CN110929055B - Multimedia quality detection method and device, electronic equipment and storage medium - Google Patents
Multimedia quality detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110929055B CN110929055B CN201911121308.0A CN201911121308A CN110929055B CN 110929055 B CN110929055 B CN 110929055B CN 201911121308 A CN201911121308 A CN 201911121308A CN 110929055 B CN110929055 B CN 110929055B
- Authority
- CN
- China
- Prior art keywords
- multimedia
- user
- feature
- target
- quality detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The disclosure relates to a multimedia quality detection method, a device, an electronic device and a storage medium, comprising: acquiring multimedia to be detected issued by any target user, and acquiring target characteristics of the multimedia to be detected; the target user is a user which is detected by a white list in advance; acquiring reference characteristics of the target user based on the multimedia which the target user has passed the quality detection; calculating the distance between the reference feature of the target user and the target feature; and under the condition that the distance meets the preset condition, determining that the multimedia to be detected passes the quality detection. According to the embodiment of the disclosure, the reference feature is extracted from the multimedia which is detected by the user, the target feature is extracted from the multimedia to be detected, and whether the new multimedia can directly pass the quality detection is determined by comparing the distance between the target feature and the reference feature, so that the quality detection of the newly released multimedia is completed under the condition of reducing the workload of detection personnel.
Description
Technical Field
The disclosure relates to the field of internet application, and in particular relates to a multimedia quality detection method, a device, an electronic device and a storage medium.
Background
With the development and enrichment of internet applications, users may release their own multimedia through a specific platform, such as releasing their own video through a video platform, or releasing pictures through an online picture sharing platform, etc., where the platform generally needs to detect whether the quality of the multimedia released by the users is acceptable. In the related art, multimedia can be detected manually, but more manpower and time are often required to be consumed, and the detection progress is slower.
In order to reduce the workload of detection personnel, a white list mechanism can be set, users with more multimedia release and fewer violations are added into a white list, and the users in the white list are subjected to no-review measures. However, the white list mechanism in the related art still has a certain risk, for example, it cannot be guaranteed that the users in the white list always release non-illegal multimedia; once the user's account in the whitelist is stolen, offending multimedia may be released.
Disclosure of Invention
The disclosure provides a multimedia quality detection method, a device, an electronic device and a storage medium, which at least solve the problems of reducing the workload of manual detection and reducing the detection risk. The technical scheme of the present disclosure is as follows:
according to a first aspect of embodiments of the present disclosure, there is provided a multimedia quality detection method, the method comprising:
acquiring multimedia to be detected issued by any target user, and acquiring target characteristics of the multimedia to be detected; the target user is a user which is detected by a white list in advance;
acquiring reference characteristics of the target user based on the multimedia which the target user has passed the quality detection;
calculating the distance between the reference feature of the target user and the target feature;
and under the condition that the distance meets the preset condition, determining that the multimedia to be detected passes the quality detection.
In one possible implementation, the white list detection includes:
determining a user who has released at least N multimedia as a candidate user;
for any candidate user: acquiring quality detection results of N multimedia recently released by the user; and if the quality detection results are all passed detection, determining that the user passes white list detection.
In one possible implementation manner, the obtaining the reference feature of the target user based on the multimedia that the target user has passed the quality detection includes:
determining M multimedia which passes the quality detection and is recently released by the target user, wherein M is less than or equal to N;
and acquiring the reference characteristic of each multimedia in the M multimedia as the reference characteristic of the user.
In one possible implementation, the calculating the distance between the reference feature of the target user and the target feature includes:
calculating the distance between the reference feature of the target user and the target feature by using the following formula:
wherein feature is i Feature for the ith reference feature of the target user t Is the target feature.
In one possible implementation manner, the determining the to-be-detected multimedia passing quality detection when the distance meets a preset condition includes:
acquiring an average distance between the reference features of the target user;
and under the condition that the distance is smaller than the average distance, determining that the multimedia to be detected passes quality detection.
According to a second aspect of embodiments of the present disclosure, there is provided a multimedia quality detection apparatus, the apparatus comprising:
the target feature acquisition module is configured to acquire the multimedia to be detected issued by any target user and acquire the target feature of the multimedia to be detected; the target user is a user which is detected by a white list in advance;
a reference feature acquisition module configured to perform acquisition of a reference feature of the target user based on multimedia that the target user has passed quality detection;
a feature distance calculation module configured to perform calculation of a distance of the reference feature of the target user from the target feature;
and the detection result determining module is configured to determine that the multimedia to be detected passes quality detection under the condition that the distance meets a preset condition.
In one possible implementation, the apparatus further includes: a whitelist detection module configured to perform:
determining a user who has released at least N multimedia as a candidate user;
for any candidate user: acquiring quality detection results of N multimedia recently released by the user; and if the quality detection results are all passed detection, determining that the user passes white list detection.
In one possible implementation manner, the reference feature acquisition module includes:
a multimedia determining unit configured to perform determining M multimedia that have passed quality detection recently issued by the target user, wherein M is N or less;
and a feature acquisition unit configured to perform acquisition of a reference feature of each of the M multimedia as a reference feature of the user.
In one possible implementation manner, the feature distance calculation module is specifically configured to perform:
calculating the distance between the reference feature of the target user and the target feature by using the following formula:
wherein feature is i Feature for the ith reference feature of the target user t Is the target feature.
In one possible implementation manner, the detection result determining module is specifically configured to perform:
acquiring an average distance between the reference features of the target user;
and under the condition that the distance is smaller than the average distance, determining that the multimedia to be detected passes quality detection.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the executable instructions to implement the multimedia quality detection method as in the first aspect and any one of the possible implementations of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the multimedia quality detection method as in any one of the first aspect and possible implementations of the first aspect.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising one or more instructions which, when executed by a processor of an electronic device, enable the electronic device to perform the operations performed by the method of multimedia quality detection of any one of the first aspect and possible implementations of the first aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects: the method comprises the steps of extracting reference characteristics from multimedia which is passed by a user and is detected, extracting target characteristics from multimedia to be detected, and determining whether new multimedia released by the user in a white list can directly pass the quality detection or not by comparing the distance between the target characteristics and the reference characteristics without manual detection, so that the quality detection of the new multimedia released is completed under the condition of reducing the workload of detection personnel.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
Fig. 1 is a flow chart illustrating a multimedia quality detection method according to an exemplary embodiment;
fig. 2 is another flow diagram illustrating a method of multimedia quality detection according to an exemplary embodiment;
fig. 3 is a schematic diagram showing a structure of a multimedia quality detecting apparatus according to an exemplary embodiment;
fig. 4 is another structural diagram of a multimedia quality detecting apparatus according to an exemplary embodiment;
fig. 5 is a schematic diagram of a structure of an electronic device according to an exemplary embodiment.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the disclosure as detailed in the foregoing summary.
Fig. 1 is a flowchart illustrating a multimedia quality detection method according to an exemplary embodiment, referring to fig. 1, a multimedia quality detection method may include steps S11 to S14:
in step S11, acquiring multimedia to be detected issued by any target user, and acquiring target characteristics of the multimedia to be detected; the target user is a user which has been detected through the white list in advance.
In the embodiment of the disclosure, the white list detection can be performed on the users who release excessive multimedia in advance, namely, the quality of the multimedia released by the users is determined. If it is determined that a user publishes a larger amount of multimedia and the quality of the published multimedia is higher, it may be determined that the user passes the white list detection.
In an embodiment, the white list detection may include: firstly, determining users who have published at least N pieces of multimedia as candidate users; then for any candidate user: and acquiring the quality detection results of N pieces of multimedia recently released by the user, and if the quality detection results are all passed detection, determining that the user passes white list detection.
It can be understood that, when acquiring the quality detection results of N multimedia recently issued by the user, if the quality detection has been performed on the multimedia before, the previous quality detection result may be acquired, or the quality detection may be performed again, which is not limited in this embodiment. In addition, the white list detection may be implemented in other manners, for example, it is determined whether the user issues at least N multimedia in the last T days, and all multimedia passes the quality detection, where appropriate values may be selected for variables such as T and N according to actual requirements.
Further, if it is necessary to acquire a quality detection result of the most recently released multimedia of the user at the time of the white list detection, since the detection result of the most recently released multimedia may vary with time, for example, all 10 multimedia released by the user a pass the detection, it may be determined that the user passes the white list detection, but if 11 th multimedia released later does not pass the detection, it may be determined that the user does not pass the white list detection later.
The present embodiment does not limit the timing of performing the white list detection, for example, periodically (e.g., every 24 hours) re-detecting the user who has passed the white list detection last time; for another example, an update trigger mechanism is set, and in the case that the multimedia released by the user which has passed the white list detection at the last time fails the quality detection, the user is directly determined to fail the white list detection; etc.
In the embodiment of the disclosure, the target feature of the multimedia to be detected may be obtained in various manners. For example, features may be extracted manually; the model can also be trained in advance, and the characteristics can be extracted by using the trained model; etc.
As another example, different forms of features can be extracted for different forms of multimedia, and thus different feature acquisition manners can be set. For example, for text multimedia, features can be extracted by means of semantic recognition and keyword extraction; for the image multimedia, the characteristics such as color characteristics, texture characteristics, shape characteristics, spatial relation characteristics and the like of the image can be extracted based on an image processing technology; for video multimedia, features can be extracted in dimensions of sound, images and video clips based on image processing technology; and so on, those skilled in the art may set the feature extraction mode and the extracted specific features according to the requirements of practical application, and the embodiments of the present disclosure are not limited thereto.
In step S12, a reference feature of the target user is acquired based on the multimedia that the target user has passed the quality detection.
Since the number of multimedia released by a user may vary with time, when acquiring a reference feature based on multimedia that a target user has passed quality detection, it is first necessary to determine multimedia for acquiring the reference feature.
In one embodiment, M (M.ltoreq.N) multimedia which has passed the quality detection and has been recently released by the target user may be determined, and then the reference feature of each of the M multimedia may be obtained as the reference feature of the target user.
For example, the condition of adding the user whitelist includes a condition that "at least 30 multimedia have been released and all multimedia pass detection", i.e., N has a value of 30, m=n may be set, i.e., reference features are extracted from 30 multimedia recently released by the user; alternatively, in order to reduce the workload of extracting the reference feature, M may be set to 5, that is, the reference feature is extracted from 5 multimedia recently released by the user; etc.
In addition, the reference feature of each of the M multimedia may be acquired in a plurality of ways. For example, the reference feature may be extracted from each multimedia after determining M multimedia which have passed the detection recently issued by the user; the reference characteristics of M multimedia which are recently released by the user and pass the quality detection can be extracted after the user is added into the white list and used as the reference characteristics of the user when the multimedia is detected for the first time based on the disclosed embodiment, and if the last multimedia to be detected passes the quality detection, the extracted characteristics from the multimedia can also be used as the reference characteristics of the user when the subsequent quality detection is performed; etc.
Furthermore, the reference feature may be extracted from the multimedia in one or more ways listed or not listed in step S11, and the embodiment of the present disclosure is not limited to a specific way of obtaining the reference feature, as long as the purpose that the extracted feature has a reference meaning with respect to the target feature can be achieved.
In step S13, calculating a distance between the reference feature of the target user and the target feature; the method comprises the steps of,
in step S14, in the case that the distance satisfies a preset condition, it is determined that the multimedia to be detected passes quality detection.
For convenience of description, step S13 will be described in conjunction with step S14:
in the embodiment of the disclosure, the reference features of the user may be multiple sets of features, for example, M feature vectors are respectively extracted from M multimedia; it is also possible to extract 1 feature vector from 1 multimedia or to combine M feature vector calculations into 1 feature vector for a set of features, for example; etc.
In an embodiment, if the reference feature and the target feature of the user are both 1 feature vector, a distance of 2 vectors may be calculated, and if the distance is not greater than a preset threshold, it is determined that the multimedia to be detected passes detection.
In another embodiment, if M sets of reference features are extracted from M multimedia of a user as reference features of the user, the distance of the target feature from the reference features of the user may be calculated in particular in a variety of ways. Corresponding conditions can be set by the distances calculated in different modes and used for judging whether the multimedia to be detected passes the detection or not.
In one example, the distances of the target feature from each reference feature may be calculated separately. Correspondingly, the calculated distances can be compared with a preset threshold value, or the average distance between the reference features can be calculated, and the calculated distances can be compared with the average distance, so that the multimedia to be detected is determined to pass detection under the condition that the value of the preset proportion (such as all or 80%) in the distances is not smaller than the preset threshold value or the average distance.
In another example, the distances of the target feature from the respective reference features may be calculated separately, and the weights of the calculated distances may be determined, for example, the weight of the multimedia may be set to be higher as the distribution time is closer in advance; or the current playing amount, comment amount or collection amount of the multimedia can be obtained, and the data is converted into the weight of the multimedia; etc.
Then, based on the calculated distances and the determined weights, a weighted sum result or a weighted average result of the distances of the target feature from the reference feature of the user is calculated. Of course, the determined weights may also be all "1", i.e. the sum or average of the distances is directly calculated.
Correspondingly, the relation between the calculated distance and the preset threshold value can be compared, and the multimedia to be detected is determined to pass detection under the condition that the distance is not greater than the preset threshold value.
The distance between the target feature and the reference feature of the user can be used as the target distance, the distance between the reference features is calculated and used as the reference distance, the relation between the target distance and the reference distance is compared, and the multimedia to be detected is determined to pass detection under the condition that the target distance is not greater than the reference distance.
For example, the distance of the target feature from the user's reference feature is calculated using the following formula (1-1):
wherein feature is i Features for the ith reference feature of the user t Is the target feature.
It will be appreciated that the distance referred to in the embodiments of the present disclosure may be expressed by a euclidean distance or may be expressed by a cosine distance, for example, the distance between any reference feature of the user and other reference features may be calculated by the following formula (1-2):
wherein feature is i Features for the ith reference feature of the user j Is the j-th reference feature of the user.
And, the average value of the M reference features of the user can be calculated by the following formula (1-3):
wherein distance is j Is the distance between the jth reference feature of the user and the other reference features.
In addition, in the embodiment of the present disclosure, the video corresponding to N or M videos is not fixed, and after a user uploads a new multimedia and passes quality detection, the user most recently distributes and passes detection M multimedia, including the new multimedia, and removes 1 multimedia with the longest distribution time. And, whether the new multimedia X is determined to pass or not, as long as the user is still in the white list, the feature of X will still be taken as the reference feature when the next quality detects other new multimedia.
The method for detecting multimedia quality provided by the present disclosure is described below with reference to a more specific example.
As shown in fig. 2, a video distribution platform is taken as an example:
white list setting stage
Active users who release at least K videos (such as 30 videos) are screened out and added into a candidate Queue K 。
Obtaining candidate Queue K Screening out the recently released K users with the video detection result of each user and adding the users with the video detection result into a white list Queue S 。
Model obtained by pre-training ori The model has better video feature extraction capability. Extracting a Queue using the model S Features of K videos recently released by each user, e.g. features extracted from the ith video of a user using a model are features i 。
(II) video quality detection stage
After a user issues a new video on the video platform, the user can firstDetermining whether the user is in Queue S If yes, further determining whether the new video can avoid manual quality detection.
Specifically, a model is used ori Extracting feature from the new video new Feature is calculated by the following formula (1-4) new Average distance from the features of the K videos new ：
Wherein feature is i Is the i-th reference feature of the features of the K videos.
And, the average distance of the features of the M (e.g. 5) recently distributed videos out of the K videos is calculated by the following formulas (1-5) and (1-6) avg ：
Wherein feature is i Features for the ith reference feature of the features of M videos j Distance for the j-th reference feature of the features of M videos j Is the distance between the jth reference feature and the other reference features in the features of the M videos.
Then, compare distance new Distance and distance avg If distance is the size of new ＜distance avg Adding the new video into an exempt queue, and subsequently, manually detecting the quality of the video; if distance new distance avg Then manual quality detection of the video is required later.
Therefore, in the example, the reference feature is extracted from the multimedia which is detected by the user through the quality detection, the target feature is extracted from the multimedia to be detected, and whether the new multimedia released by the user in the white list can directly pass the quality detection or not is determined by comparing the distance between the target feature and the reference feature without manual detection, so that the quality detection of the new multimedia released under the condition of reducing the workload of detection personnel is completed.
Fig. 3 is a block diagram of a multimedia quality detection apparatus according to an exemplary embodiment, which may include a target feature acquisition module 110, a reference feature acquisition module 120, a feature distance calculation module 130, and a detection result determination module 140.
The target feature acquiring module 110 is configured to perform acquiring a multimedia to be detected issued by any target user, and acquire a target feature of the multimedia to be detected; the target user is a user which is detected by a white list in advance;
the reference feature acquisition module 120 is configured to perform acquisition of a reference feature of the target user based on the multimedia that the target user has passed the quality detection;
the feature distance calculation module 130 is configured to perform calculation of a distance between a reference feature of the target user and the target feature;
the detection result determining module 140 is configured to perform determining that the multimedia to be detected passes quality detection if the distance meets a preset condition.
In one possible implementation, referring to fig. 4, the apparatus further includes: the whitelist detection module 150 is configured to perform:
determining a user who has released at least N multimedia as a candidate user;
for any candidate user: acquiring quality detection results of N multimedia recently released by the user; and if the quality detection results are all passed detection, determining that the user passes white list detection.
In one possible implementation manner, the reference feature acquisition module includes:
a multimedia determining unit configured to perform determining M multimedia that have passed quality detection recently issued by the target user, wherein M is N or less;
and a feature acquisition unit configured to perform acquisition of a reference feature of each of the M multimedia as a reference feature of the user.
In one possible implementation, the feature distance calculation module 130 is specifically configured to perform:
calculating the distance between the reference feature of the target user and the target feature by using the following formula:
wherein feature is i Feature for the ith reference feature of the target user t Is the target feature.
In one possible implementation, the detection result determining module 140 is specifically configured to perform:
acquiring an average distance between the reference features of the target user;
and under the condition that the distance is smaller than the average distance, determining that the multimedia to be detected passes quality detection.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Fig. 5 is a block diagram of an electronic device, according to an example embodiment. For example, electronic device 50 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, server, and the like.
Referring to fig. 5, the electronic device 50 may include one or more of the following components: a processing component 510, a memory 520, a power component 530, a multimedia component 540, an audio component 550, an input/output (I/O) interface 560, a sensor component 570, and a communication component 580.
The processing component 510 generally controls overall operation of the electronic device 50, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 510 may include one or more processors 511 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 510 can include one or more modules that facilitate interactions between the processing component 510 and other components. For example, the processing component 510 may include a multimedia module to facilitate interaction between the multimedia component 540 and the processing component 510.
The memory 520 is configured to store various types of data to support operations at the electronic device 50. Examples of such data include instructions for any application or method operating on electronic device 50, contact data, phonebook data, messages, pictures, video, and the like. The memory 520 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 530 provides power to the various components of the electronic device 50. Power supply component 530 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 50.
The multimedia component 540 includes a screen between the electronic device 50 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia assembly 540 includes a front camera and/or a rear camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the electronic device 50 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 550 is configured to output and/or input audio signals. For example, the audio component 550 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 50 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 520 or transmitted via the communication component 580. In some embodiments, the audio component 550 further includes a speaker for outputting audio signals.
The I/O interface 560 provides an interface between the processing component 510 and a peripheral interface module, which may be a keyboard, click wheel, button, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 570 includes one or more sensors for providing status assessment of various aspects of the electronic device 50. For example, the sensor assembly 570 may detect an on/off state of the electronic device 50, a relative positioning of components, such as a display and keypad of the electronic device 50, the sensor assembly 570 may also detect a change in position of the electronic device 50 or a component of the electronic device 50, the presence or absence of a user's contact with the electronic device 50, an orientation or acceleration/deceleration of the electronic device 50, and a change in temperature of the electronic device 50. The sensor assembly 570 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 570 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 570 may further include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 580 is configured to facilitate communication between the electronic device 50 and other devices, either wired or wireless. The electronic device 50 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 580 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 580 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an embodiment of the present disclosure, the electronic device 50 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the above-described methods.
In an embodiment of the present disclosure, a non-transitory computer-readable storage medium, such as memory 920, comprising instructions executable by the processor 911 of the electronic device 90 to perform the method of multimedia quality detection described above is also provided. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. In an embodiment of the present disclosure, there is also provided an application program, which when executed by a processor of an electronic device, enables the electronic device to perform the above-described multimedia quality detection method, so as to obtain the same technical effects.
In an embodiment of the present disclosure, there is also provided a computer program product that, when executed by a processor of an electronic device, enables the electronic device to perform the above-described multimedia quality detection method to obtain the same technical effects.
Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (8)
1. A method for multimedia quality detection, the method comprising:
acquiring multimedia to be detected issued by any target user, and acquiring target characteristics of the multimedia to be detected; the target user is a user which is detected by a white list in advance;
acquiring reference characteristics of the target user based on the multimedia which the target user has passed the quality detection; comprising the following steps:
determining M multimedia which has passed quality detection and is recently released by the target user, and acquiring reference characteristics of each multimedia in the M multimedia as the reference characteristics of the target user;
calculating the distance between the reference feature of the target user and the target feature; comprising the following steps:
calculating the distance between the reference feature of the target user and the target feature by using the following formula:
wherein feature is i Feature for the ith reference feature of the target user t Is the target feature;
and under the condition that the distance meets the preset condition, determining that the multimedia to be detected passes the quality detection.
2. The method of claim 1, wherein the whitelist detection comprises:
determining a user who has released at least N multimedia as a candidate user;
for any candidate user: acquiring quality detection results of N multimedia recently released by the user; and if the quality detection results are all passed detection, determining that the user passes white list detection.
3. The method according to claim 1, wherein the determining that the multimedia to be detected passes quality detection in case the distance satisfies a preset condition comprises:
acquiring an average distance between the reference features of the target user;
and under the condition that the distance is smaller than the average distance, determining that the multimedia to be detected passes quality detection.
4. A multimedia quality detection apparatus, the apparatus comprising:
the target feature acquisition module is configured to acquire the multimedia to be detected issued by any target user and acquire the target feature of the multimedia to be detected; the target user is a user which is detected by a white list in advance;
a reference feature acquisition module configured to perform acquisition of a reference feature of the target user based on multimedia that the target user has passed quality detection; the reference feature acquisition module comprises:
a multimedia determining unit configured to perform determining M multimedia that have passed quality detection recently issued by the target user;
a feature acquisition unit configured to perform acquisition of a reference feature of each of the M multimedia as a reference feature of the user;
a feature distance calculation module configured to perform calculation of a distance of the reference feature of the target user from the target feature; the feature distance calculation module is specifically configured to perform:
calculating the distance between the reference feature of the target user and the target feature by using the following formula:
wherein feature is i Feature for the ith reference feature of the target user t Is the target feature;
and the detection result determining module is configured to determine that the multimedia to be detected passes quality detection under the condition that the distance meets a preset condition.
5. The apparatus of claim 4, wherein the apparatus further comprises: a whitelist detection module configured to perform:
determining a user who has released at least N multimedia as a candidate user;
for any candidate user: acquiring quality detection results of N multimedia recently released by the user; and if the quality detection results are all passed detection, determining that the user passes white list detection.
6. The apparatus according to claim 4, wherein the detection result determination module is specifically configured to perform:
acquiring an average distance between the reference features of the target user;
and under the condition that the distance is smaller than the average distance, determining that the multimedia to be detected passes quality detection.
7. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the executable instructions to implement the multimedia quality detection method of any one of claims 1 to 3.
8. A storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the multimedia quality detection method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911121308.0A CN110929055B (en) | 2019-11-15 | 2019-11-15 | Multimedia quality detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911121308.0A CN110929055B (en) | 2019-11-15 | 2019-11-15 | Multimedia quality detection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929055A CN110929055A (en) | 2020-03-27 |
| CN110929055B true CN110929055B (en) | 2023-05-02 |
Family
ID=69853130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911121308.0A Active CN110929055B (en) | 2019-11-15 | 2019-11-15 | Multimedia quality detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929055B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218599B (en) * | 2022-02-22 | 2022-05-27 | 飞狐信息技术（天津）有限公司 | Business data processing method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447366A (en) * | 2015-08-07 | 2017-02-22 | 百度在线网络技术（北京）有限公司 | Checking method of multimedia advertisement, and training method and apparatus of advertisement checking model |
| WO2017193760A1 (en) * | 2016-05-09 | 2017-11-16 | 中兴通讯股份有限公司 | Content publishing method, device and system, and content-distributed network system |
| CN107729765A (en) * | 2017-09-30 | 2018-02-23 | 广东欧珀移动通信有限公司 | Management method, device, storage medium and the electronic equipment of multi-medium data |
| CN109670055A (en) * | 2018-11-30 | 2019-04-23 | 广州市百果园信息技术有限公司 | A kind of multi-medium data checking method, device, equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446970B (en) * | 2008-12-15 | 2012-07-04 | 腾讯科技（深圳）有限公司 | Method for censoring and process text contents issued by user and device thereof |
| CN105099796B (en) * | 2014-04-22 | 2018-07-20 | 深圳市志友企业发展促进中心 | A kind of multimedia content change detection method, device and resource broadcasting system |
| CN104580529B (en) * | 2015-02-03 | 2018-03-23 | 郑州悉知信息科技股份有限公司 | A kind of signal auditing method and device |
| CN109101527A (en) * | 2018-06-21 | 2018-12-28 | 中国科学院信息工程研究所 | A kind of magnanimity security log information filter method and device |
| CN109635073A (en) * | 2018-10-18 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Forum's community application management method, device, equipment and computer readable storage medium |
| CN109862062B (en) * | 2018-10-24 | 2022-10-18 | 平安科技（深圳）有限公司 | Content uploading management method and device, electronic equipment and storage medium |
| CN110377900A (en) * | 2019-06-17 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Checking method, device, computer equipment and the storage medium of Web content publication |
-
2019
- 2019-11-15 CN CN201911121308.0A patent/CN110929055B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447366A (en) * | 2015-08-07 | 2017-02-22 | 百度在线网络技术（北京）有限公司 | Checking method of multimedia advertisement, and training method and apparatus of advertisement checking model |
| WO2017193760A1 (en) * | 2016-05-09 | 2017-11-16 | 中兴通讯股份有限公司 | Content publishing method, device and system, and content-distributed network system |
| CN107729765A (en) * | 2017-09-30 | 2018-02-23 | 广东欧珀移动通信有限公司 | Management method, device, storage medium and the electronic equipment of multi-medium data |
| CN109670055A (en) * | 2018-11-30 | 2019-04-23 | 广州市百果园信息技术有限公司 | A kind of multi-medium data checking method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 许杨鹏.基于LNMP的微博内容监控与反垃圾***设计与实现.《中国优秀硕士学位论文全文数据库 信息科技辑》.2018,2018年(第4期),I139-543. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929055A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107105314B (en) | Video playing method and device | |
| CN107945133B (en) | Image processing method and device | |
| CN106408603B (en) | Shooting method and device | |
| EP3300407A1 (en) | Method and device for processing verification code | |
| US10216711B2 (en) | Information collection method and apparatus | |
| CN109360197B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN107133354B (en) | Method and device for acquiring image description information | |
| CN109670077B (en) | Video recommendation method and device and computer-readable storage medium | |
| CN111461304B (en) | Training method of classified neural network, text classification method, device and equipment | |
| CN110781323A (en) | Method and device for determining label of multimedia resource, electronic equipment and storage medium | |
| US11335348B2 (en) | Input method, device, apparatus, and storage medium | |
| CN110941727B (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| CN111104807B (en) | Data processing method and device and electronic equipment | |
| CN105955821B (en) | Pre-reading method and device | |
| CN108629814B (en) | Camera adjusting method and device | |
| CN112948704A (en) | Model training method and device for information recommendation, electronic equipment and medium | |
| CN110929055B (en) | Multimedia quality detection method and device, electronic equipment and storage medium | |
| CN107122801B (en) | Image classification method and device | |
| CN115512116A (en) | Image segmentation model optimization method and device, electronic equipment and readable storage medium | |
| CN105653623B (en) | Picture collection method and device | |
| CN111428806B (en) | Image tag determining method and device, electronic equipment and storage medium | |
| CN111898019B (en) | Information pushing method and device | |
| CN113761275A (en) | Video preview moving picture generation method, device and equipment and readable storage medium | |
| CN113204443A (en) | Data processing method, equipment, medium and product based on federal learning framework | |
| CN108108668B (en) | Age prediction method and device based on image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |