阅读说明：本技术 多媒体文件的侵权检测方法、装置、电子设备及存储介质 (Multimedia file infringement detection method and device, electronic equipment and storage medium ) 是由 李锦春 于 2021-08-31 设计创作，主要内容包括：本申请实施例公开了一种多媒体文件的侵权检测方法、装置、电子设备及存储介质。该方法包括：获取多媒体文件的音频数据,以及影视文件的第一文本信息；对多媒体文件的音频数据进行语音文本转换处理,得到多媒体文件的第二文本信息；获取第一文本信息与第二文本信息之间的匹配度,匹配度用于表征第一文本信息与第二文本信息之间的相似程度；若第一文本信息与第二文本信息之间的匹配度大于预设匹配度阈值,则确定多媒体文件发生侵权。通过上述方式,通过服务器将影视文件的第一文本信息和多媒体文件的第二文本信息自动匹配,基于匹配度来检测多媒体文件是否发生侵权,该过程无需人工参与,从而节省人工成本,提高检测效率。(The embodiment of the application discloses an infringement detection method and device for a multimedia file, electronic equipment and a storage medium. The method comprises the following steps: acquiring audio data of a multimedia file and first text information of a movie file; performing voice text conversion processing on the audio data of the multimedia file to obtain second text information of the multimedia file; acquiring the matching degree between the first text information and the second text information, wherein the matching degree is used for representing the similarity degree between the first text information and the second text information; and if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold value, determining that the multimedia file infringes. By the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether the multimedia file infringes or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.)

1. An infringement detection method for multimedia files, which is applied to a server and comprises the following steps:

acquiring audio data of a multimedia file and first text information of a movie file;

performing voice text conversion processing on the audio data of the multimedia file to obtain second text information of the multimedia file;

acquiring the matching degree between the first text information and the second text information, wherein the matching degree is used for representing the similarity degree between the first text information and the second text information;

and if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold value, determining that the multimedia file infringes.

2. The method according to claim 1, wherein the obtaining the matching degree between the first text information and the second text information comprises:

acquiring an editing distance between the first text information and the second text information, wherein the editing distance is used for representing the minimum number of editing operations required for converting the first text information into the second text information, and the editing operations comprise one or more of the following combinations: delete operation, insert operation, replace operation;

and determining the matching degree between the first text information and the second text information based on the editing distance, wherein the editing distance and the matching degree have a negative correlation relationship.

3. The method according to claim 1, wherein said obtaining the first text information of the movie file comprises:

receiving a sample registration request sent by a terminal, wherein the sample registration request carries an acquisition address of the movie file;

acquiring the movie file based on the acquisition address of the movie file;

and performing voice text conversion processing on the audio data in the video file to obtain first text information of the video file.

4. The method of claim 3, wherein the sample registration request further carries a preset matching degree threshold.

5. The method of claim 3, wherein the sample registration request further carries a handling means, and the handling means refers to an operation means performed on a user account corresponding to the multimedia file after determining that the multimedia file is infringed, and the handling means includes one or more of the following combinations: warning means, stop broadcasting means and seal number means.

6. The method of claim 1, wherein after determining that the multimedia file is infringed, further comprising:

taking a treatment means for the user account corresponding to the multimedia file; the treatment means comprises a combination of one or more of: warning means, stop broadcasting means and seal number means.

7. The method of claim 6, wherein taking disposition measures for the user account corresponding to the multimedia file comprises:

determining the treatment means according to an interval to which the matching degree between the first text information and the second text information belongs, wherein different intervals correspond to different treatment means;

and processing the user account corresponding to the multimedia file according to the processing means.

8. The method according to claim 7, wherein the determining the treatment means according to the interval to which the matching degree between the first text information and the second text information belongs comprises:

if the matching degree belongs to a first interval, determining the handling means as a warning means;

if the matching degree belongs to a second interval, determining that the handling means is a broadcasting stopping means;

if the matching degree belongs to a third interval, determining the handling means as a number sealing means;

the lower limit value of the first interval is greater than or equal to the preset matching degree threshold value, the lower limit value of the second interval is greater than the upper limit value of the first interval, and the lower limit value of the third interval is greater than the upper limit value of the second interval.

9. The method according to any of claims 1 to 8, wherein said obtaining audio data of the multimedia file further comprises:

detecting whether an account corresponding to the multimedia file has the copyright of the movie file or not;

and if the account corresponding to the multimedia file does not have the copyright of the movie file, executing the step of acquiring the audio data of the multimedia file.

10. A multimedia file infringement detection method is applied to a terminal, and the method comprises the following steps:

displaying a film and television file registration page, wherein the film and television file registration page comprises an address input window;

acquiring an acquisition address of the movie file in the address input window;

sending a sample registration request to a server, wherein the sample registration request carries an acquisition address of the movie file; the server is used for acquiring the movie file based on the acquisition address of the movie file; and performing voice-text conversion processing on the audio data in the video file to obtain first text information of the video file, and determining whether the multimedia file infringes based on the matching degree between the first text information and the second text information of the multimedia file.

11. The method of claim 10, wherein the movie file registration page further comprises a disposition means setup window, wherein the sample registration request further carries disposition means, and wherein the method further comprises:

setting a window in the treatment means, and acquiring the treatment means;

the handling means refers to a punishment measure taken after determining that the multimedia file is infringed, and the handling means comprises one or more of the following combinations: warning means, stop broadcasting means, and seal number means;

the warning means is used for prompting that the multimedia file is infringed through alarm information, the broadcasting stopping means is used for stopping broadcasting the multimedia file, and the number sealing means is used for setting an account corresponding to the multimedia file to be in an unavailable state.

12. The method of claim 10, wherein the movie file registration page further comprises a threshold setting window, wherein the sample registration request further carries a preset matching degree threshold, and wherein the method further comprises:

and acquiring the preset matching degree threshold value in the threshold value setting window.

13. An infringement detection apparatus for multimedia files, the apparatus being applied to a server, the apparatus comprising:

the first acquisition module is used for acquiring audio data of the multimedia file and first text information of the movie file;

the transfer module is used for performing voice text conversion processing on the audio data of the multimedia file to obtain second text information of the multimedia file;

the matching module is used for acquiring the matching degree between the first text information and the second text information, and the matching degree is used for representing the similarity degree between the first text information and the second text information;

and the determining module is used for determining that the multimedia file infringes if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold.

14. An infringement detection apparatus for multimedia files, the apparatus being applied to a terminal, the apparatus comprising:

the display module is used for displaying a film and television file registration page, and the film and television file registration page comprises an address input window;

the second acquisition module is used for acquiring the acquisition address of the movie file in the address input window;

the sending module is used for sending a sample registration request to a server, wherein the sample registration request carries an acquisition address of the movie file; the server is used for acquiring the movie file based on the acquisition address of the movie file; and performing voice-text conversion processing on the audio data in the video file to obtain first text information of the video file, and determining whether the multimedia file infringes based on the matching degree between the first text information and the second text information of the multimedia file.

15. An electronic device comprising one or more processors and memory;

one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-12.

16. A computer-readable storage medium storing program code executable by a processor, the computer-readable storage medium comprising stored program code, wherein the method of any of claims 1-12 is performed when the program code is executed.

Technical Field

The present application relates to the technical field of content security auditing, and in particular, to a method and an apparatus for detecting infringement of a multimedia file, an electronic device, and a storage medium.

Background

With the development of internet technology, the application of live video is more and more extensive. However, live video violating the copyright of film and television is also commonplace.

In order to maintain the copyright of the video files, the live broadcast platform needs to quickly identify infringed live broadcast videos in a plurality of live broadcast fields and make penalties in time. In the related technology, the live broadcast platform mainly depends on manual auditing for infringement judgment of live broadcast video, and auditors judge whether the live broadcast video infringes through own video file storage.

The copyright detection method provided by the related technology has huge labor cost consumption and low detection efficiency.

Disclosure of Invention

In view of the foregoing problems, the present application provides a method and an apparatus for detecting infringement of a multimedia file, an electronic device, and a storage medium, so as to solve the foregoing technical problems.

In a first aspect, the present application provides a method for detecting infringement of a multimedia file, applied to a server, the method including: acquiring audio data of a multimedia file and first text information of a movie file; performing voice text conversion processing on the audio data of the multimedia file to obtain second text information of the multimedia file; acquiring the matching degree between the first text information and the second text information, wherein the matching degree is used for representing the similarity degree between the first text information and the second text information; and if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold value, determining that the multimedia file infringes.

In a second aspect, the present application provides a method for detecting infringement of a multimedia file, which is applied to a terminal, and includes: displaying a film and television file registration page, wherein the film and television file registration page comprises an address input window; acquiring an acquisition address of the movie file in an address input window; sending a sample registration request to a server, wherein the sample registration request carries the address of the movie file; the server is used for acquiring the movie file based on the acquisition address of the movie file; and determining whether the multimedia file infringes or not based on the matching degree between the first text information and the second text information of the multimedia file.

In a third aspect, the present application provides an infringement detection apparatus for a multimedia file, applied to a server, the apparatus including: the first acquisition module is used for acquiring audio data of the multimedia file and first text information of the movie file; the transfer module is used for performing voice text conversion processing on the audio data of the multimedia file to obtain second text information of the multimedia file; the matching module is used for acquiring the matching degree between the first text information and the second text information, and the matching degree is used for representing the similarity degree between the first text information and the second text information; and the determining module is used for determining that the multimedia file infringes if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold.

In a fourth aspect, the present application provides an infringement detection apparatus for a multimedia file, applied to a terminal, the apparatus including: the display module is used for displaying a film and television file registration page, and the film and television file registration page comprises an address input window; the second acquisition module is used for acquiring the acquisition address of the movie file in the address input window; the sending module is used for sending a sample registration request to the server, wherein the sample registration request carries an acquisition address of the movie file; the server is used for acquiring the movie file based on the acquisition address of the movie file; and determining whether the multimedia file infringes or not based on the matching degree between the first text information and the second text information of the multimedia file.

In a fifth aspect, the present application provides an electronic device comprising one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods described above.

In a sixth aspect, the present application provides a computer readable storage medium storing program code executable by a processor, the computer readable storage medium comprising stored program code, wherein the method described above is performed when the program code runs.

The application provides a multimedia file infringement detection method and device, electronic equipment and a storage medium. In the method, audio data of a multimedia file and first text information of a movie file are acquired, then the audio data of the multimedia file is subjected to voice text conversion to obtain second text information of the multimedia file, then matching degree between the first text information and the second text information is acquired, and if the matching degree is greater than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether the multimedia file infringes or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic application environment diagram illustrating an infringement detection method for a multimedia file according to the present application;

fig. 2 is a flowchart illustrating an infringement detection method for a multimedia file proposed in the present application;

fig. 3 is a flowchart illustrating an infringement detection method for a multimedia file according to an embodiment of the present application;

FIG. 4 is a flow chart illustrating the interaction between the auditing terminal and the server in the present application;

FIG. 5 shows a schematic view of a movie file registration page of the present application;

FIG. 6 shows a schematic diagram of a terminal rights management page of the present application;

fig. 7 is a flowchart illustrating an infringement detection method for a multimedia file according to another embodiment of the present application;

fig. 8 is a block diagram illustrating a structure of an infringement detection apparatus for a multimedia file provided by the present application;

fig. 9 is a block diagram illustrating a structure of an infringement detection apparatus for a multimedia file provided by the present application;

fig. 10 shows a block diagram of an electronic device according to an embodiment of the present application;

fig. 11 shows a block diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides an infringement detection method and device for a multimedia file, electronic equipment and a storage medium, wherein in the method, audio data of the multimedia file and first text information of a movie file are obtained, then voice text conversion is carried out on the audio data of the multimedia file to obtain second text information of the multimedia file, then matching degree between the first text information and the second text information is obtained, and if the matching degree is greater than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether the multimedia file infringes or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

The following describes an implementation environment related to the infringement detection method for a multimedia file provided by the embodiment of the present application.

Referring to fig. 1, fig. 1 is a schematic diagram of an application environment of a method for detecting infringement of a multimedia file according to the present application. As shown in fig. 1, the enforcement environment may include a server 110, an audit terminal 120, and a live terminal 130.

The server 110 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and an artificial intelligence platform, or a dedicated or platform server providing a car networking service, a road Network cooperation, a vehicle road cooperation, intelligent transportation, automatic driving, an industrial internet service, and data communication (such as 4G, 5G).

In this embodiment, the server 110 has a copyright detection function, that is, calculates a matching degree between text information obtained by converting audio data of a multimedia file and text information obtained by converting audio data of an audio file of a movie file to determine whether the multimedia file infringes the copyright of the movie file. The movie file is a movie file designated by the auditor through the audit terminal 120.

The audit terminal 120 may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like. Optionally, the auditor accesses the video file copyright management platform through the audit terminal 120, and manages the copyright of the video file on the video file management platform, for example, setting a video file that needs to be subjected to copyright detection, setting an infringement judgment condition (that is, a preset matching degree threshold), and setting an infringement penalty measure (that is, a disposal means, and the like). In some embodiments, a movie file copyright management client is run on the audit terminal 120, and the movie file copyright management function is implemented by the movie file copyright management client. The audit terminal 120 and the server 110 may be directly or indirectly connected through wired or wireless communication, which is not limited in this application.

The live broadcast terminal 130 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like, but is not limited thereto. In the embodiment of the present application, the live terminal 130 has a live function. Optionally, a client runs on the live broadcast terminal 130, and the live broadcast function is implemented by the client, where the client includes but is not limited to a live broadcast client, a browser client, an instant messaging client, a content interaction client, a short video client, or a shopping client. The live terminal 130 and the server 110 may be directly or indirectly connected through wired or wireless communication, which is not limited in this application.

In specific implementation, the server 110 obtains a sample level registration request sent by the audit terminal 120, where the sample registration request includes an acquisition address of a video file, a preset matching threshold and a handling means, and the server 110 acquires the video file from the acquisition address. The server 110 obtains the audio data of the multimedia file sent by the live terminal 130, converts the audio data voice text of the movie file into the first text information, converts the audio data voice text of the multimedia file into the second text information by executing the infringement detection method of the multimedia file provided by the application, and then determines the detection result through the matching algorithm. If it is determined that the multimedia file is infringed, the server 110 takes measures to the user account corresponding to the multimedia file in the live terminal 130.

Referring to fig. 2, the server performs slicing and automatic speech recognition processing on the acquired audio data of the movie sample, and stores the obtained text information into a movie sample subtitle approximation library. And then the server acquires audio data from the live stream, slices the audio data into audio segments and caches the audio segments, and then performs automatic voice recognition processing to obtain segment text information. And finally, matching the fragment text information with the text information in the movie and television sample subtitle approximation library, and detecting a result.

Embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Referring to fig. 3, the method for detecting infringement of a multimedia file provided by the present application is applied to a server. The method comprises the following steps:

s210, acquiring audio data of the multimedia file and first text information of the movie file.

In some embodiments, the multimedia file comprises a live stream. In other embodiments, the multimedia file comprises a video file uploaded by a user on a video platform.

When the multimedia file comprises a live stream, audio data of the multimedia file is acquired by a microphone assembly of the live terminal. In some embodiments, the server obtains audio data of a multimedia file sent by a live terminal. In other embodiments, the server obtains audio data of the multimedia file sent by the streaming server, and the streaming server is configured to receive the multimedia file uploaded by the live terminal and send the multimedia file to each of the viewer terminals viewing the live broadcast. And when the multimedia file comprises a video file uploaded by a user on the video platform, the server acquires audio data of the multimedia file from a server corresponding to the video platform.

The number of the movie files may be one or more. In some embodiments, the movie files are all movie files in a movie sample subtitle approximation library. In other embodiments, the movie file is a movie file registered by an auditor. In other embodiments, the movie file is a target movie file designated by the auditor. The first text information of the film and television file is the text information obtained by voice text conversion processing of the audio data of the film and television file. Optionally, the server obtains the first text information of the movie file from the movie sample approximation library.

In some embodiments, before acquiring the audio data of the multimedia file, it is further required to detect whether an account corresponding to the multimedia file has a copyright of the movie file, for example, an official account of a movie play and an official account of a video playing platform may have a copyright of a part of the movie file. Executing the step of acquiring the audio data of the multimedia file when the account corresponding to the multimedia file is confirmed not to have the copyright of the movie file; if the account corresponding to the multimedia file is confirmed to have the copyright of the movie file, the subsequent infringement detection step is not required to be executed. Therefore, the error processing of the account with the copyright of the film and television file can be avoided, and the playing of the multimedia file is prevented from being influenced.

S220, voice text conversion processing is carried out on the audio data of the multimedia file to obtain second text information of the multimedia file.

In the embodiment of the application, the server converts the audio data of the multimedia file into the text data through an automatic speech recognition technology to obtain the second text information. In some embodiments, the automatic speech recognition technique may be a stochastic model algorithm that recognizes speech using the steps of extracting features, training templates, classifying templates, and determining templates, including dynamic time warping, hidden markov model theory, and vector quantization techniques. In other embodiments, the automatic speech recognition technique may also be a neural network algorithm, which performs speech recognition by repeatedly learning and training the audio data and gradually adjusting the method of changing the neuron connection weights.

In some embodiments, the server divides the audio data of the multimedia file into at least one piece of audio sub-data, and then performs voice-to-text conversion processing on the audio sub-data to obtain second text information of each piece of audio sub-data. Thus, real-time voice text conversion of the multimedia file can be realized. Optionally, the server slices the audio data of the multimedia file according to a first preset time interval to extract at least one multimedia file audio sub-data, where the first preset time interval is set according to experiments or experience. Illustratively, the first preset time interval is typically set to be between 30 seconds and 60 seconds.

Further, before performing the voice text conversion processing on the audio sub-data, the audio sub-data of the multimedia file needs to be screened to remove invalid audio sub-data, such as muted audio sub-data and other non-human audio sub-data. Therefore, the number of the audio subdata can be reduced, the time for converting the voice text is saved, and the infringement detection efficiency is improved.

And S230, acquiring the matching degree between the first text information and the second text information.

The matching degree represents a degree of similarity between the first text information and the second text information. The higher the matching degree is, the higher the degree of similarity between the first text information and the second text information is. The lower the matching degree, the lower the degree of similarity between the first text information and the second text information.

In some embodiments, the server obtains an editing distance between the first text information and the second text information, and determines a matching degree between the first text information and the second text information based on the editing distance. The algorithm for determining the matching degree by editing the distance may be referred to as an "editing distance similarity algorithm".

The edit distance is used to characterize a minimum number of editing operations required to convert the first text information into the second text information. The editing operation includes a combination of one or more of the following: delete operation, insert operation, replace operation. The deletion operation refers to deleting characters in the first text information or the second text information. The inserting operation refers to inserting a character in the first text information or the second text information. The replacing operation is to replace characters in the first text information or the second text information with other characters. The editing distance and the matching degree are in a negative correlation relationship. That is, the smaller the edit distance, the greater the matching degree; the larger the edit distance, the smaller the matching degree. Alternatively, the relationship between the matching degree and the edit distance is expressed by the following formula.

Matching degree 1-edit distance/text information length value_max

Text message length value_maxIndicating the larger of the length value of the first text information and the length value of the second text information.

For example, the first text information is "i love to watch tv", the second text information is "i want to watch tv", and one replacement operation is required to convert the first text information into the second text information, so the edit distance is 1, and accordingly, the matching degree is 1-1/5-0.8.

S240, if the matching degree between the first text information and the second text information is larger than a preset matching degree threshold value, determining that the multimedia file infringes.

The preset matching degree threshold value can be set by a server or an auditing terminal in a default mode or can be set by an auditing person in a self-defined mode. The preset matching degree threshold values of different video files can be the same or different. In general, the threshold may be any value between 0.8 and 0.99, and the preset matching threshold is 90% for example.

And when the matching degree between the first text information and the second text information is less than or equal to a preset matching degree threshold value, confirming that the multimedia file is not infringed.

In some embodiments, after determining that the multimedia file is infringed, the server also takes a treatment measure for the user account corresponding to the multimedia file.

The handling means is an operation means executed on the user account corresponding to the multimedia file after determining that the multimedia file is infringed. The treatment means includes warning means, stop broadcasting means and seal number means. The warning means is that the multimedia file is prompted to have infringement through alarm information. The stop means is to stop playing the multimedia file. The number sealing means is to set the account number corresponding to the multimedia file to be in an unavailable state. In addition, the server may delete the multimedia file.

In a possible implementation manner, the server determines the treatment means according to a section to which the matching degree between the first text information and the second text information belongs, and different sections correspond to different treatment means.

Optionally, if the matching degree belongs to the first interval, determining the handling means as a warning means; if the matching degree belongs to the second interval, determining the handling means as a broadcasting stopping means; and if the matching degree belongs to the third interval, determining the processing means as a number sealing means. . The lower limit value of the first interval is greater than or equal to a preset matching degree threshold value, the lower limit value of the second interval is greater than the upper limit value of the first interval, and the lower limit value of the third interval is greater than the upper limit value of the second interval.

For example, the preset matching degree threshold of a certain video file is 0.8, the first interval is 0.8-0.9, the second interval is 0.9-0.95, and the third interval is 0.95-0.99. When the matching degree is 0.85, the treatment means is a warning means; when the matching degree is 0.92, the treatment means is a broadcasting stopping means; when the matching degree is 0.98, the processing means is a number sealing means.

In other embodiments, the handling means may also be set by an auditor, and the server processes the user account corresponding to the multimedia file according to the handling means set by the auditor.

According to the infringement detection method for the multimedia file, audio data of the multimedia file and first text information of a movie file are obtained, then voice text conversion is carried out on the audio data of the multimedia file to obtain second text information of the multimedia file, then matching degree between the first text information and the second text information is obtained, and if the matching degree is larger than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether the multimedia file infringes or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

Referring to fig. 4, the present application provides a method for detecting infringement of a multimedia file, and this embodiment describes an interactive process between an audit terminal and a server, where the method may include:

s211, the terminal displays a film and television file registration page.

The film and television file registration page is used for allowing auditors to register the film and television files with the infringement detection requirement. The movie file registration page includes a name input window and an address input window. The name input window is used for inputting the name of the movie file. The address input window is used for inputting the acquisition address of the movie file.

In some embodiments, the movie file registration page further includes a threshold setting window for inputting a preset matching degree threshold. In other embodiments, the movie file registration page further includes a handling means setup window for inputting a handling means.

As shown in fig. 5, the audit terminal displays a movie file registration page 50, and the movie file registration page 50 includes an address input window 51, a name input window 52, a threshold value setting window 53, and a disposal means setting window 54.

In some embodiments, the terminal receives the registration instruction at the copyright management page, and then skips to display the movie file registration page according to the registration instruction. The copyright management page is used for managing the film and television files with infringement detection, such as inquiry, deletion, addition and the like. Optionally, the copyright management page displays a new button, and the terminal receives a registration instruction when receiving a trigger signal corresponding to the new button.

As shown in fig. 6, the copyright management page 60 includes movie file information 61 for which there is a need for infringement detection, a query button 62, an add button 63, and a delete button 64. The movie file information 61 includes a serial number, a movie name, an acquisition path, a storage time, a preset matching threshold, a disposal means, and the like of each movie file. The auditor wants to add a new movie file, can click the new adding button 63 on the copyright management page 60, and then the terminal skips to display the movie file registration page.

S212, the terminal acquires the acquisition address of the video file in the address input window.

The acquisition address of the movie file can be input by an auditor. Referring to fig. 5, the auditing terminal may obtain an obtaining address "http:// wlwzdownload. com" of the movie file input by the auditor in the address input window 51.

And S213, the terminal acquires a preset matching degree threshold value in a threshold value setting window.

The preset matching degree threshold value is input by an auditor, or is set by default by a terminal. And under the condition that the audit staff does not set the preset matching degree threshold value, setting the preset matching degree threshold value by default through the terminal. Referring to fig. 5, the auditor may enter a preset threshold of "0.8" for the degree of match in the threshold setting window 53.

S214, the terminal acquires the treatment means in the treatment means setting window.

The disposal means is input by an auditor or is set by default by the terminal. And if the treatment means is not set by the auditor, the treatment means is set by default by the terminal. In some embodiments, when the terminal receives an edit instruction for the treatment means setting window, the terminal displays a treatment means list, the terminal receives a selection signal for a target treatment means in the treatment means list, and the target treatment means is determined as a treatment means for a multimedia file in which infringement exists. The list of handling means includes off-air means, seal number means, warning means, automatic means, etc. The warning means is that the multimedia file is prompted to have infringement through alarm information. The stop means is to stop playing the multimedia file. The number sealing means is to set the account number corresponding to the multimedia file to be in an unavailable state. When the examiner does not select the treatment means, the terminal confirms the treatment means as automatic, and the server confirms the treatment means in accordance with the section to which the matching degree belongs.

Referring to fig. 5, the reviewer may enter the treatment instrument "stop" in a treatment instrument setup window 54.

S215, the terminal transmits a sample registration request to the server.

The sample registration request comprises the name of the film and television file, an acquisition address, a preset matching degree threshold value and a disposal means. In some embodiments, the movie file registration page comprises a submit button, and the auditor triggers the submit button after confirming that the information of the movie file registration page is correct, and the terminal sends a sample registration request to the server.

As shown in fig. 5, the movie file registration page 50 also includes a submit button 55 and a cancel button 56. After confirming that the information on the film and television file registration page 50 is correct, the auditor triggers a submit button 55, and the terminal sends a sample registration request to the server. When the auditor cancels the setting of the related information of the movie file, the cancel button 56 is triggered, and the movie file registration page 50 is closed.

Accordingly, the server receives the sample registration request transmitted from the terminal.

S216, the server acquires the video file based on the acquisition address of the video file.

And the server downloads the movie file from the movie file information base based on the acquired address.

S217, performing voice text conversion processing on the audio data in the movie file to obtain first text information of the movie file.

The server converts audio data of the film and television file into text data through an automatic voice recognition technology to obtain first text information, and stores the first text information into a film and television sample subtitle approximate library so as to facilitate subsequent infringement detection. The automatic speech recognition technology can be a stochastic model method, speech is recognized by adopting the steps of extracting features, training templates, classifying the templates and judging the templates, and the stochastic model algorithm comprises dynamic time warping, hidden Markov model theory, vector quantization technology and the like. In other embodiments, the automatic speech recognition technique may also be a neural network method, which performs speech recognition by repeatedly learning and training the audio data and gradually adjusting the method of changing the neuron connection weights.

In some embodiments, the server divides the audio data of the movie file into at least one piece of audio subdata, and then performs voice-to-text conversion processing on the audio subdata to obtain second text information of each piece of audio subdata. Optionally, the server slices the audio data of the video file at a second preset time interval to extract at least one piece of audio subdata of the video file, where the second preset time interval may be equal to or greater than the first preset time interval.

Further, before performing the voice text conversion processing on the audio sub-data, the audio sub-data of the movie file needs to be screened to remove invalid audio sub-data, such as muted audio sub-data and other non-human-voice audio sub-data. Therefore, the number of the audio subdata can be reduced, the time for converting the voice text is saved, and the infringement detection efficiency is improved.

According to the infringement detection method for the multimedia file, an auditor can register the movie file on a terminal, set a matching degree threshold value related to infringement detection and a handling means after infringement occurs, and send the information to a server to achieve copyright management of the movie file.

Referring to fig. 7, the present application provides a method for detecting infringement of a multimedia file, applied to an audit terminal, where the method may include:

s710, displaying a film and television file registration page, wherein the film and television file registration page comprises an address input window.

S720, acquiring the acquisition address of the movie file in the address input window.

And S730, sending a sample registration request to the server, wherein the sample registration request carries the acquisition address of the movie file.

The server is used for acquiring the movie file based on the acquisition address of the movie file; and determining whether the multimedia file infringes or not based on the matching degree between the first text information and the second text information of the multimedia file.

According to the infringement detection method for the multimedia file, a server can obtain audio data of the multimedia file and first text information of a movie file, then voice text conversion is carried out on the audio data of the multimedia file to obtain second text information of the multimedia file, then matching degree between the first text information and the second text information is obtained, and if the matching degree is larger than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether infringement occurs or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

Referring to fig. 8, a block diagram of an apparatus for detecting infringement of a multimedia file provided by the present application, operating on an electronic device, is shown, where the apparatus 800 includes: a first obtaining module 810, a transcription module 820, a matching module 830, and a determining module 840.

A first obtaining module 810, configured to obtain audio data of a multimedia file and first text information of a movie file; a transcription module 820, configured to perform voice-to-text conversion processing on audio data of the multimedia file to obtain second text information of the multimedia file; the matching module 830 is configured to obtain a matching degree between the first text information and the second text information, where the matching degree is used to represent a similarity degree between the first text information and the second text information; the determining module 840 is configured to determine that the multimedia file is infringed if the matching degree between the first text information and the second text information is greater than a preset matching degree threshold.

According to the infringement detection device for the multimedia file, the audio data of the multimedia file and the first text information of the movie file are obtained, then the audio data of the multimedia file is subjected to voice text conversion to obtain the second text information of the multimedia file, then the matching degree between the first text information and the second text information is obtained, and if the matching degree is larger than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether infringement occurs or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

In some embodiments, the matching module 830 is configured to obtain a matching degree between the first text information and the second text information, where the matching degree is used to represent a similarity degree between the first text information and the second text information. The matching module 430 is further configured to obtain an editing distance between the first text information and the second text information, where the editing distance is used to represent a minimum number of editing operations required to convert the first text information into the second text information, and the editing operations include one or more of the following combinations: delete operation, insert operation, replace operation; and determining the matching degree between the first text information and the second text information based on the editing distance, wherein the editing distance and the matching degree have a negative correlation relationship.

In some embodiments, the first obtaining module 810 is further configured to receive a sample registration request sent by the terminal, where the sample registration request carries an obtaining address of the movie and television file; acquiring a movie file based on the acquisition address of the movie file; and performing voice text conversion processing on the audio data in the movie file to obtain first text information of the movie file.

In some embodiments, the sample registration request also carries a preset match threshold.

In some embodiments, the sample registration request further carries a handling means, where the handling means refers to an operation means performed on a user account corresponding to the multimedia file after determining that the multimedia file is infringed, and the handling means includes one or more of the following combinations: warning means, stop broadcasting means and seal number means.

In some embodiments, the apparatus 800 further comprises: the processing module is used for taking processing means for the user account corresponding to the multimedia file; the treatment means comprises a combination of one or more of the following: warning means, stop broadcasting means and seal number means.

In some embodiments, the processing module is further configured to determine a processing means according to an interval to which a matching degree between the first text information and the second text information belongs, where different intervals correspond to different processing means; and processing the user account corresponding to the multimedia file according to a processing means.

In some embodiments, the handling module is further configured to determine that the handling means is an alert means if the matching degree belongs to the first interval; if the matching degree belongs to the second interval, determining the handling means as a broadcasting stopping means; if the matching degree belongs to the third interval, determining the handling means as a number sealing means; the lower limit value of the first interval is greater than or equal to the preset matching degree threshold value, the lower limit value of the second interval is greater than the upper limit value of the first interval, and the lower limit value of the third interval is greater than the upper limit value of the second interval.

As one way, the apparatus 800 further comprises: the detection module is used for detecting whether the account corresponding to the multimedia file has the copyright of the film and television file; and if the account corresponding to the multimedia file does not have the copyright of the film and television file, executing the step of acquiring the audio data of the multimedia file.

Referring to fig. 9, a block diagram of an apparatus for detecting infringement of a multimedia file provided by the present application, operating in an electronic device, includes: a display module 910, a second obtaining module 920, and a sending module 930.

A display module 910, configured to display a movie file registration page, where the movie file registration page includes an address input window; a second obtaining module 920, configured to obtain an obtaining address of the movie file in the address input window; a sending module 930, configured to send a sample registration request to the server, where the sample registration request carries an acquisition address of the movie file; the server is used for acquiring the movie file based on the acquisition address of the movie file; and determining whether the multimedia file infringes or not based on the matching degree between the first text information and the second text information of the multimedia file.

In some embodiments, the film and television file registration page further comprises a disposal means setting window, and the sample registration request further carries a disposal means; a second obtaining module 920, configured to set a window in the treatment means, and obtain the treatment means; the treatment means refers to a punishment measure taken after determining that the multimedia file is infringed, and the treatment means comprises one or more of the following combinations: warning means, stop broadcasting means, and seal number means; the warning means is used for prompting that the multimedia file is infringed through the alarm information, the broadcasting stopping means is used for stopping broadcasting the multimedia file, and the number sealing means is used for setting the account corresponding to the multimedia file to be in an unavailable state.

In some embodiments, the movie file registration page further includes a threshold setting window, and the sample registration request further carries a preset matching degree threshold; the second obtaining module 920 is further configured to obtain a preset matching degree threshold at the threshold setting window.

According to the infringement detection device for the multimedia file, the audio data of the multimedia file and the first text information of the movie file are obtained, then the audio data of the multimedia file is subjected to voice text conversion to obtain the second text information of the multimedia file, then the matching degree between the first text information and the second text information is obtained, and if the matching degree is larger than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether infringement occurs or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

It should be noted that, in the present application, an embodiment of the apparatus corresponds to an embodiment of the foregoing method, a specific implementation principle of each unit in the embodiment of the apparatus is similar to that in the embodiment of the foregoing method, and specific contents in the embodiment of the apparatus may refer to the embodiment of the method, which is not described in detail in the embodiment of the apparatus.

Referring to fig. 10, a block diagram of an electronic device provided in the present application is shown.

Based on the text processing method and apparatus, another electronic device 1000 capable of executing the text processing method is further provided in this embodiment of the application. The electronic device 1000 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like capable of running an application. The electronic device 1000 includes one or more processors 1010 (only one shown), a memory 1020, a network module 1030, a voice recognition device 1040, and a screen 1050 coupled to each other. The memory 1020 stores programs that can execute the content of the foregoing embodiments, and the processor 1010 can execute the programs stored in the memory 1020.

Processor 1010 may include one or more cores for processing data, among other things. The processor 1010 interfaces with various components throughout the electronic device 1000 using various interfaces and circuitry to perform various functions of the electronic device 1000 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1020 and invoking data stored in the memory 1020. Alternatively, the processor 1010 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1010 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1010, but may be implemented by a communication chip.

The Memory 1020 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 1020 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1020 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area may also store data created by the audit terminal 120 during use (e.g., phone book, audio and video data, chat log data), etc.

The network module 1030 is configured to receive and transmit electromagnetic waves, and implement interconversion between the electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, for example, an audio playing device. The network module 1030 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The network module 1030 may communicate with various networks such as the internet, an intranet, a wireless network, or with other devices via a wireless network. The wireless network may comprise a cellular telephone network, a wireless local area network, or a metropolitan area network. For example, the network module 1030 may exchange information with a base station.

The speech recognition device 1040 may be used for speech-to-text conversion such that the electronic device 1000 may convert audio data of a movie file and audio data of a multimedia file into first text information and second text information.

Referring to fig. 11, a computer-readable storage medium is provided. The computer readable medium 1100 has stored therein a program code that can be called by a processor to execute the method described in the above method embodiments.

The computer-readable storage medium 1100 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 1100 includes a non-volatile computer-readable storage medium. The computer readable storage medium 1100 has storage space for program code 1110 for performing any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 1110 may be compressed, for example, in a suitable form.

In summary, the present application provides a method and an apparatus for detecting infringement of a multimedia file, and an electronic device. In the method, audio data of a multimedia file and first text information of a movie file are acquired, then the audio data of the multimedia file is subjected to voice text conversion to obtain second text information of the multimedia file, then matching degree between the first text information and the second text information is acquired, and if the matching degree is greater than a preset matching degree threshold value, infringement of the multimedia file can be determined; by the method, the first text information of the movie file and the second text information of the multimedia file are automatically matched through the server, whether infringement occurs or not is detected based on the matching degree, manual participation is not needed in the process, accordingly, labor cost is saved, and detection efficiency is improved.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical feature diagrams may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.