio = media file display size/cloud conference control desktop size, and therefore, it is detected whether the media file display ratio reaches a target preset display ratio, in a specific implementation, that is, whether a ratio between the media file display size and the cloud conference control desktop size is greater than or equal to the target preset display ratio.

104: and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index.

In specific implementation, the target frame sensitivity index can be expressed in a percentage form of 0-100%, and can also be expressed in a numerical form of 0-1. Furthermore, if the percentage of 0 to 100% is used to represent the target frame sensitivity index, the target frame sensitivity index may be 75%, 80% or other percentage, and similarly, if the numerical value of 0 to 1 is used to represent the target frame sensitivity index, the target frame sensitivity index may be 0.75, 0.80 or other numerical value.

In a specific implementation, the media file often includes text information and image information at the same time, and thus the sensitivity information of the media file may include both the target frame text sensitivity index and the target frame image sensitivity index, so that the determination of the target frame sensitivity index of the media file may be determined by both the target frame text sensitivity index and the target frame image sensitivity index, or by determining the higher of the target frame text sensitivity index and the target frame image sensitivity index as the target frame sensitivity index.

The method comprises the steps of indicating a display mode of a terminal device for a target frame according to a target frame sensitivity index, and indicating the terminal device to process the target frame in different display modes according to different target frame sensitivity indexes. In the specific implementation, the higher the target frame sensitivity index is, the more harmful information which indicates that the target frame of the media file is not suitable for being displayed is, so that the display processing of the media file can be stopped when the target frame sensitivity index is at a higher value, and meanwhile, the authority transfer processing can be performed on a cloud conference host who displays the media file, so that a live broadcast accident of the cloud conference can be avoided; on the contrary, if the target frame sensitivity index is low, it indicates that the target frame of the media file may only have a small amount of slight bad information which is not enough to cause a problem to the whole media file, and the whole media file does not need to be subjected to all-round denial.

Exemplarily, a target frame sensitivity index is represented in a numerical form of 0-1, please refer to fig. 3, and fig. 3 is an exemplary schematic diagram of a method for determining a file sensitivity index based on a cloud conference provided in an embodiment of the present application, as shown in fig. 3, a cloud conference host displays a media file on a terminal device in a cloud conference control desktop, a server obtains from the terminal device that a target cloud conference host level of the cloud conference host is a middle level and a media file display proportion is 70%, according to a mapping relationship between the cloud conference host level and a preset display proportion, the server determines that a corresponding target preset display proportion is 60% when the target cloud conference host level is the middle level, so that the server detects that 70% of the media file display proportion has reached the target preset display proportion 60%, and further analyzes the target frame sensitivity index of the media file, And determining that the target frame sensitivity index of the media file is 0.05, and the reason for the target frame sensitivity index being 0.05 is a target part in a target page of the media file, and because the target frame sensitivity index is low, the server performs fuzzy display processing on the target part so as to prevent participants of the cloud conference from receiving the sensitive information in the target frame on local equipment of the participants, and ensure that the cloud conference is performed smoothly and safely.

It can be seen that in the embodiment of the application, the host grade of the target cloud conference and the display proportion of the media file are obtained from the terminal equipment; determining a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion; detecting whether the display proportion of the media file reaches a target preset display proportion or not; and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index. By adopting the method of the embodiment of the application, the target frame sensitivity index of the media file is determined when the display proportion of the media file reaches the target preset display proportion, and the display mode of the terminal equipment for the target frame is indicated according to the target frame sensitivity index, so that the occurrence of cloud conference accidents caused by the fact that the media file comprises sensitive information is avoided, and the cloud conference is ensured to be carried out safely and smoothly.

In some application scenarios, if the text information in the target frame is less, it may be directly detected whether the small amount of text information in the target frame is sensitive words, however, when the text information in the target frame is more, semantic logicality in a specific context often exists between the text information, and it is apparent that when the occupation ratio of the text information is different, there should be different text sensitivity index determination manners.

Therefore, for the application scenario, an embodiment of the present application provides another method for determining a file sensitivity index based on a cloud conference, which specifically includes:

in one possible example, the target frame sensitivity index comprises a target frame text sensitivity index, and determining the target frame sensitivity index for the media file comprises:

determining the proportion of character information in the target frame;

if the proportion of the character information is smaller than a first preset proportion, matching the character information in the target frame with a preset keyword library, and determining the character sensitivity index of the target frame according to a matching result;

if the occupation ratio of the character information is not smaller than the first preset ratio, matching the character information in the target frame with the emotion dictionary to obtain the emotion sensitivity index of the target frame;

and determining the text sensitivity index of the target frame according to the character sensitivity index or the emotion sensitivity index.

The ratio of the text information in the target frame may refer to the information content occupied by the text information in the target frame, or may refer to the visual proportion occupied by the text information in the target frame.

In a specific implementation, the first preset proportion can be expressed in a percentage form of 0-100%, and can also be expressed in a numerical form of 0-1. Further, if the first predetermined ratio is expressed in a percentage form of 0 to 100%, the first predetermined ratio may be 35%, 50% or other percentages, and similarly, if the first predetermined ratio is expressed in a numerical form of 0 to 1, the first predetermined ratio may be 0.35, 0.50 or other numerical values.

In a specific implementation, the preset keyword library may include a plurality of keyword eyes that are not allowed to appear in the cloud conference and are set in advance by a manager of the cloud conference.

In a specific implementation, the emotion dictionary may include two parts of contents, that is, a plurality of emotion word banks and weights corresponding to a plurality of words included in the plurality of emotion word banks. Further, the emotion word bank can comprise a positive emotion word bank, a negative word bank and a degree adverb word bank. The emotion dictionary is important in the process of emotion analysis of text information, and a plurality of open-source emotion dictionaries such as a Boson BosonNLP emotion dictionary are arranged on the market at present, are constructed based on data sources such as microblogs, news and forums, are also known as a Web emotion dictionary and the like, so that the open-source emotion dictionary can be applied in specific implementation, and meanwhile, an emotion dictionary which is more adaptive to a cloud conference can be trained by managers of the cloud conference by combining with attribute information of the cloud conference.

In the specific implementation, as the media file target frame is pushed to the cloud conference participants by live broadcasting, the cloud conference has a very high speed requirement on the sensitivity matching detection of the target frame, and in order to improve the working efficiency of determining whether the target frame has sensitive information, it can be seen that the sensitivity matching detection should be preferentially performed on fewer characters as far as possible, so that if the proportion of the character information is smaller than a first preset proportion, that is, if the proportion of the character information is less than a small proportion, the character information in the target frame is directly matched with a preset keyword library; and if the occupation ratio of the character information is not less than the first preset ratio, namely, when the character information occupies more parts, matching the character information in the target frame with the emotion dictionary, and analyzing the character information more accurately and considering semantic logicality.

It can be seen that in the embodiment of the application, when the target frame includes the text information, different sensitive information matching modes can be adopted for the target frame according to the proportion of the text information, when the proportion of the text information is small, the text information is matched with the preset keyword library in a simpler and direct mode, and when the proportion of the text information is large, the text information is matched with the emotion dictionary in a more accurate mode and in consideration of semantic logic, so that the determination of the text sensitivity index of the target frame is completed according to the actual situation of the proportion of the text information, the sensitivity index of the target frame of the media file can be determined, and the flexibility and the accuracy of the determination process of the sensitivity index of the target frame are improved.

In some application scenes, in the commonly used emotion dictionary, polysemous words may exist, and the same polysemous word may have distinct meanings in different contexts, so that in order to enable the emotion dictionary to be suitable for the use scenes of the cloud conference, the emotion dictionary can be adjusted and corrected according to the field terms corresponding to the cloud conference, and the accuracy of the finally determined emotion sensitivity index of the target frame is improved.

in one possible example, the emotion dictionary comprises a positive emotion word bank and a non-positive emotion word bank, and the method further comprises:

acquiring target field information corresponding to a target cloud conference;

determining a target field term lexicon corresponding to the target cloud conference according to the target field information;

matching the target field term word stock with the non-positive emotion word stock to determine a target polysemous word, wherein the target polysemous word is at least one polysemous word which is in the non-positive emotion word stock and is in literal coincidence with the target field term word stock;

deleting the target polysemous words in the emotion dictionary to obtain an adjusted emotion dictionary;

the above matching the text information in the target frame with the emotion dictionary to obtain the emotion sensitivity index of the target frame includes:

and matching the character information in the target frame with the adjusted emotion dictionary to obtain the emotion sensitivity index of the target frame.

In specific implementation, the target domain information corresponding to the target cloud conference can be determined according to an explanation product corresponding to the target cloud conference and an application industry of the explanation product.

In a specific implementation, the server may copy the emotion dictionary to obtain an emotion dictionary copy, and then delete the target ambiguous word from the emotion dictionary copy, so that the emotion dictionary copy from which the target ambiguous word is deleted is the adjusted emotion dictionary.

For example, if the target domain information corresponding to the target cloud conference is the internet marketing domain, it may be determined that the target domain term words include a term word, which indicates that the market is difficult to sufficiently satisfy and the customer is urgently required to satisfy, a term word, which indicates that most of the customers can follow the behavior of the general mind in order to achieve a rapid increase in the number of customers, and the like, according to the target domain information, which is the internet marketing domain. However, for the security domain, "detonation point" is a word that has dangerous implications, and therefore, it is common for the word "detonation point" to be included in the non-positive emotion lexicon, so that, in the context of the internet marketing domain, "detonation point" is a ambiguous word, and the server matching the target domain term lexicon with the non-positive emotion lexicon can determine the target ambiguous word including "detonation point". In order to avoid the miscalculation of the emotion sensitivity index of the character information caused by the existence of the polysemous words, the server deletes the target polysemous words in the emotion dictionary to obtain an adjusted emotion dictionary, and then matches the character information in the target frame with the adjusted emotion dictionary to finally obtain the emotion sensitivity index of the target frame.

It can be seen that, in the embodiment of the application, according to the target field information corresponding to the target cloud conference, the target field term lexicon corresponding to the target cloud conference is determined, then the target polysemous words determined after the target field term lexicon is matched with the non-positive emotion lexicon are deleted from the emotion dictionary to obtain the adjusted emotion dictionary, finally, the character information in the target frame is matched with the adjusted emotion dictionary to obtain the emotion sensitivity index of the target frame, so that the adverse effect of wrong calculation of the emotion sensitivity index of the character information caused by the existence of the polysemous words in a specific field is avoided, the flexibility and the accuracy of the target frame sensitivity index determination process are improved, and the target frame sensitivity index determination process is more personalized.

In some application scenarios, in different cloud conference environments, the supervision strictness degree of the display content of the same target frame is different, for example, if the number of participants of the cloud conference is large and the job level of the participants is high, a higher requirement is inevitably required on the security of the cloud conference content, and therefore, when the emotion sensitivity index of the target frame is determined, the comprehensive determination can be performed by combining the information supervision level of the cloud conference.

in one possible example, the matching the text information in the target frame with the adjusted emotion dictionary to obtain the emotion sensitivity index of the target frame includes:

performing word segmentation processing on the character information in the target frame to obtain a plurality of target vector word groups;

according to the adjusted emotion dictionary, performing part-of-speech type judgment on each target vector phrase in the plurality of target vector phrases to obtain a part-of-speech type corresponding to each target vector phrase, and determining an emotion score corresponding to each target vector phrase according to the part-of-speech type corresponding to each target vector phrase;

acquiring conference attributes of a target cloud conference, determining an information supervision level of the target cloud conference according to the conference attributes of the target cloud conference, and obtaining a target emotion sensitivity weight according to the information supervision level, wherein the information supervision level is used for indicating the supervision strictness degree of cloud conference contents;

and calculating to obtain the emotion sensitivity index of the target frame according to the target emotion sensitivity weight and the emotion score corresponding to each target vector word group.

In a specific implementation, a word segmentation process is performed on the text information in the target frame, and in the text information in the target frame, all words capable of being formed in words can be scanned by using a Chinese character segmentation word, so that a plurality of target vector word groups are obtained.

In a specific implementation, the part-of-speech category may be divided into a positive word, a non-positive word, and a negative word, so as to determine the part-of-speech category corresponding to each target vector phrase according to the content of the target vector phrase.

The conference attributes of the target cloud conference may include, in specific implementation, information such as conference privacy level, number of participants, and job level of the participants of the target cloud conference. Further, the information supervision level of the target cloud conference is determined according to the conference attribute of the target cloud conference, and the information supervision level may be higher when the conference privacy level of the target cloud conference is higher, the number of participants is larger, and the job level of the participants is higher, that is, the conference importance of the target cloud conference is higher, and the content supervision requirement is stricter, the information supervision level is higher.

In the specific implementation, the higher the information supervision level is, the more exclusive the situation of sensitive information in the cloud conference is, and the more impermissible the sensitive information in the cloud conference is, so that a positive correlation can be presented between the information supervision level and the target emotion-sensitive weight.

In a specific implementation, the emotion sensitivity index of the target frame may be equal to a product between a total emotion score obtained by adding the emotion scores corresponding to the target vector word groups and the target emotion sensitivity weight.

In a specific implementation, the matching of the character information in the target frame and the emotion dictionary to obtain the emotion sensitivity index of the target frame and the matching of the character information in the target frame and the adjusted emotion dictionary to obtain the emotion sensitivity index of the target frame can be implemented by adopting an emotion dictionary text matching algorithm.

Illustratively, the emotion dictionary comprises a face word lexicon, a non-face word lexicon, a negative word lexicon and a degree adverb lexicon, so that the part-of-speech categories corresponding to the vector word group comprise face words, non-face words and negative words. If the part of speech category corresponding to the target vector phrase is a negative word, the phrase emotion score of the target vector phrase is-X; if the part-of-speech category corresponding to the target vector phrase is a front word and the part-of-speech categories of the front and rear vector phrases corresponding to the target vector phrase are other words except the front word, the phrase emotion score of the target vector phrase is-X; and if the part-of-speech category corresponding to the target vector phrase is a non-positive word and the part-of-speech category of the vector phrase before the target vector phrase is a negative word, the phrase emotion score of the target vector phrase is + X. And if the word of the previous vector phrase of the target vector phrase is a degree adverb, the target vector phrase obtains a phrase weight factor for multiplication. Please refer to fig. 4, fig. 4 is a schematic flow chart of an emotion dictionary text matching algorithm based on a cloud conference according to an embodiment of the present application, and as shown in fig. 4, a word segmentation process is performed on text information in a target frame by using a method of word segmentation based on a result of a crust to obtain a plurality of target vector phrases, word-by-word judgment is performed on a part-of-speech category corresponding to each of the plurality of target vector phrases according to an emotion dictionary, after a part-of-speech category of the target vector phrase and a corresponding phrase emotion score are determined, a part-of-speech category of a previous vector phrase or a previous and subsequent vector phrases is detected according to the part-of-speech category of the target vector phrase to determine a weight factor corresponding to the target vector phrase, a final phrase emotion score corresponding to each target vector phrase is determined according to the emotion score and the phrase weight factor, after a final phrase emotion score of the plurality of target vector phrases is determined, and adding and summing the final phrase emotion scores of each target vector phrase, performing weighting operation on the obtained sum and the target emotion sensitivity weight, and finally calculating to obtain the emotion sensitivity index of the target frame.

It can be seen that, in the embodiment of the application, the information supervision level of the target cloud conference is determined according to the conference attribute of the target cloud conference, and the target emotion sensitivity weight is obtained according to the information supervision level, so that the emotion sensitivity index of the target frame obtained through final calculation is determined by the target emotion sensitivity weight and the emotion score corresponding to each target vector phrase, comprehensive consideration is further performed in combination with the information supervision level of the target cloud conference in the process of calculating the emotion sensitivity index of the target frame, and the target frame sensitivity index determination process is more personalized while the flexibility and the accuracy of the target frame sensitivity index determination process are improved.

In some application scenarios, if the image information in the target frame is less, the image information with a small occupied area in the target frame may be directly subjected to comprehensive sensitivity detection, however, the cloud conference has a very high speed requirement for sensitivity matching detection of media files, and if the image information in the target frame is more, if a large amount of image information is still subjected to comprehensive sensitivity detection, the sensitivity detection efficiency will be undoubtedly reduced, which easily causes a live broadcast accident of the cloud conference, and it is apparent that different image sensitivity index determination modes should be provided when the image information has different occupation ratios.

in one possible example, the target frame sensitivity index comprises a target frame image sensitivity index, and determining the target frame sensitivity index for the media file comprises:

determining the proportion of image information in a target frame;

if the proportion of the image information is smaller than a second preset proportion, matching the image information in the target frame with a plurality of sensitive images in a sensitive image library, and determining the complete image sensitivity index of the target frame according to the matching result;

if the image information accounts for not less than the second preset proportion, determining representative image information of the image information in the target frame, matching the representative image information with a sensitive image library, and determining a representative image sensitivity index of the target frame according to a matching result;

and determining the image sensitivity index of the target frame according to the complete image sensitivity index or the representative image sensitivity index.

In a specific implementation, the ratio of the image information in the target frame may refer to an information content occupied by the image information in the target frame, or may refer to a visual proportion occupied by a part of the image information in the target frame.

In a specific implementation, the second preset proportion can be expressed in a percentage form of 0-100%, and can also be expressed in a numerical form of 0-1. Further, if the second predetermined ratio is expressed in a percentage of 0 to 100%, the second predetermined ratio may be 15%, 30% or other percentages, and similarly, if the second predetermined ratio is expressed in a numerical value of 0 to 1, the second predetermined ratio may be 0.15, 0.30 or other numerical values.

In a specific implementation, the sensitive image library may include a plurality of sensitive images that are not allowed to appear in the cloud conference and are set in advance by a manager of the cloud conference, and may further include a plurality of sensitive images that are determined to include harmful information and sensitive information on the network.

In the specific implementation, the media file target frame is pushed to the cloud conference participants by live broadcasting, so that the cloud conference has a very high speed requirement on the sensitivity matching detection of the target frame, and in order to improve the work efficiency of determining whether the target frame has sensitive information, it can be seen that the sensitivity matching detection should be preferentially performed on a smaller image or a representative part of image as far as possible, so that if the proportion of the image information is smaller than a second preset proportion, that is, if the image information is smaller, the image information in the target frame is matched with a plurality of sensitive images included in a sensitive image library; and if the image information accounts for not less than the second preset proportion, namely, the image information accounts for a larger proportion, determining the representative image information of the image information in the target frame, and matching the representative image information with the representative characteristics with the sensitive image library.

Matching image information in the target frame with a plurality of sensitive images in a sensitive image library, wherein in the specific implementation, the complete image information in the target frame is matched with the plurality of sensitive images; the representative image information is matched with the sensitive image library, in a specific implementation, a partial image with representative characteristics in a target frame is matched with a plurality of sensitive images, and further, the representative image information with the representative characteristics can be a partial image with the largest area occupation ratio of the image information in the target frame or a partial image with the smallest similarity variance with other partial image information in a plurality of partial image information included in the image information in the target frame.

Exemplarily, assuming that the second preset proportion is 50%, that is, half of the size of the target frame, please refer to fig. 5, where fig. 5 is an exemplary schematic diagram of a file sensitivity index determining method based on a cloud conference provided in an embodiment of the present application, and the target frame of the media file is displayed in a full screen manner, as shown in fig. 5 (a), it can be seen that the target frame only includes an image of a target image, and a ratio of the target image is smaller than the second preset proportion, and therefore, the target image is matched with a plurality of sensitive images included in the sensitive image library; as shown in (b) of fig. 5, it can be seen that the target frame includes a plurality of partial images, a total occupation ratio of the plurality of partial images in the target frame is greater than a second preset ratio, and the occupation ratio of the target partial image is the largest among all the partial images, and thus the target partial image is matched with the plurality of sensitive images included in the sensitive image library.

It can be seen that, in the embodiment of the present application, when the target frame includes image information, different sensitive information matching manners can be adopted for the target frame according to the size of the proportion of the image information, when the proportion of the image information is small, the complete image information is matched with the sensitive image library, and when the proportion of the image information is large, the representative image information with representative characteristics is matched with the sensitive image library, so as to complete the determination of the image sensitivity index of the target frame according to the actual situation of the proportion of the image information, and further, the target frame sensitivity index of the media file can be determined, and the flexibility and the accuracy of the determination process of the target frame sensitivity index are improved.

In one possible example, the matching the representative image information with the sensitive image library and determining the representative image sensitivity index of the target frame according to the matching result includes:

obtaining a target key point feature vector of image information in a target frame according to an image processing algorithm;

determining a plurality of corresponding image similarities between the image information in the target frame and the plurality of sensitive images according to the feature vectors of the target key points;

acquiring attribute information of a target cloud conference, determining an information supervision level according to the attribute information of the target cloud conference, and obtaining a target image sensitivity weight according to the information supervision level;

and determining a representative image sensitivity index of the target frame according to the similarity of the plurality of images and the target image sensitivity weight.

In the specific implementation, the image processing algorithm may be a Scale-invariant feature transform (SIFT) algorithm, or may be another image processing algorithm capable of extracting a feature vector of a key point of frame image information. The SIFT algorithm is an algorithm of computer vision, the application range comprises object identification, image stitching and the like, and the SIFT algorithm is based on key point characteristics of some local appearances on the image and is independent of the size and the rotation of the image. The tolerance to light, noise, and micro-viewing angle changes present in the image is also quite high. Based on the characteristics, the SIFT algorithm can easily identify the matching image in the feature database with huge mother number, and the accuracy is high.

In a specific implementation, the representative image sensitivity index of the target frame is determined according to the maximum image similarity among the image similarities and the target image sensitivity weight, or the representative image sensitivity index of the target frame is determined according to the average image similarity among the image similarities and the target image sensitivity weight.

It can be seen that, in the embodiment of the present application, a target key point feature vector of image information in a target frame is obtained according to an image processing algorithm, a plurality of corresponding image similarities between the image information in the target frame and a plurality of sensitive images are determined according to the target key point feature vector, an information supervision level is determined according to attribute information of a target cloud conference, a target image sensitivity weight is obtained according to the information supervision level, and a representative image sensitivity index of the target frame is finally determined according to the plurality of image similarities and the target image sensitivity weight, so that the representative image sensitivity index of the target frame obtained through final calculation is determined by the target image sensitivity weight and the plurality of image similarities, and is comprehensively considered in combination with the information supervision level of the target cloud conference in the process of calculating the representative image sensitivity index of the target frame, thereby improving flexibility and accuracy of the process of determining the target frame sensitivity index and simultaneously enabling the target frame sensitivity index to be comprehensively considered The determination process is more personalized.

In some application scenarios, the size of the target frame sensitivity index often represents the severity of a cloud conference live broadcast accident, when the target frame sensitivity index is small, that is, the target frame sensitivity information is less, a cloud conference host has time to change the media file in time, and when the target frame sensitivity index is large, that is, the target frame sensitivity information is more, it is difficult to change the media file in a very short time, and a more strict limitation push measure needs to be taken for the media file.

in a possible example, the indicating, according to the target frame sensitivity index, a display mode of the terminal device for the target frame includes:

if the target frame sensitivity index is smaller than or equal to the first preset index, indicating the terminal equipment to perform delayed display processing on the target frame;

if the target frame sensitivity index is larger than the first preset index and smaller than or equal to the second preset index, the terminal equipment is instructed to carry out fuzzy display processing on the target frame;

and if the target frame sensitivity index is larger than the second preset index, indicating the terminal equipment to stop displaying the media file.

The preset index can be expressed in a percentage form of 0-100% in specific implementation, and can also be expressed in a numerical form of 0-1. Furthermore, if the preset index is expressed in a percentage form of 0-100%, the first preset index may be 20%, 30% or other percentages, and the second preset index may be 60%, 70% or other percentages, as long as the first preset index is smaller than the second preset index.

In a specific implementation, the target frame can be displayed only after a preset time interval is set, so that spare time is provided for a cloud conference host to modify, replace or otherwise process a media file on a cloud conference control desktop on the terminal device of the cloud conference host when sensitive information exists in the target frame. In the process of performing the delayed presentation processing on the target frame, the server may instruct the terminal device to change the target frame into a black screen state.

In a specific implementation, the instructing terminal device may perform blurring processing or mosaic processing on a sensitive information portion in the target frame, and perform normal display on a non-sensitive information portion except the sensitive information portion in the target frame.

In a specific implementation, the instructing terminal device may instruct the terminal device to forcibly close the media file, or may instruct the cloud conference control desktop to be in a black screen state so as to stop displaying the media file.

In specific implementation, after the display mode of the terminal device for the target frame is indicated according to the target frame sensitivity index, the hosting authority of the cloud conference host can be changed according to the size of the target frame sensitivity index. Illustratively, if the target frame sensitivity index is less than or equal to a first preset index, the server sends an alert message to a cloud conference host; if the target frame sensitivity index is larger than the first preset index and smaller than or equal to the second preset index, the server sends a change request to the cloud conference host, the cloud conference host is required to change and confirm the media file within preset time, and if no change is confirmed, the conference permission is transferred to other participants; if the target frame sensitivity index is larger than the second preset index, the server determines the cloud conference host as an illegal user, limits the pushing permission of the cloud conference host for displaying the media file, and further can forcibly remove the cloud conference host out of the target cloud conference group.

Illustratively, instructing the terminal device to perform delayed display processing on the target frame, namely instructing the terminal device to change the target frame into a black screen state until a preset time and then displaying the target frame; the method comprises the steps that the terminal equipment is instructed to carry out fuzzy display processing on a target frame, and mosaic processing is carried out on sensitive information parts in the target frame through the terminal equipment; and instructing the terminal equipment to stop the display processing of the media file, namely instructing the terminal equipment to forcibly close the media file. Referring to fig. 6, fig. 6 is a schematic diagram illustrating an example of a method for determining a file sensitivity index based on a cloud conference according to an embodiment of the present application, where a target frame of a media file is displayed in a full screen, and as shown in fig. 6 (a), when a target frame sensitivity index is less than or equal to a first preset index, the target frame is displayed in a black screen state; as shown in fig. 6 (b), when the target frame sensitivity index is greater than the first preset index and less than or equal to the second preset index, the target portion of the target frame where the sensitive information exists is subjected to mosaic processing; as shown in (c) of fig. 6, when the target frame sensitivity index is greater than the second preset index, the media file corresponding to the target frame is forcibly closed, and a popup message that the media file is closed is displayed on the cloud conference control desktop.

It can be seen that, in the embodiment of the present application, when the display mode of the terminal device for the target frame is indicated according to the target frame sensitivity index, the terminal device is specifically indicated to perform different display mode processing on the target frame according to different sizes of the target frame sensitivity index, so that when the target frame includes sensitive information, the strictness of the display mode of the terminal device for the target frame correspondingly changes in a stepwise manner according to the size of the target frame sensitivity index, so that the display mode of the terminal device for the target frame with the sensitive information is more intelligent and flexible, the occurrence of a cloud conference accident caused by the large-range leakage of the sensitive information included in the media file is avoided, and the cloud conference is ensured to be performed safely and smoothly.

In some application scenarios, the media file is usually played and pushed according to a frame sequence, so that it is difficult to ensure whether the subsequent frame has no sensitive information when the target frame has no sensitive information, and therefore, more comprehensive and more accurate sensitivity detection can be performed on the subsequent frame in advance, and while the sensitivity index of the media file is corrected, a cloud conference host can change the media file having sensitive information in the subsequent frame in advance or perform other processing operations capable of avoiding the occurrence of cloud conference live broadcast accidents.

if the proportion of the character information is not less than the first preset proportion, matching the character information in the target subsequent frame with a preset keyword library, and determining the character sensitivity index of the target subsequent frame according to the matching result; and/or determining the proportion of image information in a target subsequent frame;

The frame sensitivity index of the media file is determined frame by frame, and in a specific implementation, different frames in the media file correspond to different frame sensitivity indexes one to one.

Wherein the predetermined residence time, in a specific implementation, may be 15 seconds, 20 seconds, 1 minute, or other residence times.

In the specific implementation, when the occupation ratio of the text information in the target subsequent frame is not less than the first preset proportion, since the text information in the target frame is matched with the preset emotion dictionary when the target subsequent frame is waited to become the currently pushed target frame, in order to perform the sensitivity detection of the complementary correction in advance on the target subsequent frame which is not pushed yet, the text sensitivity index of the target subsequent frame can be evaluated by adopting a direct matching mode of matching the text information in the target subsequent frame with the preset keyword library, so that the text information sensitivity determination process of each frame of the media file is more comprehensive and complete.

Similarly, in a specific implementation, when the ratio of the image information in the target subsequent frame is not less than the second preset ratio, if the target subsequent frame is waiting to become the currently pushed target frame, the representative image information in the target frame is matched with the sensitive image library, that is, only a part of representative images in the target frame are matched, so that, in order to perform the sensitivity detection of the target subsequent frame which is not pushed in advance and has complementary correction, the complete image sensitivity index of the target subsequent frame can be evaluated by adopting a relatively complete matching manner of matching the complete image information in the target subsequent frame with a plurality of sensitive images included in the sensitive image library, so that the image information sensitivity determination process of each frame of the media file is more complete and complete.

In a specific implementation, the target subsequent frame sensitivity index of the media file may be determined by respectively configuring corresponding weights for the text sensitivity index of the target subsequent frame and the complete image sensitivity index of the target subsequent frame, and then performing weighted summation to determine the target subsequent frame sensitivity index of the media file, or by determining the larger of the text sensitivity index of the target subsequent frame and the complete image sensitivity index of the target subsequent frame as the target subsequent frame sensitivity index of the media file, or by determining the average of the text sensitivity index of the target subsequent frame and the complete image sensitivity index of the target subsequent frame as the target subsequent frame sensitivity index of the media file.

In a specific implementation, corresponding weights may be respectively configured for the target frame sensitivity index and the target subsequent frame sensitivity index of the media file, and then a weighted sum is performed to determine the target file sensitivity index of the media file, or a larger one of the target frame sensitivity index and the target subsequent frame sensitivity index may be determined as the target file sensitivity index of the media file, or an average value of the target frame sensitivity index and the target subsequent frame sensitivity index may be determined as the target file sensitivity index of the media file.

It can be seen that, in the embodiment of the present application, when the frame sensitivity index of the media file is determined, the frame-by-frame determination is performed, and when the time for the terminal device to display the target frame reaches the preset retention time, the target subsequent frame of which the display sequence is located after the target frame and which is not yet pushed is obtained in advance, the text sensitivity index and/or the complete image sensitivity index of the target subsequent frame are determined by using an information matching manner with complementary correction property, which is different from the target frame, the target subsequent frame sensitivity index is determined, the target file sensitivity index of the media file is finally determined according to the target frame sensitivity index of the media file and the target subsequent frame sensitivity index of the media file, and the display manner of the terminal device for the media file is indicated according to the target file sensitivity index. Therefore, the server can determine the character information sensitivity and/or the image information sensitivity of each frame of the media file more comprehensively and completely, and the determination of the target frame sensitivity index can be corrected complementarily by determining the target subsequent frame sensitivity index, so that the completeness, the accuracy and the intelligence of the determination process of the media file sensitivity index can be improved.

Referring to fig. 7, in accordance with the embodiment shown in fig. 2, fig. 7 is a schematic structural diagram of a file sensitivity index determining apparatus based on a cloud conference according to an embodiment of the present application, as shown in fig. 7:

a file sensitivity index determining device based on a cloud conference is applied to a server, the server is in communication connection with terminal equipment, the terminal equipment is equipment for carrying out the cloud conference, and the device comprises:

the obtaining unit 201 is configured to obtain a target cloud conference hosting level and a media file display ratio from a terminal device.

The determining unit 202 is configured to determine a target preset display ratio corresponding to the target cloud conference hosting level according to a mapping relationship between the target cloud conference hosting level and the preset display ratio.

The detecting unit 203 is configured to detect whether the media file display ratio reaches a target preset display ratio.

The indicating unit 204 is configured to determine a target frame sensitivity index of the media file if the media file display ratio reaches a target preset display ratio, and indicate a display mode of the terminal device for the target frame according to the target frame sensitivity index.

It can be seen that in the apparatus provided in the embodiment of the present application, the obtaining unit obtains the hosting grade of the target cloud conference and the display ratio of the media file from the terminal device; the determining unit determines a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion; the detection unit detects whether the display proportion of the media file reaches a target preset display proportion; when the media file display proportion reaches the target preset display proportion, the indicating unit determines a target frame sensitivity index of the media file and indicates the display mode of the terminal equipment to the target frame according to the target frame sensitivity index. By adopting the device provided by the embodiment of the application, the target frame sensitivity index of the media file is determined when the display proportion of the media file reaches the target preset display proportion, and the display mode of the terminal equipment for the target frame is indicated according to the target frame sensitivity index, so that the occurrence of cloud conference accidents caused by the fact that the media file comprises sensitive information is avoided, and the cloud conference is ensured to be safely and smoothly carried out.

Specifically, in the embodiment of the present application, the functional units may be divided according to the method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.

The integrated units described above, if implemented in the form of software program modules and sold or used as separate products, may be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application, in essence or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Consistent with the embodiment shown in fig. 2, an electronic device is provided in an embodiment of the present application, please refer to fig. 8, fig. 8 is a schematic diagram illustrating a server structure of a hardware operating environment of an electronic device provided in an embodiment of the present application, and as shown in fig. 8, the electronic device includes a processor, a memory, and computer-executable instructions stored in the memory and operable on the processor, and when the computer-executable instructions are executed, the electronic device executes the instructions including any step of the cloud conference-based file sensitivity index determination method.

Wherein, the processor is a CPU (Central Processing Unit).

The memory may be a high-speed RAM memory, or may be a stable memory, such as a disk memory.

Those skilled in the art will appreciate that the configuration of the server shown in fig. 8 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

As shown in fig. 8, the memory may include computer-executable instructions for an operating system, a network communication module, and a cloud conference based file sensitivity index determination method. The operating system is used for managing and controlling hardware and software resources of the server and supporting the operation of executing instructions by the computer. The network communication module is used for realizing communication between each component in the memory and communication with other hardware and software in the server, and the communication may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000(Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), etc.

In the server shown in fig. 8, the processor is configured to execute computer-executable instructions for personnel management stored in the memory, and to implement the following steps: acquiring a target cloud conference host grade and a media file display ratio from terminal equipment; determining a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion; detecting whether the display proportion of the media file reaches a target preset display proportion or not; and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index.

For specific implementation of the server according to the present application, reference may be made to each embodiment of the file sensitivity index determining method based on the cloud conference, which is not described herein again.

An embodiment of the present application provides a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are executed on a communication apparatus, the communication apparatus is caused to perform the following steps: acquiring a target cloud conference host grade and a media file display ratio from terminal equipment; determining a target preset display proportion corresponding to the target cloud conference host level according to a mapping relation between the target cloud conference host level and the preset display proportion; detecting whether the display proportion of the media file reaches a target preset display proportion or not; and if the media file display proportion reaches the target preset display proportion, determining a target frame sensitivity index of the media file, and indicating a display mode of the terminal equipment for the target frame according to the target frame sensitivity index. The computer includes an electronic device.

The electronic terminal equipment comprises a mobile phone, a tablet computer, a personal digital assistant, wearable equipment and the like.

The computer-readable storage medium may be an internal storage unit of the electronic device described in the above embodiments, for example, a hard disk or a memory of the electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the electronic device. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the electronic device. Computer-readable storage media are used to store computer-executable instructions and data as well as other computer-executable instructions and data needed by electronic devices. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

For specific implementation of the computer-readable storage medium related to the present application, reference may be made to each embodiment of the cloud conference-based file sensitivity index determining method, which is not described herein again.

Embodiments of the present application provide a computer program product, where the computer program product includes a computer program operable to make a computer perform part or all of the steps of any one of the cloud conference based file sensitivity index determination methods as described in the above method embodiments, and the computer program product may be a software installation package.

It should be noted that, for the sake of simplicity, any of the foregoing embodiments of the method for determining a document sensitivity index based on a cloud conference are all described as a series of combinations of actions, but it should be understood by those skilled in the art that the present application is not limited by the described sequence of actions, as some steps may be performed in other sequences or simultaneously according to the present application. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

The foregoing embodiments of the present application are introduced in detail, and the principles and implementations of a cloud conference-based document sensitivity index determination method according to the present application are explained herein by applying specific examples, and the descriptions of the foregoing embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the method for determining a document sensitivity index based on a cloud conference, the specific implementation and the application scope may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present application.

While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

It will be understood by those of ordinary skill in the art that all or part of the steps of the various methods of any of the above method embodiments of the cloud conference based file sensitivity index determination method may be implemented by instructing associated hardware by a program, which may be stored in a computer-readable memory, and the memory may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

Obviously, those skilled in the art may make various changes and modifications to the file sensitivity index determination method based on cloud conference provided in the present application without departing from the spirit and scope of the present 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

1. A file sensitivity index determining method based on a cloud conference is applied to a server, the server is in communication connection with a terminal device, the terminal device is a device for performing the cloud conference, and the method comprises the following steps:

acquiring a target cloud conference host level and a media file display ratio from the terminal equipment, wherein the target cloud conference host level is comprehensively determined according to the host total duration, host total frequency, host accident occurrence frequency and the obtained host evaluation aspect of the current cloud conference host;

detecting whether the display proportion of the media file reaches the target preset display proportion or not;

2. The method of claim 1, wherein the target frame sensitivity index comprises a target frame text sensitivity index, and wherein determining a target frame sensitivity index for a media file comprises:

determining the proportion of character information in the target frame;

if the proportion of the text information is smaller than a first preset proportion, matching the text information in the target frame with a preset keyword library, and determining the text sensitivity index of the target frame according to a matching result;

if the occupation ratio of the character information is not smaller than the first preset proportion, matching the character information in the target frame with an emotion dictionary to obtain an emotion sensitivity index of the target frame;

and determining the target frame text sensitivity index according to the character sensitivity index or the emotion sensitivity index.

3. The method of claim 2, wherein the emotion dictionary comprises a positive emotion thesaurus and a non-positive emotion thesaurus, and wherein the method further comprises:

acquiring target field information corresponding to the target cloud conference;

determining a target domain term word bank corresponding to the target cloud conference according to the target domain information;

the matching of the character information in the target frame and the emotion dictionary to obtain the emotion sensitivity index of the target frame comprises the following steps:

4. The method of claim 3, wherein the matching the text information in the target frame with the adjusted emotion dictionary to obtain the emotion sensitivity index of the target frame comprises:

acquiring conference attributes of the target cloud conference, determining information supervision levels of the target cloud conference according to the conference attributes of the target cloud conference, and obtaining target emotion sensitivity weights according to the information supervision levels, wherein the information supervision levels are used for indicating the supervision strictness degree of cloud conference contents;

and calculating the emotion sensitivity index of the target frame according to the target emotion sensitivity weight and the emotion score corresponding to each target vector phrase.

5. The method of claim 1, wherein the target frame sensitivity index comprises a target frame image sensitivity index, and wherein determining a target frame sensitivity index for a media file comprises:

determining the proportion of image information in a target frame;

if the image information accounts for not less than the second preset proportion, determining representative image information of the image information in the target frame, matching the representative image information with the sensitive image library, and determining a representative image sensitivity index of the target frame according to a matching result;

6. The method of claim 5, wherein matching the representative image information with the sensitive image library and determining the representative image sensitivity index of the target frame according to the matching result comprises:

obtaining a target key point feature vector of the image information in the target frame according to an image processing algorithm;

determining a plurality of corresponding image similarities between the image information in the target frame and the plurality of sensitive images according to the target key point feature vector;

acquiring attribute information of the target cloud conference, determining an information supervision level according to the attribute information of the target cloud conference, and obtaining a target image sensitivity weight according to the information supervision level;

and determining a representative image sensitivity index of the target frame according to the image similarities and the target image sensitivity weight.

7. The method according to any one of claims 1 to 6, wherein the indicating, according to the target frame sensitivity index, a display manner of the target frame by the terminal device comprises:

if the target frame sensitivity index is smaller than or equal to a first preset index, instructing the terminal equipment to perform delayed display processing on the target frame;

if the target frame sensitivity index is larger than the first preset index and smaller than or equal to a second preset index, the terminal equipment is instructed to carry out fuzzy display processing on the target frame;

and if the target frame sensitivity index is larger than the second preset index, instructing the terminal equipment to stop displaying the media file.

8. The device for determining the file sensitivity index based on the cloud conference is applied to a server, the server is in communication connection with a terminal device, the terminal device is a device for carrying out the cloud conference, and the device comprises:

the acquisition unit is used for acquiring a target cloud conference host grade and a media file display ratio from the terminal equipment, wherein the target cloud conference host grade is comprehensively determined according to the current cloud conference host total host duration, host total frequency, host accident occurrence frequency and the obtained host evaluation aspect;

the detection unit is used for detecting whether the media file display proportion reaches the target preset display proportion or not;

and the indicating unit is used for determining a target frame sensitivity index of the media file if the media file display proportion reaches the target preset display proportion, and indicating the display mode of the terminal equipment to the target frame according to the target frame sensitivity index.

9. An electronic device comprising a processor, a memory, and computer-executable instructions stored on the memory and executable on the processor, which when executed cause the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon computer instructions which, when run on a communication device, cause the communication device to perform the method of any one of claims 1-7.