CN110505490A

CN110505490A - Multi-medium data recognition methods and system

Info

Publication number: CN110505490A
Application number: CN201810481057.6A
Authority: CN
Inventors: 丁一; 肖长杰; 廉亚男; 徐刚; 黄海宇
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-05-18
Filing date: 2018-05-18
Publication date: 2019-11-26

Abstract

This application discloses a kind of multi-medium data recognition methods and systems.Wherein, this method comprises: identification whether there is invalid data from the first data collected in original multimedia data；If there are invalid datas in the first data, collected second data from original multimedia data or data recording are obtained；It identifies in the second data with the presence or absence of invalid data；If in the second data, there are invalid datas, it is determined that original multimedia data belongs to illegal multi-medium data.Present application addresses the low technical problems of multi-medium data recognition methods recognition efficiency in the prior art and accuracy.

Description

Multi-medium data recognition methods and system

Technical field

This application involves multi-medium data security fields, in particular to a kind of multi-medium data recognition methods and are System.

Background technique

Multi-medium data is broadcast live, it is effective in order to ensure video content such as in the application scenarios of net cast Health needs to audit video content.Currently used multi-medium data recognition methods is to be broadcast live in multi-medium data In the process, multi-medium data is intercepted according to fixed interception frequency, and by being identified to the data being truncated to, judged In the data being truncated to whether there is sensitive information or doubtful sensitive information, so that it is determined that multi-medium data whether pass through it is careful Core.

But the particularity based on cost and real-time live broadcast, existing multi-medium data recognition methods can only be set for the overall situation Fixed screenshot frequency is set, causes some in multi-medium data there are sensitive information or the time point quilt of doubtful sensitive information It omits, in addition, needing to carry out human configuration and manual confirmation one by one for particular video frequency.In order to improve recognition accuracy, need On the basis of Verify in System, secondary audit is carried out by manpower intervention, it is time-consuming and laborious.

For the low problem of multi-medium data recognition methods recognition efficiency in the prior art and accuracy, not yet mention at present Effective solution scheme out.

Summary of the invention

The embodiment of the present application provides a kind of multi-medium data recognition methods and system, in the prior art at least to solve Multi-medium data recognition methods recognition efficiency and the low technical problem of accuracy.

According to the one aspect of the embodiment of the present application, a kind of multi-medium data recognition methods is provided, comprising: identify from original It whether there is invalid data in beginning multi-medium data in collected first data；If there are invalid data in the first data, Then obtain collected second data from original multimedia data or data recording, wherein data recording is former by recording The data that beginning multi-medium data obtains；It identifies in the second data with the presence or absence of invalid data；If existed in the second data illegal Data, it is determined that original multimedia data belongs to illegal multi-medium data.

According to the another aspect of the embodiment of the present application, a kind of multi-medium data recognition methods is additionally provided, comprising: play former Collected first data in beginning multi-medium data；There are in the case where invalid data in the first data, play from original more Collected second data in media data or data recording, wherein data recording is to be obtained by recording original multimedia data The data arrived；There are in the case where invalid data in determining the second data, the recognition result of original multimedia data is shown, In, recognition result belongs to illegal multi-medium data for characterizing original multimedia data.

According to the another aspect of the embodiment of the present application, a kind of multi-medium data identifying system is additionally provided, comprising: identification is set It is standby, it whether there is invalid data from the first data collected in original multimedia data for identification；Recording arrangement is used for Data recording is obtained by recording original multimedia data；It identifies equipment, is connect with recording arrangement, if being also used to the first data In there are invalid data, then obtain collected second data from original multimedia data or data recording, and identify second It whether there is invalid data in data, if there are invalid datas in the second data, it is determined that original multimedia data belongs to non- Method multi-medium data.

According to the another aspect of the embodiment of the present application, a kind of storage medium is additionally provided, storage medium includes the journey of storage Sequence, wherein equipment where control storage medium executes following steps in program operation: identification is adopted from original multimedia data It whether there is invalid data in the first data collected；If there are invalid datas in the first data, obtain from original more matchmakers Collected second data in volume data or data recording, wherein data recording is to be obtained by recording original multimedia data Data；It identifies in the second data with the presence or absence of invalid data；If in the second data, there are invalid datas, it is determined that original more Media data belongs to illegal multi-medium data.

According to the another aspect of the embodiment of the present application, a kind of processor is additionally provided, processor is used to run program, In, program executes following steps when running: identification is from the first data collected in original multimedia data with the presence or absence of non- Method data；If there are invalid datas in the first data, obtain collected from original multimedia data or data recording Second data, wherein data recording is the data obtained by recording original multimedia data；Identify in the second data whether deposit In invalid data；If in the second data, there are invalid datas, it is determined that original multimedia data belongs to illegal multi-medium data.

According to the another aspect of the embodiment of the present application, a kind of multi-medium data identifying system is additionally provided, comprising: processing Device；And memory, it is connect with processor, for providing the instruction for handling following processing step for processor: identifying from original It whether there is invalid data in multi-medium data in collected first data；If there are invalid data in the first data, Obtain collected second data from original multimedia data or data recording, wherein data recording is original by recording The data that multi-medium data obtains；It identifies in the second data with the presence or absence of invalid data；If there is illegal number in the second data According to, it is determined that original multimedia data belongs to illegal multi-medium data.

In the embodiment of the present application, can identify whether there is from the first data collected in original multimedia data Invalid data, when, there are when invalid data, further acquisition is adopted from original multimedia data or data recording in the first data The second data collected, and identify and whether there is invalid data in the second data, when determining that there are invalid datas in the second data When, it can determine that original multimedia data belongs to illegal multi-medium data, to realize the purpose of multi-medium data audit.

It is easily noted that, since in determining the first data, there are after invalid data, initial multimedia can be passed through Collected second data are identified in data or data recording, to determine whether original multimedia data belongs to non-fado matchmaker Volume data, compared with prior art, without being audited according to fixed audit frequency, and without by manually carrying out secondary examine Core reaches raising recognition accuracy, saves recognition time and cost, improves recognition efficiency, promotes the technology effect of user experience Fruit.

Scheme provided by the present application solves multi-medium data recognition methods recognition efficiency in the prior art and standard as a result, The low technical problem of exactness.

Detailed description of the invention

The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:

Fig. 1 be according to the embodiment of the present application it is a kind of for realizing multi-medium data recognition methods terminal (or move Dynamic equipment) hardware block diagram；

Fig. 2 is to be used as to connect according to a kind of terminal for realizing multi-medium data recognition methods of the embodiment of the present application The schematic diagram of receiving end；

Fig. 3 is the flow chart according to a kind of multi-medium data recognition methods of the embodiment of the present application 1；

Fig. 4 is the flow chart according to a kind of optional multi-medium data recognition methods of the embodiment of the present application；

Fig. 5 is the flow chart according to the optional multi-medium data recognition methods of another kind of the embodiment of the present application；

Fig. 6 is the flow chart according to a kind of multi-medium data recognition methods of the embodiment of the present application 2；

Fig. 7 is the schematic diagram according to a kind of multi-medium data identification device of the embodiment of the present application 3；

Fig. 8 is the schematic diagram according to a kind of multi-medium data identification device of the embodiment of the present application 4；

Fig. 9 is the schematic diagram according to a kind of multi-medium data identifying system of the embodiment of the present application 5；

Figure 10 is the schematic diagram according to a kind of optional multi-medium data identifying system of the embodiment of the present application 5；

Figure 11 is the schematic diagram according to the optional multi-medium data identifying system of another kind of the embodiment of the present application 5；And

Figure 12 is the structural block diagram according to a kind of terminal of the embodiment of the present application.

Specific embodiment

In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection It encloses.

It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, " Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein can in addition to illustrating herein or Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product Or other step or units that equipment is intrinsic.

Firstly, the part noun or term that occur during the embodiment of the present application is described are suitable for following solution It releases:

Network direct broadcasting: it can be the same time by network in different intercommunion platform viewing videos.

Sensitive information: it is related to the content of the bad behaviors such as pornographic, vulgar, violence.

CDN: content distributing network, full name are Content Delivery Network, by placing section everywhere in network One on the existing Internet basic layer intelligent virtual network that point server is constituted, can be in real time according to network flow Amount and the connection of each node, load state and to the integrated informations such as the distance of user and response time by the request of user again It is oriented on the service node nearest from user.

OSS storage service: object storage service, Object Storage Service, be a kind of magnanimity, safety, it is low at Originally, highly reliable cloud storage service device.

Embodiment 1

According to the embodiment of the present application, a kind of embodiment of multi-medium data recognition methods is provided, it should be noted that In The step of process of attached drawing illustrates can execute in a computer system such as a set of computer executable instructions, also, It, in some cases, can be to be different from shown in sequence execution herein although logical order is shown in flow charts The step of out or describing.

Embodiment of the method provided by the embodiment of the present application one can be in mobile terminal, terminal or similar fortune It calculates and is executed in device.Fig. 1 shows a kind of terminal (or mobile device) for realizing multi-medium data recognition methods Hardware block diagram.As shown in Figure 1, terminal 10 (or mobile device 10) may include one or more (adopts in figure With 102a, 102b ... ..., 102n is shown) processor 102 (processor 102 can include but is not limited to Micro-processor MCV or The processing unit of programmable logic device FPGA etc.), memory 104 for storing data and the biography for communication function Defeated device 106.It in addition to this, can also include: display, input/output interface (I/O interface), universal serial bus (USB) Port (a port that can be used as in the port of I/O interface is included), network interface, power supply and/or camera.This field is general Logical technical staff is appreciated that structure shown in FIG. 1 is only to illustrate, and does not cause to limit to the structure of above-mentioned electronic device. For example, terminal 10 may also include the more perhaps less component than shown in Fig. 1 or have different from shown in Fig. 1 Configuration.

It is to be noted that said one or multiple processors 102 and/or other data processing circuits lead to herein Can often " data processing circuit " be referred to as.The data processing circuit all or part of can be presented as software, hardware, firmware Or any other combination.In addition, data processing circuit for single independent processing module or all or part of can be integrated to meter In any one in other elements in calculation machine terminal 10 (or mobile device).Such as knowledge involved in the embodiment of the present application Other equipment, the data processing circuit control (such as the choosing for the variable resistance end path connecting with interface as a kind of processor It selects).

Memory 104 can be used for storing the software program and module of application software, such as more matchmakers in the embodiment of the present application Corresponding program instruction/the data storage device of volume data identification method, processor 102 are stored in memory 104 by operation Software program and module realize that above-mentioned multi-medium data is known thereby executing various function application and data processing Other method.Memory 104 may include high speed random access memory, may also include nonvolatile memory, such as one or more magnetic Property storage device, flash memory or other non-volatile solid state memories.In some instances, memory 104 can further comprise The memory remotely located relative to processor 102, these remote memories can pass through network connection to terminal 10. The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.

Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include The wireless network that the communication providers of terminal 10 provide.In an example, transmitting device 106 includes that a network is suitable Orchestration (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to Internet is communicated.In an example, transmitting device 106 can be radio frequency (Radio Frequency, RF) module, For wirelessly being communicated with internet.

Display can such as touch-screen type liquid crystal display (LCD), the liquid crystal display aloow user with The user interface of terminal 10 (or mobile device) interacts.

Hardware block diagram shown in fig. 1 acts not only as the example of above-mentioned terminal 10 (or mobile device) Property block diagram, is also used as the exemplary block diagram of above-mentioned server, and in a kind of alternative embodiment, Fig. 2 shows use with block diagram A kind of embodiment of the above-mentioned terminal shown in FIG. 1 10 (or mobile device) as receiving end.As shown in Fig. 2, computer Terminal 10 (or mobile device) via data network connection or can be electronically connected to one or more clients.A kind of optional reality It applies in example, above-mentioned terminal 10 (or mobile device) can be server.Data network connection can be LAN connection, Wide area network connection, internet connection or other kinds of data network connection.Terminal 10 (or mobile device) can be held Row is to be connected to the network service by a server (such as security server) or the execution of one group of server.Network server is Network-based user service, such as social networks, cloud resource, Email, on-line payment or other application on site.

Under above-mentioned running environment, this application provides multi-medium data recognition methods as shown in Figure 3.Fig. 3 is basis A kind of flow chart of the multi-medium data recognition methods of the embodiment of the present application 1.As shown in figure 3, this method may include walking as follows It is rapid:

Step S32, identification whether there is invalid data from the first data collected in original multimedia data.

Specifically, above-mentioned original multimedia data can be the video of current live, audio etc., in initial multimedia number It, can be by being intercepted to original multimedia data, for example, screenshot is carried out to video, to collect during live streaming First data, the first above-mentioned data can be image, audio etc., and the application is not specifically limited in this embodiment, and implement in the application In example, it is described in detail so that multi-medium data is video as an example；Since original multimedia data is to be shot to upload by user, In order to ensure effective health of original multimedia data, need to judge in original multimedia data with the presence or absence of invalid data.

Optionally, invalid data is used to characterize the data that the probability for belonging to sensitive information is greater than or equal to predetermined probabilities.

Specifically, above-mentioned invalid data can be sensitive information or doubtful sensitive information.

Step S34 is obtained from original multimedia data or data recording if there are invalid datas in the first data Collected second data, wherein data recording is the data obtained by recording original multimedia data.

It specifically,, can be according to instruction in order to improve recognition accuracy since original multimedia data is during live streaming Format original multimedia data is recorded, so as to by carrying out secondary audit to data recording；In multimedia number According in the scene for video, the second above-mentioned data can be image.

It should be noted that improving recognition accuracy in order to avoid omitting there are the time point of invalid data, can using It is turned up in the interception frequency for intercepting the first data, cycle time will be also intercepted, so as to get more second data.

Step S36 is identified and be whether there is invalid data in the second data.

It should be noted that since the interception frequency of the first data of interception is different with the interception interception frequency of the second data, The first data and the second data got can be the same or different, thus invalid data present in the second data and Invalid data present in one data may be the same or different.

Step S38, if there are invalid datas in the second data, it is determined that original multimedia data belongs to illegal multimedia Data.

In a kind of optional scheme, during net cast, server can be audited by video to original view Frequency carries out screenshot, and judges with the presence or absence of sensitive information or doubtful sensitive information in the first image, if it does not exist, then continuing Screenshot is carried out to original video according to original intercepted frequency, if it is present the interception frequency of screenshot can be turned up, according to tune Interception frequency after whole carries out screenshot to original video, further judges in the second image with the presence or absence of sensitive information or doubtful Sensitive information, if it is present can determine that, there are sensitive information in original video, which belongs to violated video, on The main broadcaster for passing the video is violated main broadcaster.

In another optional scheme, during net cast, can in advance according to specified format, record at Recorded video is simultaneously saved, while can be audited server by video and be carried out screenshot to original video, and judge the first figure It whether there is sensitive information or doubtful sensitive information as in, if it does not exist, then continue to carry out screenshot to original video, if In the presence of, then the interception frequency of screenshot can be turned up, according to interception frequency adjusted to the recorded video prerecorded into Row screenshot further judges with the presence or absence of sensitive information or doubtful sensitive information in the second image, if it is present can be true Determine there are sensitive information in original video, which belongs to violated video, and the main broadcaster for uploading the video is violated main broadcaster.

It should be noted that above two scheme in practical review process, can according to need and be selected, It can choose only with one such scheme, two schemes can also be combined.

It should also be noted that, each auditing result can be returned in time after by being audited to original video User is assigned, thus the violated video of first time real-time informing user and the main broadcaster for needing emphasis audit to pay close attention to.

Fig. 4 is according to a kind of flow chart of optional multi-medium data recognition methods of the embodiment of the present application, and Fig. 5 is basis The flow chart of the optional multi-medium data recognition methods of the another kind of the embodiment of the present application is straight with video below with reference to Fig. 4 and Fig. 5 The application preferred embodiment is described in detail for the application scenarios broadcast.

Multi-medium data identifying system as shown in Figure 4 and Figure 5 mainly includes following part: main broadcaster, user, CDN node, CDN live streaming center source station, the service of net cast screenshot, service is recorded in net cast, OSS storage service, net cast video are examined Core service and the secondary review service of net cast.Wherein, main broadcaster can have plug-flow tool by oneself by live streaming platform, and OBS plug-flow is set The equipment such as standby, mobile phone can be broadcast live plug-flow after through legitimate verification；CDN node can be the live streaming edge CDN Node facilitates user to access nearby, can shorten the time delay that user accesses live streaming plug-flow；CDN live streaming center source station can be directly CDN source station is broadcast, the multi-medium data of live streaming is received and stored；Video interception service is being regarded mainly for the screenshot service of video In frequency audit, screenshot is main audit means；Net cast is recorded service and is mainly used for real-time live broadcast video according to specified Format, record and at video file and saved；OSS storage service is used to store the video recorded；Net cast video is examined Core service is mainly used for can receive the screenshot that video interception service generates, and carries out video audit and result readjustment；Video Secondary review service is broadcast live and is mainly used for the first trial for the audit service of net cast video as a result, carrying out rules customization, and lead to The auditing rule for crossing setting carries out automatic review to first trial result, wherein review depends on the recorded video of original video.

As shown in figure 4, main broadcaster gives original video live streaming plug-flow to CDN node (such as Fig. 4 in a kind of preferred embodiment In step 41 shown in), as CDN node live streaming plug-flow to CDN be broadcast live center source station (as shown in the step 42 in Fig. 4), video Live streaming screenshot service can be broadcast live in the source station of center from CDN and carry out screenshot drawing stream (as shown in the step 43 in Fig. 4), and judgement is No progress high frequency audits screenshot (as shown in the step 44 in Fig. 4), if auditing screenshot without high frequency, audits according to the overall situation Frequency, such as key frame audit frequency of 10s carry out screenshot (as shown in the step 45 in Fig. 4), the audit of net cast video Service can audit screenshot, judge in screenshot with the presence or absence of sensitive information or the doubtful sensitive information (step in such as Fig. 4 Shown in rapid 46), if it is present the doubtful violated threshold value of triggering, and configure net cast screenshot service and carry out high frequency audit screenshot (as shown in the step 47 in Fig. 4), net cast screenshot service determine that carrying out high frequency audits screenshot, can audit frequency according to high frequency Rate, such as non-key frame audit frequency of 1s carry out screenshot, and the audit service of net cast video can audit screenshot (as shown in the step 48 in Fig. 4), and adjust back user (as shown in the step 49 in Fig. 4).

Through the above scheme, once video auditing system is found with the presence of screenshot sensitive information or doubtful sensitive information, Then automatic trigger audit frequency adaptively adjust, under send instructions to screenshot system, can start after being adjusted to original video High frequency audit frequency audited, and user is adjusted back, to reach the identification for promoting video audit during net cast Rate, and reduce manpower intervention.

As shown in figure 5, in another preferred embodiment, step 51 is to 53 and the step 41 in Fig. 4 to 43 phases in Fig. 5 Together, the service of net cast screenshot can carry out screenshot (as shown in the step 54 in Fig. 5) according to overall situation audit frequency, net cast Video audit service can audit (such as step 55 institute in Fig. 5 screenshot by the video auditing rule of user configuration Show), judge with the presence or absence of sensitive information or doubtful sensitive information in screenshot, and by auditing result readjustment user (in such as Fig. 5 Shown in step 56), if it is present the secondary review service of triggering net cast carries out the secondary audit (step in such as Fig. 5 automatically Shown in 57).Net cast, which records service and can be broadcast live in the source station of center record drawing from CDN, flows (such as step 58 institute in Fig. 5 Show), and recorded video is stored in OSS storage server (as shown in the step 59 in Fig. 5), the secondary review service of net cast From the recorded video (as shown in the step 510 in Fig. 5) for needing secondary audit time section is obtained in OSS storage service, that is, can To obtain sensitization time point toward for the previous period or the recorded video of front and back a period of time, for recorded video, screenshot again, The screenshot period is less than the global screenshot period, such as key frame audit frequency of 3s carries out screenshot, and the view for passing through user configuration Frequency is audited time review rule and is audited (as shown in the step 511 in Fig. 5) to recorded video, judges in screenshot with the presence or absence of quick Information or doubtful sensitive information are felt, if it is present auditing result adjusts back user (as shown in the step 512 in Fig. 5) Meanwhile retaining the mark of evidence video, and be saved in specified storage catalogue (as shown in the step 513 in Fig. 5).

Through the above scheme, can in net cast real-time perfoming content auditing, and discovery sensitive information or doubt When like sensitive information, automatic secondary audit is carried out, thus reach the discrimination that video audit is promoted during net cast, and Reduce manpower intervention.

It should be noted that service is recorded in net cast screenshot service as shown in Figure 4 and Figure 5, net cast, OSS is deposited Storage service, net cast video audit service and the secondary review service of net cast can be the service in the same server, The service being also possible in different server, that is, corresponding server is net cast capture server, net cast Video Record Processor, OSS storage server, net cast video audit server and the secondary review server of net cast.

Scheme provided by the above embodiments of the present application 1 can identify collected first from original multimedia data It whether there is invalid data in data, when there are when invalid data, further obtaining from original multimedia data in the first data Or collected second data in data recording, and identify and whether there is invalid data in the second data, when determining the second data In there are that when invalid data, can determine that original multimedia data belongs to illegal multi-medium data, to realize multi-medium data The purpose of audit.

The scheme of above-described embodiment 1 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

In the above embodiments of the present application, in step S34, obtain before the second data collected in data recording, it should Method can also include the following steps:

Step S310 obtains play time of first data in original multimedia data.

Step S312 determines the corresponding recording time section of play time, wherein recording time section be play time before or Preset time period later.

Specifically, in order to improve recognition accuracy, first time audit after, need to first time audit in sensitivity when Between point carry out secondary review, the original video in order to ensure the accuracy of secondary review, near available sensitization time point；On The preset time period stated can be the recording time that user wants to the recorded video got, can be quasi- according to practical identification Exactness, recognition efficiency and cost are configured.

Step S314 obtains data recording by recording the original multimedia data in the recording time section.

In a kind of optional scheme, during net cast, when determining that there are sensitive informations in some screenshot image Or when doubtful sensitive information, a period of time can be chosen before and after the play time of the image or for the previous period as recording when Between, and corresponding original video is recorded, obtain recorded video.

Original video is recorded in time it should be noted that ensuring that, it can be while net cast, to entire Original video is recorded, can be from whole when determining in some screenshot image there are when sensitive information or doubtful sensitive information A period of time or recorded video for the previous period before and after the play time of the image are selected in a recorded video, obtain needing into The recorded video of row screenshot.

It should also be noted that, step S314 can be changed are as follows: from carrying out recording obtained view to entire original video In frequency file, the corresponding video of recording time section is obtained, recorded video is obtained.

In the above embodiments of the present application, after determining that original multimedia data belongs to illegal multi-medium data, label record Data processed, and store the data recording after label.

In a kind of optional scheme, during net cast, due to being recorded to original video, in order to retain Corresponding evidence, there are sensitive information or doubtful sensitive informations in determining recorded video, namely determine that video belongs to illegally After video, which can be marked, and the recorded video after label is stored, thus when needing to prove It, can quick obtaining be sensitive to existing directly from a large amount of recorded video according to label when video belongs to the evidence of illegal video The recorded video of information or doubtful sensitive information.

Through the above scheme, by the way that data recording to be marked and store, identification certainty is promoted to reach Effect.

It is the party in situation collected in original multimedia data in the second data in the above embodiments of the present application Method may include steps of:

Step S316 intercepts initial multimedia according to the first frequency acquisition in the playing process of original multimedia data Data obtain the first data.

Specifically, the first above-mentioned frequency acquisition can be global audit frequency, such as can be key frame of 10s and examine Nuclear frequency can be configured by user.

Step S318, when there are when invalid data, being turned up the first frequency acquisition in the first data, first after being adjusted Frequency acquisition.

Specifically, above-mentioned the first frequency acquisition adjusted can be high frequency audit frequency, such as to can be 1s primary Non-key frame audits frequency, can be configured by user.

Step S320 intercepts original multimedia data according to the first frequency acquisition adjusted, obtains the second data.

In a kind of optional scheme, as shown in figure 4, starting to be broadcast live in original video for net cast screenshot service Later, screenshot is carried out first, in accordance with the first frequency acquisition, and the first image transmitting is audited into service to net cast video and is carried out Audit, if do not cut according still further to the first frequency acquisition in the first image there are sensitive information or doubtful sensitive information Figure is changed to carry out screenshot according to the first frequency acquisition adjusted, obtains the second image, and the second image transmitting is straight to video It broadcasts video audit service to be audited, so that it is determined that whether original video belongs to illegal video.

It is in situation collected in data recording in the second data, this method can be in the above embodiments of the present application Include the following steps:

Step S322 intercepts initial multimedia according to the first frequency acquisition in the playing process of original multimedia data Data obtain the first data.

Specifically, the first above-mentioned frequency acquisition can be conventional audit frequency, such as primary, the Ke Yiyou that can be 10s User is configured.

Step S324, when there are when invalid data, intercepting data recording in the first data according to the second frequency acquisition, obtain Second data, and, continue to intercept original multimedia data according to the first frequency acquisition, wherein the second frequency acquisition is greater than first Frequency acquisition.

Specifically, the second above-mentioned frequency acquisition can the period high for conventional audit frequency namely screenshot than conventional end, For example, conventional audit frequency is 10s primary, then it is primary to can be 3s for the second frequency acquisition, can be configured by user.

In a kind of optional scheme, as shown in figure 5, since the secondary review service of net cast is carried out to recorded video Audit can carry out simultaneously with the audit service of net cast video, therefore, can be original for net cast screenshot service Screenshot is carried out to original video according to the first frequency acquisition always during net cast, and the first image transmitting is straight to video Video audit service is broadcast to be audited, once find that there are sensitive information or doubtful sensitive informations in the first image, then it can be with Triggering carries out screenshot to recorded video according to the second frequency acquisition, and gives net cast secondary review service the second image transmitting It is audited, to realize the automatic progress secondary audit of video.

In the above embodiments of the present application, step S32 is identified and be whether there is invalid data or step S36 in the first data, It identifies in the second data and includes: with the presence or absence of invalid data

Step S326 determines the marking value of the first data or the second data.

First data are compared by step S328 with the first default marking value and the second default marking value, or by second The marking value of data is compared with the first default marking value and the second default marking value.

Specifically, the first above-mentioned default marking value can be determine the first data or the second data there are sensitive information or The doubtful violation threshold value of doubtful sensitive information, the default marking value of above-mentioned second, which can be, determines the first data or the second data not There are the non-violation threshold values of sensitive information or doubtful sensitive information, for example, qualifying is 60 if violated sensitivity score is 90 points Point, then the by stages 80-90 can be preset, as doubtful violation threshold value, and presets 60 points as non-violation threshold value, if The marking value of image is greater than or equal to the threshold value, can determine in image there are sensitive information or doubtful sensitive information, need Adjustment audit frequency carries out secondary audit.

It should be noted that in the embodiment as shown in fig.4, doubtful violation threshold value can be set into multiple, and difference is doubted Different like the corresponding audit frequency of violation threshold value, marking value is higher in doubtful violation threshold value, shows that there are sensitive informations in image Or the probability of doubtful sensitive information is higher, in order to improve recognition accuracy, corresponding audit frequency is higher, and the screenshot period gets over It is short, so as to determine whether original video belongs to illegal video in time.

Step S330, if the marking value of the first data or the second data is greater than or equal to the first default marking value, really There are invalid datas in fixed first data or the second data.

Step S332, if the marking value of the first data or the second data is less than or equal to the second default marking value, really Invalid data is not present in fixed first data or the second data.

In a kind of optional scheme, original video is audited in order to realize, can by the first image or Second image is given a mark, and judges whether the marking value of the first image or the second image is greater than or equal to doubtful violated threshold value, If it is greater than or be equal to, then can determine that there are sensitive information or doubtful sensitive informations in the first data or the second data；Such as Fruit is less than, then further judges whether the marking value of the first image or the second image is less than or equal to non-violation threshold value, if It is less than or equal to, then can determines that there is no sensitive information or doubtful sensitive informations in the first data or the second data.

In the above embodiments of the present application, in step S32, identify from the first data collected in original multimedia data Before invalid data, original multimedia data is obtained from source server, wherein original multimedia data is by pushing Equipment pushes to source server.

Specifically, above-mentioned source server can be CDN live streaming center source station as shown in Figure 4 and Figure 5, and above-mentioned push is set It is standby to can be the plug-flow tool that main broadcaster in Fig. 4 and Fig. 5 uses, the equipment such as OBS flow pulling equipment, mobile phone.

In a kind of optional scheme, as shown in Figure 4 and Figure 5, main broadcaster can have plug-flow tool by oneself by live streaming platform, The equipment such as OBS flow pulling equipment, mobile phone, after through legitimate verification, by original video live streaming plug-flow to CDN node, by CDN Node is broadcast live plug-flow and is stored to CDN live streaming center source station, so that the service of net cast screenshot can carry out original video Screenshot, net cast are recorded service and can be recorded to original video.

It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application It is necessary.

Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much In the case of the former be more preferably embodiment.Based on this understanding, the technical solution of the application is substantially in other words to existing The part that technology contributes can be embodied in the form of software products, which is stored in a storage In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate Machine, server or network equipment etc.) execute method described in each embodiment of the application.

Embodiment 2

According to the embodiment of the present application, a kind of embodiment of multi-medium data recognition methods is additionally provided, it should be noted that Step shown in the flowchart of the accompanying drawings can execute in a computer system such as a set of computer executable instructions, and It, in some cases, can be to be different from sequence execution institute herein and although logical order is shown in flow charts The step of showing or describing.

Fig. 6 is the flow chart according to a kind of multi-medium data recognition methods of the embodiment of the present application 2.As shown in fig. 6, the party Method may include steps of:

Step S62 plays collected first data from original multimedia data.

Specifically, above-mentioned original multimedia data can be the video of current live, audio etc., in initial multimedia number It, can be by being intercepted to original multimedia data, for example, screenshot is carried out to video, to collect during live streaming First data, the first above-mentioned data can be image, audio etc., and the application is not specifically limited in this embodiment, and implement in the application In example, it is described in detail so that multi-medium data is video as an example.

Step S64, there are in the case where invalid data, play from original multimedia data or record number in the first data Collected second data in, wherein data recording is the data obtained by recording original multimedia data.

Specifically, since original multimedia data is to be shot to upload by user, in order to ensure original multimedia data Effectively health needs to judge that, with the presence or absence of invalid data in original multimedia data, above-mentioned invalid data can be sensitive letter Breath or doubtful sensitive information；It, can be according to finger in order to improve recognition accuracy in original multimedia data during live streaming The format of order records original multimedia data, so as to by carrying out secondary audit to data recording；In multimedia Data are in the scene of video, and the second above-mentioned data can be image.

Step S66, there are the identification knots in the case where invalid data, showing original multimedia data in the second data Fruit, wherein recognition result belongs to illegal multi-medium data for characterizing original multimedia data.

Scheme provided by the above embodiments of the present application 2 can play collected first from original multimedia data Data can be identified with the presence or absence of invalid data in the first data, there are in the case where invalid data in the first data, be played Collected second data from original multimedia data or data recording, and identify in the second data with the presence or absence of illegal number According to there are in the case where invalid data in the second data, the recognition result of original multimedia data being shown, to realize more matchmakers The purpose of volume data audit.

The scheme of above-described embodiment 2 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

Embodiment 3

According to the embodiment of the present application, additionally provide a kind of for implementing the multimedia number of above-mentioned multi-medium data recognition methods According to identification device, as shown in fig. 7, the device 700 includes: the first identification module 702, obtains module 704, the second identification module 706 and determining module 708.

Wherein, the first identification module 702 for identification from the first data collected in original multimedia data whether There are invalid datas；If acquisition module 704 is used in the first data, there are invalid datas, obtain from original multimedia data Or collected second data in data recording, wherein data recording is the data obtained by recording original multimedia data； Second identification module 706 whether there is invalid data in the second data for identification；If determining module 708 is used for the second data In there are invalid datas, it is determined that original multimedia data belongs to illegal multi-medium data.

Specifically, above-mentioned original multimedia data can be the video of current live, audio etc., in initial multimedia number It, can be by being intercepted to original multimedia data, for example, screenshot is carried out to video, to collect during live streaming First data, the first above-mentioned data can be image, audio etc., and the application is not specifically limited in this embodiment, and implement in the application In example, it is described in detail so that multi-medium data is video as an example；Since original multimedia data is to be shot to upload by user, In order to ensure effective health of original multimedia data, need to judge to whether there is invalid data in original multimedia data, on The invalid data stated can be sensitive information or doubtful sensitive information；Since original multimedia data is during live streaming, it is Raising recognition accuracy, can record original multimedia data according to the format of instruction, so as to by record Data processed carry out secondary audit；In the scene that multi-medium data is video, the second above-mentioned data can be image.

Herein it should be noted that above-mentioned first identification module 702, obtain module 704, the second identification module 706 and really Cover half block 708 corresponds to the step S32 to step S38 in embodiment 1, example that four modules and corresponding step are realized and Application scenarios are identical, but are not limited to the above embodiments 1 disclosure of that.It should be noted that above-mentioned module is as device A part may operate in the terminal 10 of the offer of embodiment 1.

Scheme provided by the above embodiments of the present application 3 can identify collected first from original multimedia data It whether there is invalid data in data, when there are when invalid data, further obtaining from original multimedia data in the first data Or collected second data in data recording, and identify and whether there is invalid data in the second data, when determining the second data In there are that when invalid data, can determine that original multimedia data belongs to illegal multi-medium data, to realize multi-medium data The purpose of audit.

The scheme of above-described embodiment 3 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

In the above embodiments of the present application, the device further include: record module.

Wherein, it obtains module and is also used to obtain play time of first data in original multimedia data；Determining module It is also used to determine the corresponding recording time section of play time, wherein recording time section is default before or after play time Period；Module is recorded to be also used to obtain data recording by recording the original multimedia data in the recording time section.

In the above embodiments of the present application, the device further include: the first interception module, adjustment module and the second interception module.

Wherein, the first interception module is used in the playing process of original multimedia data, is cut according to the first frequency acquisition Original multimedia data is taken, the first data are obtained；Module is adjusted for there are when invalid data, be turned up first to adopt in the first data Collect frequency, the first frequency acquisition after being adjusted；Second interception module is used to intercept according to the first frequency acquisition adjusted Original multimedia data obtains the second data.

In the above embodiments of the present application, the device further include: the first interception module and third interception module.

Wherein, the first interception module is used in the playing process of original multimedia data, is cut according to the first frequency acquisition Original multimedia data is taken, the first data are obtained；Third interception module be used for when in the first data there are when invalid data, according to Second frequency acquisition intercepts data recording, obtains the second data, wherein the second frequency acquisition is greater than the first frequency acquisition；First Interception module is also used to when there are when invalid data, continue to intercept initial multimedia number according to the first frequency acquisition in the first data According to.

In the above embodiments of the present application, the first identification module or the second identification module include: the first determination unit, comparison list Member and the second determination unit.

Wherein, the first determination unit is used to determine the marking value of the first data or the second data；Judging unit is used for the One data are compared with the first default marking value and the second default marking value, or the marking value of the second data is preset with first Marking value and the second default marking value are compared；If the second determination unit is for the first data or the marking value of the second data More than or equal to the first default marking value, it is determined that there are invalid datas in the first data or the second data, if the first data Or second the marking values of data be less than or equal to the second default marking value, it is determined that there is no non-in the first data or the second data Method data.

In the above embodiments of the present application, obtains module and is also used to obtain original multimedia data from source server, wherein Original multimedia data pushes to source server by pushing equipment.

Embodiment 4

According to the embodiment of the present application, additionally provide a kind of for implementing the multimedia number of above-mentioned multi-medium data recognition methods According to identification device, as shown in figure 8, the device 800 includes: the first playing module 802, the second playing module 804 and display module 806。

Wherein, the first playing module 802 is for playing collected first data from original multimedia data；Second broadcasts Amplification module 804 is used in the first data play there are in the case where invalid data from original multimedia data or data recording In collected second data, wherein data recording is by recording the obtained data of original multimedia data；Display module 806 for, there are in the case where invalid data, showing the recognition result of original multimedia data in the second data, wherein knows Other result belongs to illegal multi-medium data for characterizing original multimedia data.

Specifically, above-mentioned original multimedia data can be the video of current live, audio etc., in initial multimedia number It, can be by being intercepted to original multimedia data, for example, screenshot is carried out to video, to collect during live streaming First data, the first above-mentioned data can be image, audio etc., and the application is not specifically limited in this embodiment, and implement in the application In example, it is described in detail so that multi-medium data is video as an example；Since original multimedia data is to be shot to upload by user, In order to ensure effective health of original multimedia data, need to judge to whether there is invalid data in original multimedia data, on The invalid data stated can be sensitive information or doubtful sensitive information；In original multimedia data during live streaming, in order to Recognition accuracy is improved, original multimedia data can be recorded according to the format of instruction, so as to by recording Data carry out secondary audit；In the scene that multi-medium data is video, the second above-mentioned data can be image.

Herein it should be noted that above-mentioned first playing module 802, the second playing module 804 and display module 806 are right The example and application scenarios phase that should be realized in the step S62 to step S66 in embodiment 2, three modules with corresponding step Together, but 2 disclosure of that are not limited to the above embodiments.It should be noted that above-mentioned module can be with as a part of device It operates in the terminal 10 of the offer of embodiment 1.

Scheme provided by the above embodiments of the present application 4 can play collected first from original multimedia data Data can be identified with the presence or absence of invalid data in the first data, there are in the case where invalid data in the first data, be played Collected second data from original multimedia data or data recording, and identify in the second data with the presence or absence of illegal number According to there are in the case where invalid data in the second data, the recognition result of original multimedia data being shown, to realize more matchmakers The purpose of volume data audit.

The scheme of above-described embodiment 4 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

Embodiment 5

According to the embodiment of the present application, a kind of embodiment of multi-medium data identifying system is additionally provided.

Fig. 9 is the schematic diagram according to a kind of multi-medium data identifying system of the embodiment of the present application 5.As shown in figure 9, this is System may include: identification equipment 92 and recording arrangement 94.

Wherein, identification equipment 92 is for identification from the first data collected in original multimedia data with the presence or absence of non- Method data；Recording arrangement 94 is used to obtain data recording by recording original multimedia data；Identify that equipment and recording arrangement connect It connects, if be also used in the first data there are invalid data, acquisition is collected from original multimedia data or data recording The second data, and identify the second data in whether there is invalid data, if there are invalid datas in the second data, it is determined that Original multimedia data belongs to illegal multi-medium data.

Specifically, above-mentioned identification equipment can be the server for being identified to original multimedia data, the clothes Business device can run net cast video audit service and the secondary review service of net cast as shown in Figure 4 and Figure 5, above-mentioned Recording arrangement can be the server for being recorded to original multimedia data, which can run such as Fig. 4 and Fig. 5 Shown in net cast record service, two servers can be attached by internet；Above-mentioned original multimedia data Video, the audio etc. that can be current live can be by initial multimedia numbers during original multimedia data live streaming According to being intercepted, for example, carrying out screenshot to video, to collect the first data, the first above-mentioned data can be image, sound Frequency etc., the application is not specifically limited in this embodiment, and in the embodiment of the present application, is carried out specifically so that multi-medium data is video as an example It is bright；Since original multimedia data is to be shot to upload by user, in order to ensure effective health of original multimedia data, need Judge that, with the presence or absence of invalid data in original multimedia data, above-mentioned invalid data can be sensitive information or doubtful sensitivity Information；It, can be according to the format of instruction to original in order to improve recognition accuracy since original multimedia data is during live streaming Beginning multi-medium data is recorded, so as to by carrying out secondary audit to data recording；It is video in multi-medium data In scene, the second above-mentioned data can be image.

Scheme provided by the above embodiments of the present application 5 can identify collected first from original multimedia data It whether there is invalid data in data, when there are when invalid data, further obtaining from original multimedia data in the first data Or collected second data in data recording, and identify and whether there is invalid data in the second data, when determining the second data In there are that when invalid data, can determine that original multimedia data belongs to illegal multi-medium data, to realize multi-medium data The purpose of audit.

The scheme of above-described embodiment 5 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

In the above embodiments of the present application, recording arrangement includes: processor and record device.

Wherein, when processor is played for obtaining play time of first data in original multimedia data, and determining Between corresponding recording time section, wherein recording time section be play time before or after preset time period；Record device with Processor connection, for obtaining data recording by recording the original multimedia data in the recording time section.

It should also be noted that, recording arrangement can record entire original multimedia data, and by identification equipment Play time of first data in original multimedia data is obtained, and determines the corresponding recording time section of play time, thus Corresponding data recording can be got from recording arrangement.

In the above embodiments of the present application, as shown in Figure 10, which can also include: storage equipment 96.

Wherein, identification equipment is also used to after determining that original multimedia data belongs to illegal multi-medium data, label record Data processed；Storage equipment is connect with identification equipment, for storing the data recording after marking.

Specifically, above-mentioned storage equipment can be the server for being stored to recorded video, which can To run OSS storage service as shown in Figure 4 and Figure 5, can be attached by internet with other two servers.

In the above embodiments of the present application, as shown in Figure 10, which can also include: the first interception equipment 98.

Wherein, the first interception equipment is connect with equipment is identified, in the playing process of original multimedia data, according to First frequency acquisition intercepts original multimedia data, obtains the first data, when the there are when invalid data, is turned up in the first data One frequency acquisition, the first frequency acquisition after being adjusted, and initial multimedia is intercepted according to the first frequency acquisition adjusted Data obtain the second data.

Specifically, the first above-mentioned interception equipment can be the server for carrying out screenshot to original video, the service Device can run net cast screenshot service as shown in Figure 4 and Figure 5, can be carried out by internet with other three servers Connection；The first above-mentioned frequency acquisition can be global audit frequency, such as can be key frame audit frequency of 10s, can To be configured by user；Above-mentioned the first frequency acquisition adjusted can be high frequency audit frequency, such as can be 1s mono- Secondary non-key frame audits frequency, can be configured by user.

In the above embodiments of the present application, as shown in figure 11, which can also include: the first interception equipment 98 and second section Take equipment 910.

Wherein, the first interception equipment is connect with equipment is identified, in the playing process of original multimedia data, according to First frequency acquisition intercepts original multimedia data, obtains the first data, when in the first data there are when invalid data, according to the One frequency acquisition continues to intercept original multimedia data；Second interception equipment, connect, for working as with identification equipment and recording arrangement There are when invalid data in first data, data recording is intercepted according to the second frequency acquisition, obtains the second data, wherein second Frequency acquisition is greater than the first frequency acquisition.

Specifically, the first above-mentioned interception equipment can be the server for being stored to original video, above-mentioned Second interception equipment can be the server for being stored to recorded video, and two servers can be run such as Fig. 4 and Fig. 5 Shown in net cast screenshot service, can be attached by internet with other three servers；The first above-mentioned acquisition Frequency can be conventional audit frequency, such as to can be 10s primary, can be configured by user；The second above-mentioned acquisition frequency Rate can the period high for conventional audit frequency namely screenshot than conventional end, for example, conventional audit frequency is 10s primary, then the It is primary that two frequency acquisitions can be 3s, can be configured by user.

In the above embodiments of the present application, identification equipment is also used to determine the marking value of the first data or the second data, by the One data are compared with the first default marking value and the second default marking value, or the marking value of the second data is preset with first Marking value and the second default marking value are compared, if the marking value of the first data or the second data is greater than or equal to first in advance If marking value, it is determined that there are invalid datas in the first data or the second data, if the marking of the first data or the second data Value is less than or equal to the second default marking value, it is determined that invalid data is not present in the first data or the second data.

In the above embodiments of the present application, which can also include: pushing equipment and source server.

Wherein, pushing equipment is for pushing original multimedia data；Source server, with pushing equipment, the first screenshot equipment It is connected with recording arrangement, for storing original multimedia data.

Embodiment 6

According to the embodiment of the present application, a kind of embodiment of multi-medium data identifying system is additionally provided, comprising:

Processor.And

Memory is connect with processor, for providing the instruction for handling following processing step for processor: being identified from original It whether there is invalid data in multi-medium data in collected first data；If there are invalid data in the first data, Obtain collected second data from original multimedia data or data recording, wherein data recording is original by recording The data that multi-medium data is recorded；It identifies in the second data with the presence or absence of invalid data；If deposited in the second data In invalid data, it is determined that original multimedia data belongs to illegal multi-medium data.

Scheme provided by the above embodiments of the present application 6 can identify collected first from original multimedia data It whether there is invalid data in data, when there are when invalid data, further obtaining from original multimedia data in the first data Or collected second data in data recording, and identify and whether there is invalid data in the second data, when determining the second data In there are that when invalid data, can determine that original multimedia data belongs to illegal multi-medium data, to realize multi-medium data The purpose of audit.

The scheme of above-described embodiment 6 provided by the present application solves multi-medium data identification side in the prior art as a result, Method recognition efficiency and the low technical problem of accuracy.

Embodiment 7

Embodiments herein can provide a kind of terminal, which can be in terminal group Any one computer terminal.Optionally, in the present embodiment, above-mentioned terminal also could alternatively be mobile whole The terminal devices such as end.

Optionally, in the present embodiment, above-mentioned terminal can be located in multiple network equipments of computer network At least one network equipment.

In the present embodiment, above-mentioned terminal can execute the program of following steps in multi-medium data recognition methods Code: identification whether there is invalid data from the first data collected in original multimedia data；If in the first data There are invalid datas, then obtain collected second data from original multimedia data or data recording, wherein data recording For the data recorded by recording original multimedia data；It identifies in the second data with the presence or absence of invalid data；Such as There are invalid datas in the second data of fruit, it is determined that original multimedia data belongs to illegal multi-medium data.

Optionally, Figure 12 is the structural block diagram according to a kind of terminal of the embodiment of the present application.As shown in figure 12, should Terminal A may include: one or more (one is only shown in figure) processors 1202 and memory 1204.

Wherein, memory can be used for storing software program and module, as the multi-medium data in the embodiment of the present application is known Corresponding program instruction/the module of other method and apparatus, the software program and mould that processor is stored in memory by operation Block realizes above-mentioned multi-medium data recognition methods thereby executing various function application and data processing.Memory can wrap Include high speed random access memory, can also include nonvolatile memory, as one or more magnetic storage device, flash memory or Other non-volatile solid state memories of person.In some instances, memory can further comprise remotely located relative to processor Memory, these remote memories can pass through network connection to terminal A.The example of above-mentioned network includes but is not limited to interconnect Net, intranet, local area network, mobile radio communication and combinations thereof.

Processor can call the information and application program of memory storage by transmitting device, to execute following step: Identification whether there is invalid data from the first data collected in original multimedia data；If in the first data, there are non- Method data then obtain collected second data from original multimedia data or data recording, wherein data recording is to pass through Record the data that original multimedia data is recorded；It identifies in the second data with the presence or absence of invalid data；If second There are invalid datas in data, it is determined that original multimedia data belongs to illegal multi-medium data.

Optionally, the program code of following steps can also be performed in above-mentioned processor: invalid data belongs to quick for characterization The probability for feeling information is greater than or equal to the data of predetermined probabilities.

Optionally, the program code of following steps can also be performed in above-mentioned processor: acquiring from data recording obtaining Before the second data arrived, play time of first data in original multimedia data is obtained；Determine that play time is corresponding Recording time section, wherein recording time section is the preset time period before or after play time；By recording the recording time Original multimedia data in section, obtains data recording.

Optionally, the program code of following steps can also be performed in above-mentioned processor: determining original multimedia data category After illegal multi-medium data, data recording is marked, and stores the data recording after label.

Optionally, the program code of following steps can also be performed in above-mentioned processor: being from original more matchmakers in the second data In volume data in collected situation, in the playing process of original multimedia data, intercepted according to the first frequency acquisition original Multi-medium data obtains the first data；When, there are when invalid data, the first frequency acquisition of height-regulating is adjusted in the first data The first frequency acquisition afterwards；Continue to intercept original multimedia data according to the first frequency acquisition adjusted, obtains the second data.

Optionally, the program code of following steps can also be performed in above-mentioned processor: being in data recording in the second data In collected situation, in the playing process of original multimedia data, initial multimedia number is intercepted according to the first frequency acquisition According to obtaining the first data；When there are when invalid data, intercepting data recording in the first data according to the second frequency acquisition, obtain Second data, and, continue to intercept original multimedia data according to the first frequency acquisition, wherein the second frequency acquisition is greater than first Frequency acquisition.

Optionally, the program code of following steps can also be performed in above-mentioned processor: determining the first data or the second data Marking value；First data are compared with the first default marking value and the second default marking value, or beating the second data Score value is compared with the first default marking value and the second default marking value；If the marking value of the first data or the second data is big In or equal to the first default marking value, it is determined that there are invalid datas in the first data or the second data；If the first data or The marking value of second data is less than or equal to the second default marking value, it is determined that there is no illegal in the first data or the second data Data.

Optionally, the program code of following steps can also be performed in above-mentioned processor: identifying from original multimedia data In in collected first data with the presence or absence of before invalid data, original multimedia data is obtained from source server, wherein Original multimedia data pushes to source server by pushing equipment.

Using the embodiment of the present application, can identify whether there is from the first data collected in original multimedia data Invalid data, when, there are when invalid data, further acquisition is adopted from original multimedia data or data recording in the first data The second data collected, and identify and whether there is invalid data in the second data, when determining that there are invalid datas in the second data When, it can determine that original multimedia data belongs to illegal multi-medium data, to realize the purpose of multi-medium data audit.

It will appreciated by the skilled person that structure shown in Figure 12 is only to illustrate, terminal is also possible to Smart phone (such as Android phone, iOS mobile phone), tablet computer, applause computer and mobile internet device (Mobile Internet Devices, MID), the terminal devices such as PAD.Figure 12 it does not cause to limit to the structure of above-mentioned electronic device.Example Such as, terminal A may also include the more or less component (such as network interface, display device) than shown in Figure 12, Or with the configuration different from shown in Figure 12.

Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can It is completed with instructing the relevant hardware of terminal device by program, which can store in a computer readable storage medium In, storage medium may include: flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), disk or CD etc..

Embodiment 8

Embodiments herein additionally provides a kind of storage medium.Optionally, in the present embodiment, above-mentioned storage medium can For saving program code performed by multi-medium data recognition methods provided by above-described embodiment one.

Optionally, in the present embodiment, above-mentioned storage medium can be located in computer network in computer terminal group In any one terminal, or in any one mobile terminal in mobile terminal group.

Optionally, in the present embodiment, storage medium is arranged to store the program code for executing following steps: knowing It whether there is invalid data not from the first data collected in original multimedia data；If existed in the first data illegal Data then obtain collected second data from original multimedia data or data recording, wherein data recording is to pass through record The data that original multimedia data processed is recorded；It identifies in the second data with the presence or absence of invalid data；If the second number There are invalid datas in, it is determined that original multimedia data belongs to illegal multi-medium data.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: invalid data For characterizing data of the probability more than or equal to predetermined probabilities for belonging to sensitive information.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: obtain from In data recording before collected second data, play time of first data in original multimedia data is obtained；It determines The corresponding recording time section of play time, wherein recording time section is the preset time period before or after play time；Pass through The original multimedia data in the recording time section is recorded, data recording is obtained.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: former determining Beginning multi-medium data belongs to after illegal multi-medium data, marks data recording, and stores the data recording after label.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: in the second number According in the playing process of original multimedia data, being adopted according to first in situation collected in original multimedia data Collect frequency and intercept original multimedia data, obtains the first data；When there are the first acquisition when invalid data, is turned up in the first data Frequency, the first frequency acquisition after being adjusted；Continue to intercept original multimedia data according to the first frequency acquisition adjusted, Obtain the second data.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: in the second number According to being in the playing process of original multimedia data, to be cut according to the first frequency acquisition in data recording in collected situation Original multimedia data is taken, the first data are obtained；When there are when invalid data, being intercepted according to the second frequency acquisition in the first data Data recording obtains the second data, and, continue to intercept original multimedia data according to the first frequency acquisition, wherein the second acquisition Frequency is greater than the first frequency acquisition.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: determining first The marking value of data or the second data；First data are compared with the first default marking value and the second default marking value, or The marking value of second data is compared with the first default marking value and the second default marking value；If the first data or second The marking value of data is greater than or equal to the first default marking value, it is determined that there are invalid datas in the first data or the second data； If the marking value of the first data or the second data is less than or equal to the second default marking value, it is determined that the first data or the second number Invalid data is not present in.

Optionally, above-mentioned storage medium is also configured to store the program code for executing following steps: identification from It is obtained from source server original more in collected first data with the presence or absence of before invalid data in original multimedia data Media data, wherein original multimedia data pushes to source server by pushing equipment.

Above-mentioned the embodiment of the present application serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.

In above-described embodiment of the application, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment The part of detailed description, reference can be made to the related descriptions of other embodiments.

In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, only A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module It connects, can be electrical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of software functional units.

If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the application whole or Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code Medium.

The above is only the preferred embodiment of the application, it is noted that for the ordinary skill people of the art For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered It is considered as the protection scope of the application.

Claims

1. a kind of multi-medium data recognition methods characterized by comprising

Identification whether there is invalid data from the first data collected in original multimedia data；

If there are invalid data in first data, acquisition is acquired from the original multimedia data or data recording The second data arrived；

It identifies in second data with the presence or absence of invalid data；

If in second data, there are invalid datas, it is determined that the original multimedia data belongs to illegal multimedia number According to.

2. the method according to claim 1, wherein the invalid data belongs to the general of sensitive information for characterizing Rate is greater than or equal to the data of predetermined probabilities.

3. according to the method described in claim 2, it is characterized in that, obtain from data recording collected second data it Before, the method also includes:

Obtain play time of first data in the original multimedia data；

Determine the corresponding recording time section of the play time, wherein the recording time section be the play time before or Preset time period later；

By recording the original multimedia data in the recording time section, the data recording is obtained.

4. according to the method described in claim 3, it is characterized in that, determining that the original multimedia data belongs to non-fado matchmaker After volume data, the data recording is marked, and stores the data recording after label.

5. according to the method described in claim 2, it is characterized in that, being from the original multimedia data in second data In in collected situation, the method also includes:

In the playing process of the original multimedia data, the original multimedia data is intercepted according to the first frequency acquisition, Obtain first data；

When, there are when invalid data, height-regulating first frequency acquisition, first after being adjusted acquires in first data Frequency；

Continue to intercept the original multimedia data according to first frequency acquisition adjusted, obtains second data.

6. according to the method described in claim 2, it is characterized in that, in second data being collected in the data recording In the case where, the method also includes:

When there are when invalid data, intercepting the data recording according to the second frequency acquisition in first data, obtain described Second data, and, continue to intercept the original multimedia data according to first frequency acquisition, wherein second acquisition Frequency is greater than first frequency acquisition.

7. method as claimed in any of claims 1 to 6, which is characterized in that in identification first data whether There are include: with the presence or absence of invalid data in invalid data, or identification second data

Determine the marking value of first data or second data；

First data are compared with the first default marking value and the second default marking value, or by second data Marking value is compared with the first default marking value and the second default marking value；

If the marking value of first data or second data is greater than or equal to the described first default marking value, it is determined that There are invalid datas in first data or second data；

If the marking value of first data or second data is less than or equal to the described second default marking value, it is determined that Invalid data is not present in first data or second data.

8. the method according to the description of claim 7 is characterized in that in identification collected first from original multimedia data With the presence or absence of before invalid data in data, the original multimedia data is obtained from source server, wherein described original more Media data pushes to the source server by pushing equipment.

9. a kind of multi-medium data recognition methods characterized by comprising

Play collected first data from original multimedia data；

There are in the case where invalid data in first data, play from the original multimedia data or data recording Collected second data；

There are in the case where invalid data in second data, the recognition result of the original multimedia data is shown, In, the recognition result belongs to illegal multi-medium data for characterizing the original multimedia data.

10. a kind of multi-medium data identifying system characterized by comprising

It identifies equipment, whether there is invalid data from the first data collected in original multimedia data for identification；

Recording arrangement, for obtaining data recording by recording the original multimedia data；

The identification equipment, connect with the recording arrangement, if be also used in first data, there are invalid datas, obtains Collected second data from the original multimedia data or data recording are taken, and identifies and whether is deposited in second data In invalid data, if there are invalid datas in second data, it is determined that the original multimedia data belongs to non-fado Media data.

11. system according to claim 10, which is characterized in that the recording arrangement includes:

Processor is broadcast for obtaining play time of first data in the original multimedia data, and described in determination Put time corresponding recording time section, wherein the recording time section is the preset time before or after the play time Section；

Record device is connected to the processor, for obtaining by recording the original multimedia data in the recording time section To the data recording.

12. system according to claim 11, which is characterized in that

The identification equipment is also used to after determining that the original multimedia data belongs to illegal multi-medium data, described in label Data recording；

The system also includes: storage equipment is connect, for storing the data recording after marking with the identification equipment.

13. system according to claim 11, which is characterized in that the system also includes:

First interception equipment, connect, in the original multimedia data with the identification equipment and the recording arrangement In playing process, the original multimedia data is intercepted according to the first frequency acquisition, first data are obtained, described in determination There are when invalid data in first data, first frequency acquisition, the first frequency acquisition after being adjusted, according to institute is turned up It states the first frequency acquisition adjusted and intercepts the original multimedia data, obtain second data.

14. system according to claim 11, which is characterized in that the system also includes:

First interception equipment, connect with the identification equipment, in the playing process of the original multimedia data, according to First frequency acquisition intercepts the original multimedia data, obtains first data, exists when determining in first data When invalid data, continue to intercept the original multimedia data according to first frequency acquisition；

Second interception equipment, connect with the identification equipment and the recording arrangement, for depositing when in determining first data In invalid data, the data recording is intercepted according to the second frequency acquisition, obtains second data, wherein described second Frequency acquisition is greater than first frequency acquisition.

15. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program When control the storage medium where equipment execute following steps: identification collected first data from original multimedia data In whether there is invalid data；If there are invalid datas in first data, obtain from the original multimedia data Or collected second data in data recording；It identifies in second data with the presence or absence of invalid data；If described second There are invalid datas in data, it is determined that the original multimedia data belongs to illegal multi-medium data.

16. a kind of processor, which is characterized in that the processor is for running program, wherein executed such as when described program is run Lower step: identification whether there is invalid data from the first data collected in original multimedia data；If described first There are invalid datas in data, then obtain collected second data from the original multimedia data or data recording；Know It whether there is invalid data in not described second data；If in second data, there are invalid datas, it is determined that the original Beginning multi-medium data belongs to illegal multi-medium data.

17. a kind of multi-medium data identifying system characterized by comprising

Processor；And

Memory is connected to the processor, for providing the instruction for handling following processing step for the processor: identification from It whether there is invalid data in original multimedia data in collected first data；If existed in first data illegal Data then obtain collected second data from the original multimedia data or data recording；Identify second data In whether there is invalid data；If in second data, there are invalid datas, it is determined that the original multimedia data category In illegal multi-medium data.