CN110347866A - Information processing method, device, storage medium and electronic equipment - Google Patents
Information processing method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110347866A CN110347866A CN201910606313.4A CN201910606313A CN110347866A CN 110347866 A CN110347866 A CN 110347866A CN 201910606313 A CN201910606313 A CN 201910606313A CN 110347866 A CN110347866 A CN 110347866A
- Authority
- CN
- China
- Prior art keywords
- keyword
- label
- data
- audio data
- target data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7834—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using audio features
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of information processing method, device, storage medium and electronic equipments, wherein this method comprises: obtaining target data, wherein the target data includes image data and audio data;Keyword search is carried out to the audio data;At least one keyword in the audio data is obtained according to preset condition, corresponding first label is formed based on the keyword;By first label addition in the image of the target data, the first operation can be carried out to the target data by first label.The information processing method of the embodiment of the present invention, mode based on speech recognition, keyword search is carried out to the speech content of personage in target data, obtain the keyword that can characterize target data content, and the first label is added based on the keyword, it can be realized and add tagged purpose automatically, be beneficial to improve the addition efficiency of label, to save cost of labor.
Description
Technical field
This application involves technical field of electronic equipment, in particular to a kind of information processing method, information processing unit, storage
Medium and electronic equipment.
Background technique
With the development of multimedia technology, pass through videograph conference process, teaching process, enforcing law and monitoring process
Equal event procedure are more and more common, and consequent is that the data volume of video is increasing, and user by searching in video manually
Particular video frequency content efficiency it is lower.In the prior art, by way of adding video tab at specific video content, with
Facilitate user when playing video, the mesh quickly jumped at particular video frequency content can be realized by clicking video tab
's.But photographic device can not directly add video tab in the prior art, addition manually after the completion of needing to image, video tab
It is lower to add efficiency.
Apply for content
This application provides a kind of information processing method, information processing unit, storage medium and electronic equipments, for solving
It adds the lower technical problem of video tab efficiency manually in the prior art, video tab can be added automatically.
In order to solve the above-mentioned technical problem, embodiments herein adopts the technical scheme that
A kind of information processing method, comprising:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, is formed accordingly based on the keyword
The first label;
It, can be to described to pass through first label by first label addition in the image of the target data
Target data carries out the first operation.
In some embodiments, described to obtain at least one keyword in the audio data according to preset condition, packet
It includes:
In the case where including the first keyword in detecting the audio data, the appearance of first keyword is judged
Whether frequency meets predeterminated frequency threshold value;
If it is, determining that first keyword is effective keyword, and obtain first keyword.
It is in some embodiments, described that corresponding first label is formed based on the keyword, comprising:
First first keyword detected in special time period and corresponding first time point are obtained, wherein described
Special time period is that the frequency of occurrences of first keyword meets the predeterminated frequency threshold value corresponding period;
Corresponding first label is formed based on first first keyword and the first time point.
In some embodiments, described to obtain at least one keyword in the audio data, base according to preset condition
Corresponding first label is formed in the keyword, comprising:
In the case where including the second keyword in detecting the audio data, determine comprising second keyword
The start time point that audio data section plays, wherein the audio data section is the continuous audio data of the same user of acquisition;
Corresponding first label is formed based on second keyword and the start time point.
It is in some embodiments, described that keyword search is carried out to the audio data, comprising:
Identify the corresponding text information of the audio data;
It whether detects in the text information including the preset keyword in preset set of keywords.
In some embodiments, the acquisition target data includes:
Obtain the target data generated in the first electronic equipment and the second electronic equipment video call process;
Or
Obtain the target data in preset memory areas.
In some embodiments, described to include: to audio data progress keyword search
Keyword search is carried out to the audio data while obtaining the target data;Or
Keyword search is carried out to the audio data according to the first instruction.
A kind of information processing unit, comprising:
Module is obtained, for obtaining target data, wherein the target data includes image data and audio data;
Detection module, for carrying out keyword search to the audio data;
Module is obtained, for obtaining at least one keyword in the audio data according to preset condition, based on described
Keyword forms corresponding first label;
Adding module, for adding first label in the image of the target data, to pass through described first
Label can carry out the first operation to the target data.
A kind of storage medium is stored with computer program, realizes following steps when loaded and executed:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, is formed accordingly based on the keyword
The first label;
It, can be to described to pass through first label by first label addition in the image of the target data
Target data carries out the first operation.
A kind of electronic equipment includes at least memory and processor, is stored with executable program on the memory, described
Processor realizes following steps when executing the executable program on the memory:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, is formed accordingly based on the keyword
The first label;
It, can be to described to pass through first label by first label addition in the image of the target data
Target data carries out the first operation.
The beneficial effect of the embodiment of the present application is:
The information processing method of the embodiment of the present invention, by carrying out keyword search to the audio data in target data,
At least one keyword in audio data is obtained according to preset condition later, and the keyword based on acquisition forms corresponding the
One label, finally by the addition of the first label in the image of target data.Namely the mode based on speech recognition, to target data
The speech content of middle personage carries out keyword search, obtains the keyword that can characterize target data content, and be based on the key
Word adds the first label, can be realized and adds tagged purpose automatically, is beneficial to improve the addition efficiency of label, artificial to save
Cost.
Detailed description of the invention
Fig. 1 is the flow chart of the information processing method of the embodiment of the present application;
Fig. 2 is a kind of scene schematic diagram of specific embodiment of the information processing method of the embodiment of the present application;
Fig. 3 is the process for carrying out keyword search step in the information processing method of the embodiment of the present application to audio data
Figure;
Fig. 4 is to obtain keyword in the information processing method of the embodiment of the present application and form the first label step based on keyword
A kind of flow chart of rapid embodiment;
Fig. 5 is to obtain keyword in the information processing method of the embodiment of the present application and form the first label step based on keyword
The flow chart of rapid another embodiment;
Fig. 6 is the structural block diagram of the information processing unit of the embodiment of the present application;
Fig. 7 is the structural block diagram of the detection module of the information processing unit of the embodiment of the present application;
Fig. 8 is a kind of structural block diagram of embodiment of the formation module of the information processing unit of the embodiment of the present application;
Fig. 9 is the structural block diagram of the another embodiment of the formation module of the information processing unit of the embodiment of the present application;
Figure 10 is the structural block diagram of the electronic equipment of the embodiment of the present application.
Description of symbols:
10- obtains module;20- detection module;21- recognition unit;22- detection unit;30- forms module;31- judgement
Unit;32- third acquiring unit;The 4th acquiring unit of 33-;34- first forms unit;35- determination unit;The formation of 36- second
Unit;40- adding module;901- memory;902- processor.
Specific embodiment
The various schemes and feature of the application are described herein with reference to attached drawing.
It should be understood that various modifications can be made to the embodiment applied herein.Therefore, description above should not regard
To limit, and only as the example of embodiment.Those skilled in the art will expect in the scope and spirit of the present application
Other modifications.
The attached drawing being included in the description and forms part of the description shows embodiments herein, and with it is upper
What face provided is used to explain the application together to substantially description and the detailed description given below to embodiment of the application
Principle.
By the description of the preferred form with reference to the accompanying drawings to the embodiment for being given as non-limiting example, the application's
These and other characteristic will become apparent.
It is also understood that although the application is described referring to some specific examples, those skilled in the art
Member realizes many other equivalents of the application in which can determine, they have feature as claimed in claim and therefore all
In the protection scope defined by whereby.
When read in conjunction with the accompanying drawings, in view of following detailed description, above and other aspect, the feature and advantage of the application will become
It is more readily apparent.
The specific embodiment of the application is described hereinafter with reference to attached drawing;It will be appreciated, however, that applied embodiment is only
Various ways implementation can be used in the example of the application.Known and/or duplicate function and structure and be not described in detail to avoid
Unnecessary or extra details makes the application smudgy.Therefore, applied specific structural and functionality is thin herein
Section is not intended to restrictions, but as just the basis of claim and representative basis be used to instructing those skilled in the art with
Substantially any appropriate detailed construction diversely uses the application.
This specification can be used phrase " in one embodiment ", " in another embodiment ", " in another embodiment
In " or " in other embodiments ", it can be referred to one or more of the identical or different embodiment according to the application.
The embodiment of the present application provides a kind of information processing method, specifically comprises the following steps:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, is formed accordingly based on the keyword
The first label;
It, can be to described to pass through first label by first label addition in the image of the target data
Target data carries out the first operation.
The information processing method of the embodiment of the present invention, by carrying out keyword search to the audio data in target data,
At least one keyword in audio data is obtained according to preset condition later, and the keyword based on acquisition forms corresponding the
One label, finally by the addition of the first label in the image of target data.Namely the mode based on speech recognition, to target data
The speech content of middle personage carries out keyword search, obtains the keyword that can characterize target data content, and be based on the key
Word adds the first label, can be realized and adds tagged purpose automatically, is beneficial to improve the addition efficiency of label, artificial to save
Cost.
The application preferred embodiment is described in detail with reference to the accompanying drawing.
Fig. 1 is the flow chart of the information processing method of the embodiment of the present application, shown in Figure 1, the letter of the embodiment of the present application
Breath processing method includes the following steps:
S100 obtains target data, wherein the target data includes image data and audio data, such as video class number
According to etc..The target data can be the data generated in real time, can also be the target data being stored in preset memory areas, such as be stored in
Target data in database.In the specific implementation process, the process for obtaining target data can be for from for acquiring video class number
According to video camera or calculator in video class data is deployed into the process of target storage position, can also be for from target storage position
Target data is extracted into the process in built-in storage or register.
S200 carries out keyword search to the audio data.Wherein, which matches with image data
Audio, the audio data can be the audio recorded while acquisition or production image data, can also be to get image data
Afterwards, the audio data of recording is matched.The keyword can be the keyword chosen in advance, and carrying out keyword search to audio data is
Whether to include the keyword chosen in advance in detection audio data.The keyword can also be for according to default detected rule acquisition
Keyword, carrying out keyword search to audio data is that audio data is detected and obtained according to default detected rule
The word that meets default examination criteria, word are as keyword.Such as using the higher word of the frequency of occurrences as keyword.The key detected
Word can be one or more identical keywords, can also be multiple and different keywords.
S300 obtains at least one keyword in the audio data according to preset condition, based on the crucial font
At corresponding first label.The keyword that is obtained from a segment of audio data may quantity it is more, but and not all meet addition
The condition of label.For example, causing same words to continuously repeat appearance because talker's sentence repeats when talking with or explaining and publicising.
Although the video content being also possible in the keyword and video data that occur obtaining mismatches alternatively, keyword does not repeat
The problems such as.In the specific implementation process, the settable preset condition for being screened to keyword, and according to preset condition pair
Keyword is screened, and to obtain the one or more keywords for meeting preset condition, is then based on keyword and is formed accordingly
First label, such as using keyword as the title of the first label, or using keyword as label substance of label etc..
S400 can to pass through first label by first label addition in the image of the target data
First operation is carried out to the target data.After first label that completes, add tags in the image of target data
Corresponding position.First operation can be skip operation, search operaqtion or other operations.Such as in target data playing process
In, first label can be shown in the positions such as progress bar or tab bar, user can be by selecting first label or click
Directionkeys etc. adjusts the playback progress of target data to the corresponding position of the first label.After label is completed in addition, it can incite somebody to action
Target data is uploaded to database, and forms the first label with search term and be associated with, so that user is when using word and search is searched for
The first label and corresponding target data can be retrieved, is somebody's turn to do with facilitating user to obtain the target data and play from corresponding position
Target data.
Information processing method in the embodiment of the present application carries out keyword search, energy to audio data based on speech recognition
Enough automatic acquisitions can characterize the keyword of target data content, and first is added in target data based on the keyword got
Label allows users to execute the first operation to target data using first label.Without artificially passing through viewing target data
Content carry out artificial definition of keywords, the keyword based on acquisition can add the first label automatically, be beneficial to improve label and add
Add efficiency, save cost of labor, label is added suitable for the video data to magnanimity, to improve user experience.
The process of target data is obtained there are many form, is cooperated shown in Fig. 2, in one embodiment, the acquisition target
Data can include: obtain the target data generated in the first electronic equipment and the second electronic equipment video call process.This first
Electronic equipment and the second electronic equipment can there are many type, such as laptop, tablet computer, smart phone are logical with video
Talk about the electronic equipment of function.In this way, can synchronize and adopt in video call process in the first electronic equipment and the second electronic equipment
Collect image data and audio data to form target data.Such as in long-distance video teaching process, the electronics of teacher side can be passed through
Image data and audio data in equipment acquisition teaching process utilize speech recognition technology to detect audio to form target data
Keyword in data forms the first label based on keyword and corresponding time, then adds the first label in number of targets
According to image on, later can by target data store in the database for student viewing, can reduce teacher burden, simplify religion
Learn the manufacturing process of video.Also the video data in conference process can be acquired by conference system, so in such as teleconference
Keyword search is carried out to video data afterwards and adds label, it will be able to fast, easily make TV news.In another reality
It applies in example, the target data of acquisition can also be the target data in preset memory areas.The preset memory areas can be electronic equipment
Specific memory section in memory can also be the specific memory section in such as database of Video service quotient.The target data can
For the video data of the types such as such as film, TV play, documentary film, short-sighted frequency.By taking Teaching Service platform as an example, recorded in teacher
It can be placed in preset memory areas after completing video data, the video data in preset memory areas can be obtained automatically by system later
And label is added, it is uploaded to Foreground Data library, then for user's viewing.
In some embodiments, keyword search is carried out to the audio data, the target data can be being got
Simultaneously with regard to carrying out keyword search to the audio data automatically, the audio data can also be carried out according to the first instruction crucial
Word detection, namely start to carry out keyword search to audio data in the case where getting the first instruction.With teleconference system
For system, in a kind of situation, can during meeting carries out synchronous acquisition one or more conference terminal video data, with this
Meanwhile carrying out keyword search automatically and adding label, to add label to entire video data.In another middle situation, attend a meeting
Personnel can send the first instruction to conference system by conference terminal, to refer to only when conference content is related to relevant content
Show that conference system starts the audio data in video data to meeting and carries out keyword search, and add label, so as to after the meeting
Relevant content is looked back.
Cooperate shown in Fig. 3, it is in some embodiments, described that keyword search is carried out to the audio data, comprising:
S201 identifies the corresponding text information of the audio data;
Whether S202 detects in the text information including the preset keyword in preset set of keywords.
In the specific implementation process, speech recognition technology can be used to identify audio data, to obtain the audio
The corresponding complete text information of data.The process can be completed using speech recognition modeling, speech recognition modeling can by pair
The model framework of foundation is trained to be formed, wherein the training process includes: preparation training dataset, the training data
Collection includes audio data set and corresponding text data set;Using the audio data set as input data, with the text
Data set is as the output data training model framework, to form the corresponding Characteristic Vectors of several units such as with word, phoneme
Amount, and characteristic vector is stored in database.Audio data is decomposed into speech recognition process several corresponding to word or phoneme
Characteristic vector in these audio sections and database is carried out similarity-rough set, to obtain corresponding text information by audio section.
Preset set of keywords can be the word set for including the preset keyword chosen in advance.Preset keyword can be according to required knowledge
The type of other target data, the industry, content etc. are chosen.For example, if fruit is special to computer major or machinery
The instructional video of industry adds keyword, then can choose preset keyword from computer technical terms or mechanical major vocabulary.
In a preferred embodiment, which may include at least one preset keyword sequences, the preset key
Word sequence may include the multiple preset keywords being arranged successively chosen from preset text.The preset text can be and number of targets
According to the corresponding text of content, such as can subject under discussion want, meeting PowerPoint (PPT) text, teaching material, syllabus, teaching
PPT text and drama etc..The chapter title in preset text, paragraph heading, content can be chosen after getting preset text to want
The contents such as point are arranged in preset keyword sequences according to content sequencing and are stored in preset keyword as preset keyword
It concentrates.It is then based on the preset set of keywords to identify the text information of acquisition, selected keyword can in this way
The main contents and sequencing of accurate characterization target data can then make added label more accurate.For example, obtaining
When getting the video data of teachers ' teaching, the PPT text of teaching is also obtained, preset set of keywords is formed based on the PPT text, so
Keyword search is carried out to the audio data in video data based on the preset set of keywords afterwards, then based on the keyword of acquisition
Generate the first label, and the first label be added in the image of target data, in this way, added first label then with PPT
The main contents of text and video data are corresponding.
Cooperate shown in Fig. 4, in some embodiments, at least one obtained according to preset condition in the audio data
A keyword, comprising:
S301 judges first keyword in the case where in detecting the audio data comprising the first keyword
The frequency of occurrences whether meet predeterminated frequency threshold value;
S302, if the frequency of occurrences of the first keyword meets predeterminated frequency threshold value, it is determined that first keyword is
Effective keyword, and obtain first keyword.
In the specific implementation process, when the partial content of target data is related to a certain plot, scene or teaching chapters and sections,
Audio data would generally repeat in special time period corresponding to the contents of the section and it is high-frequency there is relevant keyword,
Such keyword can be relatively accurate characterization the contents of the section.By the way that the frequency of occurrences is met the first of predeterminated frequency threshold value
Keyword is determined as effective keyword, can be improved the accuracy of the keyword got, and then improves and to generate and add
The accuracy of first label.For example, by taking computer teaching video as an example, it, may be because relating to when telling about central processing unit (CPU)
And data are transmitted or work in coordination and refer to GPU between CPU and graphics processor (GPU), but the actually partial video data
Relate generally to CPU.After getting two keywords of CPU and GPU, judge whether the frequency of occurrences of CPU and GPU meets default frequency
Rate threshold value is judged that the frequency of occurrences of CPU meets predeterminated frequency threshold value, and the frequency of occurrences of GPU does not meet predeterminated frequency threshold value,
It then determines that CPU is effective keyword, and obtains this keyword of CPU.
It is in some embodiments, described that corresponding first label is formed based on the keyword, comprising:
S303 obtains first first keyword detected in special time period and corresponding first time point,
Described in special time period be first keyword the frequency of occurrences meet the predeterminated frequency threshold value corresponding period.The
The time point that one time point can occur for the first time for the first keyword in special time period.For example, being regarded in one section of computer teaching
For frequency in 5 points of 30 seconds to 20 points 30 seconds this periods in, the frequency of occurrences of " CPU classification " meets predeterminated frequency threshold value,
And " CPU classification " occur for the first time be 5 points 30 seconds, it is determined that " CPU classification " be effective keyword, obtain " CPU classification " this
While a first keyword, " 5 points 30 seconds " this first time point is also obtained.
S304 forms corresponding first label based on first first keyword and the first time point.?
, can be using the first keyword as the theme of the first label or main contents after getting the first keyword and first time point, it can
Using first time point as the progression time point in target data of the first label.The example in step S303 is such as adopted, it can
Form the label of one entitled " CPU classification ", which can add in video data 5 points at 30 seconds.
Cooperate shown in Fig. 5, in some embodiments, at least one obtained according to preset condition in the audio data
A keyword forms corresponding first label based on the keyword, comprising:
S305 in the case where in detecting the audio data comprising the second keyword, is determined and is closed comprising described second
The start time point that the audio data section of key word plays, wherein the audio data section is the continuant of the same user of acquisition
Frequency evidence;
S306 forms corresponding first label based on second keyword and the start time point.
By the way that the time point of the first label to be determined as to the start time point of the speech of same user, it can be avoided and miss use
The speech content relevant to second keyword that family is told about, can make the addition of label more accurate.To include multiple meetings
For the tele-conferencing system of terminal, after getting the video data of meeting, it can be said based on speech intonation identification different user
Audio data is divided into multiple audio data sections by the audio of words, detects such as " CPU in a wherein audio data section
In the case where classification " keyword, the start time point of the audio data section comprising " CPU classification " keyword can be further determined that,
As 30 points 15 seconds, then produce one entitled " CPU classification " the first label, and by the label addition in video data
30 points at 15 seconds.
Fig. 6 is the structural block diagram of the information processing unit of the embodiment of the present application, shown in Figure 6, the embodiment of the present application
Information processing unit includes: to obtain module 10, detection module 20, form module 30 and adding module 40, in which:
Module 10 is obtained for obtaining target data.Wherein, the target data includes image data and audio data, such as
Video class data etc..The target data can be the data generated in real time, can also be the target data being stored in preset memory areas,
As stored target data in the database.In the specific implementation process, the process for obtaining target data can be for from for acquiring
Video class data is deployed into the process of target storage position in the video camera or calculator of video class data, can also be from target
Target data is extracted the process in built-in storage or register by storage location.
Detection module 20 is used to carry out keyword search to the audio data.Wherein, which is and image number
According to the audio to match, it can also be to obtain which, which can be the audio recorded while acquisition or production image data,
To after image data, the audio data of recording is matched.The keyword can be the keyword chosen in advance, close to audio data
Whether it includes the keyword chosen in advance that the detection of key word is in detection audio data.The keyword can also be for according to default detection
The keyword of Rule, carrying out keyword search to audio data is, and carries out according to default detected rule to audio data
It detects and obtains the word for meeting default examination criteria, word as keyword.Such as using the higher word of the frequency of occurrences as keyword.Inspection
The keyword measured can be one or more identical keywords, can also be multiple and different keywords.
It forms module 30 to be used to obtain at least one keyword in the audio data according to preset condition, based on described
Keyword forms corresponding first label.The possible quantity of the keyword obtained from a segment of audio data is more but and not all
Meet and adds tagged condition.For example, causing same words continuously to weigh because talker's sentence repeats when talking with or explaining and publicising
It appears again existing.Alternatively, although keyword does not repeat, the video content being also possible in the keyword and video data that occur obtaining
The problems such as mismatch.In the specific implementation process, the settable preset condition for being screened to keyword, and according to default
Condition screens keyword, to obtain the one or more keywords for meeting preset condition, is then based on keyword and is formed
Corresponding first label, such as using keyword as the title of the first label, or using keyword as label substance of label etc..
Adding module 40 is used for by first label addition in the image of the target data, to pass through described first
Label can carry out the first operation to the target data.After first label that completes, target data is added tags to
Image in corresponding position.First operation can be skip operation, search operaqtion or other operations.Such as in target data
In playing process, first label can be shown in the positions such as progress bar or tab bar, user can be by selecting first mark
Label or click directionkeys etc. adjust the playback progress of target data to the corresponding position of the first label.Label is completed in addition
Afterwards, target data can be uploaded to database, and form the first label with search term and be associated with, so that user is utilizing search term
The first label and corresponding target data can be retrieved when retrieval, to facilitate user to obtain the target data and from corresponding position
Play the target data.
Information processing unit in the embodiment of the present application carries out keyword search, energy to audio data based on speech recognition
Enough automatic acquisitions can characterize the keyword of target data content, and first is added in target data based on the keyword got
Label allows users to execute the first operation to target data using first label.Without artificially passing through viewing target data
Content carry out artificial definition of keywords, the keyword based on acquisition can add the first label automatically, be beneficial to improve label and add
Add efficiency, save cost of labor, label is added suitable for the video data to magnanimity, to improve user experience.
The specific structure of module 10 is obtained there are many form, in one embodiment, the acquisition module 10 includes: the
One acquiring unit, the first acquisition unit are generated for obtaining in the first electronic equipment and the second electronic equipment video call process
Target data;First electronic equipment and the second electronic equipment can there are many types, such as laptop, tablet computer, intelligence
The electronic equipments with video call function such as energy mobile phone.In this way, carrying out video in the first electronic equipment and the second electronic equipment
In communication process, can synchronous acquisition image data and audio data to form target data.Such as in long-distance video teaching process,
Can by the electronic equipment of teacher side acquire teaching process in image data and audio data to form target data, to target
After data add label, student can be shared with or shared to network for viewing, teacher's burden is can reduce, simplify instructional video
Manufacturing process.Also the video data in conference process can be acquired by conference system, then to view in such as teleconference
Frequency is according to progress keyword search and adds label, it will be able to fast, easily make TV news.In another embodiment
In, the acquisition module 10 can include: second acquisition unit, the second acquisition unit are used to obtain the target in preset memory areas
Data.The preset memory areas can be the specific memory section in the memory of electronic equipment, can also be the number of such as Video service quotient
According to the specific memory section in library.The target data can be the video counts of the type such as film, TV play, documentary film, short-sighted frequency
According to.By taking Teaching Service platform as an example, it can be placed in preset memory areas after teacher records completion video data, it later can be by being
The automatic video data obtained in preset memory areas of system simultaneously adds label, is uploaded to Foreground Data library, then for user's viewing.
In some embodiments, the detection module 20 can be while obtaining the target data to the audio data
Carry out keyword search;Keyword search can also be carried out to the audio data according to the first instruction, namely get first
Start to carry out keyword search to audio data in the case where instruction.It, can be in meeting in a kind of situation by taking tele-conferencing system as an example
The video data of synchronous acquisition one or more conference terminal carries out keyword search at the same time automatically during view carries out
And label is added, to add label to entire video data.In another middle situation, personnel participating in the meeting can only be related in conference content
When relevant content, the first instruction is sent to conference system by conference terminal, to indicate that conference system starts the view to meeting
Audio data of the frequency in carries out keyword search, and adds label, to look back after the meeting relevant content.
Cooperate shown in Fig. 7, in some embodiments, the detection module 20 includes: recognition unit 21 and detection unit
22, wherein the corresponding text information of the audio data for identification of recognition unit 21;Detection unit 22 is described for detecting
Whether including the preset keyword in preset set of keywords in text information.
In the specific implementation process, recognition unit 21 can be used speech recognition technology and identify to audio data, to obtain
Take the corresponding complete text information of the audio data.Recognition unit 21 can complete the process using speech recognition modeling,
Speech recognition modeling can be formed by being trained to the model framework of foundation, wherein the training process includes: to prepare training
Data set, the training dataset include audio data set and corresponding text data set;Using the audio data set as
Input data, the training model framework using the text data set as output data, to form several and word, phoneme etc.
The corresponding characteristic vector of unit, and characteristic vector is stored in database.If audio data is decomposed into speech recognition process
Characteristic vector in these audio sections and database is carried out similarity-rough set by the dry audio section for corresponding to word or phoneme, thus
Obtain corresponding text information.
Preset set of keywords can be the word set for including the preset keyword chosen in advance.Preset keyword can be according to required knowledge
The type of other target data, the industry, content etc. are chosen.For example, if fruit is special to computer major or machinery
The instructional video of industry adds keyword, then can choose preset keyword from computer technical terms or mechanical major vocabulary.
In a preferred embodiment, which may include at least one preset keyword sequences, the preset key
Word sequence may include the multiple preset keywords being arranged successively chosen from preset text.The preset text can be and number of targets
According to the corresponding text of content, such as can subject under discussion want, meeting PowerPoint (PPT) text, teaching material, syllabus, teaching
PPT text and drama etc..The chapter title in preset text, paragraph heading, content can be chosen after getting preset text to want
The contents such as point are arranged in preset keyword sequences according to content sequencing and are stored in preset keyword as preset keyword
It concentrates.It is then based on the preset set of keywords to identify the text information of acquisition, selected keyword can in this way
The main contents and sequencing of accurate characterization target data can then make added label more accurate.For example, obtaining
When getting the video data of teachers ' teaching, the PPT text of teaching is also obtained, preset set of keywords is formed based on the PPT text, so
Keyword search is carried out to the audio data in video data based on the preset set of keywords afterwards, then based on the keyword of acquisition
Generate the first label, and the first label be added in the image of target data, in this way, added first label then with PPT
The main contents of text and video data are corresponding.
Cooperate shown in Fig. 8, in some embodiments, the formation module 30 includes: that judging unit 31 and third obtain list
Member 32 judges described first in the case that judging unit 31 is used in detecting the audio data comprising the first keyword
Whether the frequency of occurrences of keyword meets predeterminated frequency threshold value;Third acquiring unit 32 is used for the appearance in first keyword
In the case that frequency meets the predeterminated frequency threshold value, determine that first keyword is effective keyword, and obtain described the
One keyword.
In the specific implementation process, when the partial content of target data is related to a certain plot, scene or teaching chapters and sections,
Audio data would generally repeat in special time period corresponding to the contents of the section and it is high-frequency there is relevant keyword,
Such keyword can be relatively accurate characterization the contents of the section.By the way that the frequency of occurrences is met the first of predeterminated frequency threshold value
Keyword is determined as effective keyword, can be improved the accuracy of the keyword got, and then improves and to generate and add
The accuracy of first label.For example, by taking computer teaching video as an example, it, may be because relating to when telling about central processing unit (CPU)
And data are transmitted or work in coordination and refer to GPU between CPU and graphics processor (GPU), but the actually partial video data
Relate generally to CPU.After getting two keywords of CPU and GPU, judge whether the frequency of occurrences of CPU and GPU meets default frequency
Rate threshold value is judged that the frequency of occurrences of CPU meets predeterminated frequency threshold value, and the frequency of occurrences of GPU does not meet predeterminated frequency threshold value,
It then determines that CPU is effective keyword, and obtains this keyword of CPU.
In some embodiments, the formation module 30 further include: the 4th acquiring unit 33 and first forms unit 34.The
Four acquiring units 33 are used to obtain first first keyword detected in special time period and corresponding first time point,
Wherein the special time period is that the frequency of occurrences of first keyword meets the predeterminated frequency threshold value corresponding period;
First formation unit 34 is used to be formed corresponding first mark based on first first keyword and the first time point
Label.The time point that first time point can occur for the first time for the first keyword in special time period.Getting the first keyword
After first time point, can using the first keyword as the theme of the first label or main contents, can using first time point as
The progression time point in target data of first label.For example, in one section of computer teaching video data 5 points 30 seconds extremely
In 20 points of 30 seconds this periods, the frequency of occurrences of " CPU classification " meets predeterminated frequency threshold value, and " CPU classification " goes out for the first time
Be now 5 points 30 seconds, it is determined that " CPU classification " be effective keyword, obtain " CPU classification " this first keyword while,
Also " 5 points 30 seconds " this first time point is obtained.Later, the label of one entitled " CPU classification " can be formed, which can add
5 points are added in video data at 30 seconds.
Cooperate shown in Fig. 9, in some embodiments, the formation module 30 comprises determining that unit 35 and second forms list
Member 36 determines in the case that determination unit 35 is used in detecting the audio data comprising the second keyword comprising described
The start time point that the audio data section of second keyword plays, wherein the audio data section is the same user of acquisition
Continuous audio data;Second formation unit 36 is used to form corresponding institute based on second keyword and the start time point
State the first label.By the way that the time point of the first label to be determined as to the start time point of the speech of same user, mistake can be avoided
The speech content relevant to second keyword that user tells about is crossed, the addition of label can be made more accurate.To include multiple
For the tele-conferencing system of conference terminal, after getting the video data of meeting, different use can be identified based on speech intonation
The audio of family speech, is divided into multiple audio data sections for audio data, detects for example in a wherein audio data section
In the case where " CPU classification " keyword, the initial time of the audio data section comprising " CPU classification " keyword can be further determined that
Point, such as 30 points 15 seconds, then produce one entitled " CPU classification " the first label, and by the label addition in video counts
According to 30 points at 15 seconds.
The embodiment of the present application also provides a kind of storage mediums, are stored with computer program, when a computer program is executed
The method for realizing that the application any embodiment provides illustratively includes the following steps:
S100 obtains target data, wherein the target data includes image data and audio data;
S200 carries out keyword search to the audio data;
S300 obtains at least one keyword in the audio data according to preset condition, based on the crucial font
At corresponding first label;
S400 can to pass through first label by first label addition in the image of the target data
First operation is carried out to the target data.
When at least one the keyword step obtained according to preset condition in the audio data for executing computer program
When, specifically it is executed by processor following steps: in the case where in detecting the audio data comprising the first keyword, judgement
Whether the frequency of occurrences of first keyword meets predeterminated frequency threshold value;If it is, determining that first keyword is to have
Keyword is imitated, and obtains first keyword.
When executing when forming corresponding first labelling step based on the keyword of computer program, specifically by processor
It executes following steps: obtaining first first keyword detected in special time period and corresponding first time point,
Described in special time period be first keyword the frequency of occurrences meet the predeterminated frequency threshold value corresponding period;Base
Corresponding first label is formed in first first keyword and the first time point.
When at least one keyword obtained according to preset condition in the audio data for executing computer program, it is based on
When the keyword forms corresponding first labelling step, it is specifically executed by processor following steps: detecting the audio
Comprising in the case where the second keyword, determining the initial time that the audio data section comprising second keyword plays in data
Point, wherein the audio data section is the continuous audio data of the same user of acquisition;Based on second keyword and described
Start time point forms corresponding first label.
When executing when carrying out keyword search step to the audio data of computer program, specifically it is executed by processor
Following steps: the corresponding text information of the audio data is identified;Whether detect in the text information includes preset key
The preset keyword that word is concentrated.
When executing the acquisition target data step of computer program, it is specifically executed by processor following steps: obtaining the
The target data generated in one electronic equipment and the second electronic equipment video call process;Or the target in acquisition preset memory areas
Data.
When executing when carrying out keyword search step to the audio data of computer program, specifically it is executed by processor
Following steps: keyword search is carried out to the audio data while obtaining the target data;Or according to the first instruction
Keyword search is carried out to the audio data.
Above-mentioned storage medium can be set in the electronic equipment for including at least memory, processor, with the shape of memory
Formula exists, and details are not described herein again for specific implementation.
The embodiment of the present application also provides a kind of electronic equipment, shown in Figure 10, which includes at least storage
Device 901 and processor 902, executable program is stored on memory 901, and processor 902 is executing holding on memory 901
The method that the application any embodiment provides is realized when line program, illustratively, steps are as follows for executable program:
S100 obtains target data, wherein the target data includes image data and audio data;
S200 carries out keyword search to the audio data;
S300 obtains at least one keyword in the audio data according to preset condition, based on the crucial font
At corresponding first label;
S400 can to pass through first label by first label addition in the image of the target data
First operation is carried out to the target data.
What processor 902 stored on executing memory 901 obtains in the audio data at least according to preset condition
When the executable program of one keyword, it is implemented as follows step: crucial comprising first in detecting the audio data
In the case where word, judge whether the frequency of occurrences of first keyword meets predeterminated frequency threshold value;If it is, described in determining
First keyword is effective keyword, and obtains first keyword.
Processor 902 stored on executing memory 901 based on the keyword form corresponding first label can
When executing program, it is implemented as follows step: obtaining first first keyword detected in special time period and correspondence
First time point, wherein the special time period be first keyword the frequency of occurrences meet the predeterminated frequency threshold value
The corresponding period;Corresponding first label is formed based on first first keyword and the first time point.
What processor 902 stored on executing memory 901 obtains in the audio data at least according to preset condition
One keyword is implemented as follows step when forming the executable program of corresponding first label based on the keyword:
It detects in the audio data comprising determining the audio data section comprising second keyword in the case where the second keyword
The start time point of broadcasting, wherein the audio data section is the continuous audio data of the same user of acquisition;Based on described
Two keywords and the start time point form corresponding first label.
What processor 902 stored on executing memory 901, which carries out keyword search to the audio data, can be performed
When program, it is implemented as follows step: identifying the corresponding text information of the audio data;Detecting in the text information is
The no preset keyword including in preset set of keywords.
For processor 902 in the executable program of the acquisition target data stored on executing memory 901, specific implementation is such as
Lower step: the target data generated in the first electronic equipment and the second electronic equipment video call process is obtained;Or it obtains preset
Target data in memory block.
What processor 902 stored on executing memory 901, which carries out keyword search to the audio data, can be performed
When program, it is implemented as follows step: keyword search being carried out to the audio data while obtaining the target data;
Or keyword search is carried out to the audio data according to the first instruction.
Above embodiments are only the exemplary embodiment of the application, are not used in limitation the application, the protection scope of the application
It is defined by the claims.Those skilled in the art can make respectively the application in the essence and protection scope of the application
Kind modification or equivalent replacement, this modification or equivalent replacement also should be regarded as falling within the scope of protection of this application.
Claims (10)
1. a kind of information processing method, comprising:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, forms corresponding based on the keyword
One label;
By first label addition in the image of the target data, with can be to the target by first label
Data carry out the first operation.
2. information processing method according to claim 1, wherein described to be obtained in the audio data according to preset condition
At least one keyword, comprising:
In the case where including the first keyword in detecting the audio data, the frequency of occurrences of first keyword is judged
Whether predeterminated frequency threshold value is met;
If it is, determining that first keyword is effective keyword, and obtain first keyword.
3. information processing method according to claim 2, wherein described to form corresponding first mark based on the keyword
Label, comprising:
First first keyword detected in special time period and corresponding first time point are obtained, wherein described specific
Period is that the frequency of occurrences of first keyword meets the predeterminated frequency threshold value corresponding period;
Corresponding first label is formed based on first first keyword and the first time point.
4. information processing method according to claim 1, wherein described to be obtained in the audio data according to preset condition
At least one keyword, corresponding first label is formed based on the keyword, comprising:
In the case where including the second keyword in detecting the audio data, the audio comprising second keyword is determined
The start time point that data segment plays, wherein the audio data section is the continuous audio data of the same user of acquisition;
Corresponding first label is formed based on second keyword and the start time point.
5. information processing method according to claim 1, wherein it is described that keyword search is carried out to the audio data,
Include:
Identify the corresponding text information of the audio data;
It whether detects in the text information including the preset keyword in preset set of keywords.
6. information processing method according to claim 1, wherein the acquisition target data includes:
Obtain the target data generated in the first electronic equipment and the second electronic equipment video call process;Or
Obtain the target data in preset memory areas.
7. information processing method according to claim 1, wherein described to carry out keyword search packet to the audio data
It includes:
Keyword search is carried out to the audio data while obtaining the target data;Or
Keyword search is carried out to the audio data according to the first instruction.
8. a kind of information processing unit, comprising:
Module is obtained, for obtaining target data, wherein the target data includes image data and audio data;
Detection module, for carrying out keyword search to the audio data;
Module is obtained, for obtaining at least one keyword in the audio data according to preset condition, is based on the key
Word forms corresponding first label;
Adding module, for adding first label in the image of the target data, to pass through first label
The first operation can be carried out to the target data.
9. a kind of storage medium is stored with computer program, realizes following steps when loaded and executed:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, forms corresponding based on the keyword
One label;
By first label addition in the image of the target data, with can be to the target by first label
Data carry out the first operation.
10. a kind of electronic equipment includes at least memory and processor, is stored with executable program on the memory, described
Processor realizes following steps when executing the executable program on the memory:
Obtain target data, wherein the target data includes image data and audio data;
Keyword search is carried out to the audio data;
At least one keyword in the audio data is obtained according to preset condition, forms corresponding based on the keyword
One label;
By first label addition in the image of the target data, with can be to the target by first label
Data carry out the first operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910606313.4A CN110347866B (en) | 2019-07-05 | 2019-07-05 | Information processing method, information processing device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910606313.4A CN110347866B (en) | 2019-07-05 | 2019-07-05 | Information processing method, information processing device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110347866A true CN110347866A (en) | 2019-10-18 |
CN110347866B CN110347866B (en) | 2023-06-23 |
Family
ID=68177929
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910606313.4A Active CN110347866B (en) | 2019-07-05 | 2019-07-05 | Information processing method, information processing device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110347866B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111212317A (en) * | 2020-01-15 | 2020-05-29 | 清华大学 | Skip navigation method for video playing |
CN111640453A (en) * | 2020-05-13 | 2020-09-08 | 广州国音智能科技有限公司 | Speech spectrum matching method, device and equipment and computer readable storage medium |
CN111723816A (en) * | 2020-06-28 | 2020-09-29 | 北京联想软件有限公司 | Teaching note acquisition method and electronic equipment |
CN112115301A (en) * | 2020-08-31 | 2020-12-22 | 湖北美和易思教育科技有限公司 | Video annotation method and system based on classroom notes |
CN114449333A (en) * | 2020-10-30 | 2022-05-06 | 华为终端有限公司 | Video note generation method and electronic equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005352782A (en) * | 2004-06-10 | 2005-12-22 | Canon Inc | Device and method for image retrieval |
CN1977264A (en) * | 2004-06-28 | 2007-06-06 | 松下电器产业株式会社 | Video/audio stream processing device and video/audio stream processing method |
US20070288237A1 (en) * | 2006-06-07 | 2007-12-13 | Chung-Hsien Wu | Method And Apparatus For Multimedia Data Management |
US20100179972A1 (en) * | 2009-01-09 | 2010-07-15 | Yasuharu Asano | Data processing apparatus, data processing method, and program |
CN104391960A (en) * | 2014-11-28 | 2015-03-04 | 北京奇艺世纪科技有限公司 | Video annotation method and system |
CN105824930A (en) * | 2016-03-17 | 2016-08-03 | 深圳市金立通信设备有限公司 | Voice message processing method and terminal |
US20170221523A1 (en) * | 2012-04-24 | 2017-08-03 | Liveclips Llc | Annotating media content for automatic content understanding |
CN107679227A (en) * | 2017-10-23 | 2018-02-09 | 柴建华 | Video index label setting method, device and server |
CN108763366A (en) * | 2018-05-17 | 2018-11-06 | 惠州学院 | The grasping means of video image emphasis picture, device, storage medium and electronic equipment |
CN109561339A (en) * | 2017-09-27 | 2019-04-02 | 北京国双科技有限公司 | The treating method and apparatus of video file |
-
2019
- 2019-07-05 CN CN201910606313.4A patent/CN110347866B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005352782A (en) * | 2004-06-10 | 2005-12-22 | Canon Inc | Device and method for image retrieval |
CN1977264A (en) * | 2004-06-28 | 2007-06-06 | 松下电器产业株式会社 | Video/audio stream processing device and video/audio stream processing method |
US20070288237A1 (en) * | 2006-06-07 | 2007-12-13 | Chung-Hsien Wu | Method And Apparatus For Multimedia Data Management |
US20100179972A1 (en) * | 2009-01-09 | 2010-07-15 | Yasuharu Asano | Data processing apparatus, data processing method, and program |
US20170221523A1 (en) * | 2012-04-24 | 2017-08-03 | Liveclips Llc | Annotating media content for automatic content understanding |
CN104391960A (en) * | 2014-11-28 | 2015-03-04 | 北京奇艺世纪科技有限公司 | Video annotation method and system |
CN105824930A (en) * | 2016-03-17 | 2016-08-03 | 深圳市金立通信设备有限公司 | Voice message processing method and terminal |
CN109561339A (en) * | 2017-09-27 | 2019-04-02 | 北京国双科技有限公司 | The treating method and apparatus of video file |
CN107679227A (en) * | 2017-10-23 | 2018-02-09 | 柴建华 | Video index label setting method, device and server |
CN108763366A (en) * | 2018-05-17 | 2018-11-06 | 惠州学院 | The grasping means of video image emphasis picture, device, storage medium and electronic equipment |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111212317A (en) * | 2020-01-15 | 2020-05-29 | 清华大学 | Skip navigation method for video playing |
CN111640453A (en) * | 2020-05-13 | 2020-09-08 | 广州国音智能科技有限公司 | Speech spectrum matching method, device and equipment and computer readable storage medium |
CN111723816A (en) * | 2020-06-28 | 2020-09-29 | 北京联想软件有限公司 | Teaching note acquisition method and electronic equipment |
CN111723816B (en) * | 2020-06-28 | 2023-10-27 | 北京联想软件有限公司 | Acquisition method of teaching notes and electronic equipment |
CN112115301A (en) * | 2020-08-31 | 2020-12-22 | 湖北美和易思教育科技有限公司 | Video annotation method and system based on classroom notes |
CN112115301B (en) * | 2020-08-31 | 2023-09-19 | 武汉美和易思数字科技有限公司 | Video annotation method and system based on classroom notes |
CN114449333A (en) * | 2020-10-30 | 2022-05-06 | 华为终端有限公司 | Video note generation method and electronic equipment |
CN114449333B (en) * | 2020-10-30 | 2023-09-01 | 华为终端有限公司 | Video note generation method and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110347866B (en) | 2023-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110347866A (en) | Information processing method, device, storage medium and electronic equipment | |
CN109801193B (en) | Follow-up teaching system with voice evaluation function | |
CN109359215B (en) | Video intelligent pushing method and system | |
CN110991645B (en) | Self-adaptive learning method, system and storage medium based on knowledge model | |
CN106021496A (en) | Video search method and video search device | |
CN110516791B (en) | Visual question-answering method and system based on multiple attention | |
US20050114357A1 (en) | Collaborative media indexing system and method | |
CN110148400A (en) | The pronunciation recognition methods of type, the training method of model, device and equipment | |
CN111695422B (en) | Video tag acquisition method and device, storage medium and server | |
CN106355429A (en) | Image material recommendation method and device | |
CN110162599A (en) | Personnel recruitment and interview method, apparatus and computer readable storage medium | |
CN111563158B (en) | Text ranking method, ranking apparatus, server and computer-readable storage medium | |
CN108491463A (en) | Label determines method and device | |
CN113395578A (en) | Method, device and equipment for extracting video theme text and storage medium | |
CN107408238A (en) | From voice data and computer operation context automatic capture information | |
CN114501064B (en) | Video generation method, device, equipment, medium and product | |
CN111538852B (en) | Multimedia resource processing method, device, storage medium and equipment | |
CN111681678B (en) | Method, system, device and storage medium for automatically generating sound effects and matching videos | |
CN111026786B (en) | Dictation list generation method and home education equipment | |
CN112528049B (en) | Video synthesis method, device, electronic equipment and computer readable storage medium | |
CN114493944A (en) | Method, device and equipment for determining learning path and storage medium | |
CN113992973A (en) | Video abstract generation method and device, electronic equipment and storage medium | |
CN113052025A (en) | Training method of image fusion model, image fusion method and electronic equipment | |
CN116487012A (en) | Intelligent practice teaching method, system, medium and equipment for clinical medical staff | |
CN111859970B (en) | Method, apparatus, device and medium for processing information |
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 |