CN109996026B - Video special effect interaction method, device, equipment and medium based on wearable equipment - Google Patents
Video special effect interaction method, device, equipment and medium based on wearable equipment Download PDFInfo
- Publication number
- CN109996026B CN109996026B CN201910327776.7A CN201910327776A CN109996026B CN 109996026 B CN109996026 B CN 109996026B CN 201910327776 A CN201910327776 A CN 201910327776A CN 109996026 B CN109996026 B CN 109996026B
- Authority
- CN
- China
- Prior art keywords
- special effect
- keyword
- preset
- loading
- video call
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
Abstract
The invention is suitable for the technical field of intelligent wearing, and provides a video special effect interaction method, a device, equipment and a medium based on wearable equipment, wherein the method comprises the following steps: when the fact that the wearable device and a terminal carry out video call is detected, voice of the video call is obtained, semantic recognition is carried out on the obtained voice to obtain a keyword in the voice, the obtained keyword is matched with a preset special effect name to obtain matching similarity, when the matching similarity is larger than a preset similarity threshold value, a special effect corresponding to the keyword is obtained, the obtained special effect is loaded into the video call according to preset loading conditions and preset loading parameters, therefore, the operation complexity of the user using the special effect in the video call process is reduced, interaction obstacle of the user using the special effect is reduced, and user experience is improved.
Description
Technical Field
The invention belongs to the technical field of intelligent wearing, and particularly relates to a video special effect interaction method, device, equipment and medium based on wearable equipment.
Background
With the development of intelligent wearing technology, a user can carry out video conversation through a video call function of wearable equipment at present, in order to increase the interestingness of video call, a manufacturer of the wearable equipment presets an interactive special effect in wearable setting so that the user can interact in the video call, when the user of the wearable equipment sends a loading special effect request in the video call, the wearable equipment presents the preset interactive special effect on a video call interface, and the user selects through the special effect presented in the video call interface.
However, due to the limitation of the size of the screen of the wearable device, the presented special effect options can block the video call interface, and meanwhile, when the preset special effect options of the wearable device are more, the manual selection of the special effect not only increases the operation complexity of the user, but also enables the attention of the user to be transferred to the operation flow from the video call, so that interaction obstacles are generated, and further the user experience is reduced.
Disclosure of Invention
The invention aims to provide a video special effect interaction method, a device, equipment and a medium based on wearable equipment, and aims to solve the problem that in the prior art, the complexity of interactive special effect operation used by a user of the wearable equipment in a video call process is high.
In one aspect, the present invention provides a video special effect interaction method based on wearable equipment, including the following steps:
when the fact that the wearable device carries out video call with a terminal is detected, obtaining voice of the video call;
performing semantic recognition on the acquired voice to acquire key words in the voice;
matching the acquired keywords with a preset special effect name to obtain matching similarity;
when the matching similarity is larger than a preset similarity threshold, obtaining a special effect corresponding to the keyword;
and loading the obtained special effect into the video call according to a preset loading condition and a preset loading parameter.
Preferably, before the step of obtaining the special effect corresponding to the keyword, the method includes:
acquiring scene parameters of the video call;
and acquiring a special effect corresponding to the keyword according to the scene parameters.
Preferably, after the step of matching the obtained keyword with a preset special effect name to obtain matching similarity, the method includes:
when the matching similarity is equal to 100%, obtaining a special effect corresponding to the keyword;
and loading the obtained special effect into the video call according to a preset loading parameter.
Preferably, after the step of obtaining the special effect corresponding to the keyword, the method includes:
displaying the obtained special effect in an alternative area of a video call interface;
and when a special effect loading request input by a wearable device user through the alternative area is received, loading the obtained special effect into the video call according to preset loading parameters.
Preferably, after the step of obtaining the special effect corresponding to the keyword, the method further includes:
acquiring an image frame of the video call, performing image recognition on the acquired image frame, and calculating a loading parameter of the acquired special effect in the image frame;
and loading the obtained special effect into the video call according to a preset loading condition and the calculated loading parameter.
In another aspect, the present invention provides a video special effect interaction apparatus based on wearable devices, where the apparatus includes:
the voice acquisition unit is used for acquiring voice of the video call when the wearable device is detected to carry out the video call with the terminal;
the semantic recognition unit is used for performing semantic recognition on the acquired voice to acquire keywords in the voice;
the similarity calculation unit is used for matching the acquired keywords with a preset special effect name to obtain matching similarity;
a special effect obtaining unit, configured to obtain a special effect corresponding to the keyword when the matching similarity is greater than a preset similarity threshold; and
and the special effect loading unit is used for loading the obtained special effect into the video call according to a preset loading condition and a preset loading parameter.
Preferably, the apparatus further comprises:
the special effect display unit is used for displaying the obtained special effect in an alternative area of a video call interface; and
and the first special effect loading unit is used for loading the obtained special effect into the video call according to preset loading parameters when a special effect loading request input by a wearable device user through the standby area is received.
Preferably, the apparatus further comprises:
the parameter calculation unit is used for acquiring image frames of the video call, performing image recognition on the acquired image frames, and calculating loading parameters of the acquired special effects in the image frames; and
and the second special effect loading unit is used for loading the obtained special effect into the video call according to a preset loading condition and the calculated loading parameter.
In another aspect, the present invention also provides a wearable device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method when executing the computer program.
In another aspect, the present invention also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above.
When the wearable device and the terminal are detected to carry out video call, voice of the video call is obtained, semantic recognition is carried out on the obtained voice to obtain a keyword in the voice, the obtained keyword is matched with a preset special effect name to obtain matching similarity, when the matching similarity is larger than a preset similarity threshold value, a special effect corresponding to the keyword is obtained, and the obtained special effect is loaded into the video call according to preset loading conditions and preset loading parameters, so that the operation complexity of the user for using the special effect in the video call process is reduced, the interaction obstacle of the user for using the special effect is reduced, and the user experience is further improved.
Drawings
Fig. 1 is a flowchart illustrating an implementation of a video special effect interaction method based on a wearable device according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of a video special effect interaction method based on a wearable device according to a second embodiment of the present invention;
fig. 3 is a flowchart of an implementation of a video special effect interaction method based on wearable equipment according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video special effect interaction apparatus based on wearable devices according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a video special effect interaction apparatus based on wearable devices according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a video special effect interaction apparatus based on wearable devices according to a sixth embodiment of the present invention; and
fig. 7 is a schematic structural diagram of a wearable device according to a seventh embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific implementations of the present invention is provided in conjunction with specific embodiments:
the first embodiment is as follows:
fig. 1 shows an implementation flow of a video special effect interaction method based on a wearable device according to an embodiment of the present invention, and for convenience of description, only parts related to the embodiment of the present invention are shown, which are detailed as follows:
in step S101, when it is detected that the wearable device is in a video call with the terminal, a voice of the video call is acquired.
The embodiment of the invention is suitable for wearable equipment which has a video call function, and particularly can acquire the voice of a user of the wearable equipment and the voice of a terminal user when acquiring the voice of the video call so as to perform deep analysis on the voice of the video call subsequently.
In step S102, semantic recognition is performed on the acquired speech to acquire keywords in the speech.
In the embodiment of the present invention, when performing semantic recognition on the obtained speech, the user identity of the speech may not be distinguished, specifically, the obtained speech may be segmented to obtain a plurality of speech segments, each speech segment is converted into a text, the text is subjected to semantic analysis to generate an analysis result, the analysis result includes keywords of the speech segment, the obtained keywords may be one or more, after performing semantic recognition on the obtained speech to obtain the keywords in the speech, preferably, the obtained keywords are classified into classes, the keyword classes include a first keyword and a second keyword, so as to facilitate subsequent quick confirmation of corresponding special effects according to the keyword classes, and improve the confirmation efficiency of the special effects, of course, three or more classes are allocated to the obtained keywords, and is not limited herein.
As an example, if the text content corresponding to the obtained video call voice segment includes: "you are happy holiday after the year! "the obtained keywords of the voice include a first keyword" happy holiday "and a second keyword" new year "and" spring festival ".
When performing semantic recognition on the acquired voice, the user identities of the voices can also be distinguished, and then the voice of one of the two parties of the call is used as the basic voice of the semantic recognition, and the voice of the other party is used as the auxiliary voice of the semantic recognition, for example, the voice of the wearable device user is used as the basic voice of the semantic recognition, and the voice of the terminal user is used as the voice of the auxiliary semantic recognition. Specifically, before performing semantic recognition on the obtained voice, a voice recognition model of a wearable device user may be established first, the obtained voice is matched with the established voice recognition model to determine the user identity of the voice in the obtained video call, then according to the semantic recognition method, semantic recognition is performed on the obtained user voices of both parties of the call respectively, the basic voice may be subjected to semantic recognition first to obtain a first keyword, then semantic recognition is performed on the auxiliary voice to obtain a second keyword, and the first keyword and the second keyword are final keywords.
In step S103, the obtained keyword is matched with a preset special effect name, so as to obtain a matching similarity.
In the embodiment of the invention, a special effect library is established in the wearable device, the preset special effects are stored in the special effect library, each specific special effect corresponds to a specific special effect name, all the special effect names can be independently stored in the special effect name library, then the obtained keywords are matched with the names in the special effect name library one by one, and the specific matching similarity is obtained.
Before matching the acquired keyword with a preset special effect name, the special effects can be classified, e.g., holiday blessing class, call class, cartoon class, etc., based on the keyword assigned level obtained in step S102, when the obtained keyword is matched with the preset special effect name, preferably, the obtained first keyword is matched with the preset special effect name to obtain a second matching similarity, and when the second matching similarity is greater than a preset second similarity threshold, obtaining the classification to which the special effect name corresponding to the first keyword belongs, matching the obtained second keyword with the special effect name under the classification based on the first keyword to obtain a first matching similarity, and taking the first matching similarity as the final matching similarity, thereby improving the calculation accuracy of the matching similarity.
As an example, the obtained keywords are a first keyword "happy holiday" and a second keyword "new year" and "spring festival", the preset special effects "happy holiday" and "happy new year" belong to a class of holiday blessing, the first-level similarity threshold is 50%, the first keyword is firstly matched with the special effect name to obtain second matching similarities of 100% and 80%, and further, based on the first keyword, the second keyword "new year" and "spring festival" are matched with the classified special effect names "happy holiday" and "happy new year" to obtain matching similarities of 90% and 100%.
It should be noted that the preset special effect names may be set in a unified manner when the wearable device leaves a factory, or may be downloaded by a user through an official website update or other ways of the wearable device as needed, which is not limited herein, and the special effect name corresponding to each special effect may be a default of the system, and preferably, the special effect name supports the user to modify according to the use habit, so that the actual interaction requirement of the user on the special effect in the actual call process is met, and the user experience is improved.
In step S104, when the matching similarity is greater than a preset similarity threshold, a special effect corresponding to the keyword is obtained.
In an embodiment of the present invention, the preset similarity threshold may be a specific value, for example, 80%, after the matching similarity is obtained, the obtained matching similarity is compared with the preset similarity threshold, when the matching similarity is greater than the preset similarity threshold, a special effect name corresponding to the keyword when the similarity is compared is obtained, and a special effect corresponding to the special effect name is used as one or more special effects corresponding to the keyword, where the special effect may include one or more of an animation special effect, a sticker special effect, and a text special effect, and of course, the special effect may also include other special effects, which is not limited herein.
Before obtaining the special effect corresponding to the keyword, preferably, a scene parameter of the video call is obtained, and the special effect corresponding to the keyword is obtained according to the scene parameter, so as to improve accuracy of obtaining the special effect corresponding to the keyword. Specifically, the scene parameters may include time parameters (e.g., current date, time, holidays, etc.) of the video call, weather parameters (e.g., sunny/rainy/snowy, temperature, wind direction and wind speed, etc.), one or more parameters of user emotion (e.g., hurt, excitement, etc.) of the video call, user gender, user geographical location, etc., of course, other parameters may also be included, such as user age, special effect usage habits of the user, etc., which are not limited herein.
Illustratively, the animation special effect corresponding to the keyword "good cold" includes wind blowing, rain blowing and snow blowing, the corresponding sticker special effect includes a quilt, and if the acquired keyword is "good cold" and the acquired weather parameter includes snow blowing, the corresponding special effect is acquired as a quilt and snow blowing according to the weather parameter and the keyword.
For another example, the special effects corresponding to the keyword "happy holiday" include happy spring festival and happy morning festival, and if the acquired keyword is "happy holiday", and the acquired time parameter includes happy morning festival, the corresponding special effect is happy afternoon festival obtained according to the time parameter and the keyword.
In step S105, the obtained special effect is loaded into the video call according to a preset loading condition and a preset loading parameter.
In the embodiment of the present invention, before the obtained special effect is loaded into the video call according to the preset loading condition and the preset loading parameter, the user may set the loading condition, where the loading condition may be that the special effect is automatically loaded into the video call when the loading condition of the preset target is met, or may also be a loading request input by the user.
When the loading condition is that the special effect is automatically loaded into the video call when the preset target is met, specifically, the preset target may be that the obtained special effects corresponding to the keyword meet a preset number (for example, less than or equal to three), or that the obtained special effects corresponding to the keyword meet a preset number of special effects (for example, one with the highest priority) after being subjected to priority ranking according to the matching similarity, or that the matching similarity corresponding to the obtained special effects meets a preset similarity range (for example, greater than or equal to 90%), or of course, a combination of two or more of the above conditions may be used, which is not limited herein. Preferably, when the matching similarity is equal to 100%, a special effect corresponding to the keyword is obtained, and the obtained special effect is loaded into the video call according to a preset loading parameter.
When the obtained special effect is loaded into the video call according to the preset loading condition and the preset loading parameter, the preset loading parameter may include one or more parameters such as a preset loading position, a preset loading duration, a preset loading size, and the like, and each special effect may correspond to a different loading parameter.
After the obtained special effect is loaded into the video call according to the preset loading condition and the preset loading parameter, the loaded special effect is preferably added into a common special effect library so as to facilitate the user to quickly select the special effect according to the use habit in the following process.
In the embodiment of the invention, when the fact that the wearable device and the terminal carry out video call is detected, voice of the video call is obtained, semantic recognition is carried out on the obtained voice to obtain a keyword in the voice, the obtained keyword is matched with a preset special effect name to obtain matching similarity, when the matching similarity is larger than a preset similarity threshold value, a special effect corresponding to the keyword is obtained, and the obtained special effect is loaded into the video call according to a preset loading condition and a preset loading parameter, so that the operation complexity of the user for using the special effect in the video call process is reduced, the interaction obstacle of the user for using the special effect is reduced, and the user experience is further improved.
Example two:
fig. 2 shows an implementation flow of a video special effect interaction method based on a wearable device according to a second embodiment of the present invention, and for convenience of description, only the relevant portions related to the second embodiment of the present invention are shown, which are detailed as follows:
in step S201, when it is detected that the wearable device performs a video call with the terminal, a voice of the video call is acquired.
In step S202, semantic recognition is performed on the acquired speech to acquire keywords in the speech.
In step S203, the obtained keyword is matched with a preset special effect name, so as to obtain a matching similarity.
In step S204, when the matching similarity is greater than a preset similarity threshold, a special effect corresponding to the keyword is obtained.
In the embodiment of the present invention, the implementation of steps S201 to S204 may refer to the description of steps S101 to S104 in the foregoing embodiment one, and will not be described herein again.
In step S205, the acquired special effect is displayed in the candidate area of the video call interface.
In the embodiment of the invention, when the obtained special effects are displayed in the alternative area of the video call interface, when a plurality of obtained special effects are available, the obtained special effects can be subjected to priority sequencing according to the matching similarity, and then the obtained special effects are displayed in the alternative area of the video call interface according to the priority sequencing result, so that a user can conveniently and quickly select the special effects. When the obtained special effects are subjected to priority sequencing, whether the obtained special effects exist in a common special effect library or not can be judged, and the obtained special effects are subjected to priority sequencing according to the judgment result and the matching similarity, so that the accuracy of priority sequencing is further improved.
In step S206, when a special effect loading request input by the wearable device user through the candidate area is received, the obtained special effect is loaded into the video call according to a preset loading parameter.
In this embodiment of the present invention, when the preset loading parameter loads the obtained special effect into the video call, the preset loading parameter may include parameters such as a preset loading position, a preset loading time, and a preset loading size, which are not limited herein.
After the obtained special effect is loaded into the video call according to the preset loading condition and the preset loading parameter, the loaded special effect is preferably added into a common special effect library so as to facilitate the user to quickly select the special effect according to the use habit in the following process.
In the embodiment of the invention, the obtained special effect is displayed in the alternative area of the video call interface, and when a special effect loading request input by a wearable device user through the alternative area is received, the obtained special effect is loaded into the video call according to the preset loading parameters, so that the accuracy of loading the special effect into the video call is improved, and the user experience is further improved.
Example three:
fig. 3 shows an implementation flow of a video special effect interaction method based on a wearable device according to a third embodiment of the present invention, and for convenience of description, only the relevant portions related to the third embodiment of the present invention are shown, which is detailed as follows:
in step S301, when it is detected that the wearable device is in a video call with the terminal, a voice of the video call is acquired.
In step S302, semantic recognition is performed on the acquired speech to acquire keywords in the speech.
In step S303, the obtained keyword is matched with a preset special effect name, so as to obtain a matching similarity.
In step S304, when the matching similarity is greater than a preset similarity threshold, a special effect corresponding to the keyword is obtained.
In the embodiment of the present invention, the implementation of steps S301 to S304 can be referred to the description of steps S101 to S104 in the previous embodiment, and will not be described herein again.
In step S305, image frames of the video call are acquired, image recognition is performed on the acquired image frames, and loading parameters of the acquired special effect in the image frames are calculated.
In the embodiment of the present invention, an image frame in a video call may be acquired at a time when the special effect corresponding to the keyword is acquired, and then a loading parameter of the acquired special effect in the image frame may be calculated according to a preset loading rule of the acquired special effect, where the preset loading rule may include a ratio of the special effect in the image frame, a loading key point in the image frame, and a positional relationship between a reference point of the special effect and the key point (for example, a distance 1/10 from the loading size of the special effect in the image frame directly above the key point), and may further include other loading parameters, such as an inclination, which are not limited herein.
In step S306, the obtained special effect is loaded into the video call according to the calculated loading parameter and the preset loading condition.
In this embodiment of the present invention, the implementation of step S306 may refer to the description of step S105 in the first embodiment, which is not repeated herein, and it should be noted that the loading parameter in this embodiment of the present invention is obtained by calculation, and when the obtained special effect is loaded into the video call, the image frame of the video call may also be obtained in real time, and the obtained image frame is subjected to image recognition to update the loading parameter, so as to implement intelligent tracking display of the special effect on the loading key point in the image.
Example four:
fig. 4 shows a structure of a wearable device-based video special effect interaction apparatus according to a fourth embodiment of the present invention, and for convenience of description, only the relevant portions of the embodiment of the present invention are shown, where the wearable device-based video special effect interaction apparatus includes:
a voice acquiring unit 41, configured to acquire a voice of a video call when it is detected that the wearable device performs the video call with the terminal;
a semantic recognition unit 42, configured to perform semantic recognition on the obtained speech to obtain a keyword in the speech;
a similarity calculation unit 43, configured to match the obtained keyword with a preset special effect name to obtain a matching similarity;
a special effect obtaining unit 44, configured to obtain a special effect corresponding to the keyword when the matching similarity is greater than a preset similarity threshold; and
and the special effect loading unit 45 is configured to load the obtained special effect into the video call according to a preset loading condition and a preset loading parameter.
In the embodiment of the present invention, each unit of the video special effect interaction apparatus based on the wearable device may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein. For specific implementation of each unit of the video special effect interaction apparatus based on the wearable device, reference may be made to the description of the first method embodiment, and details are not repeated here.
Example five:
fig. 5 shows a structure of a wearable device-based video special effect interaction apparatus according to a fifth embodiment of the present invention, and for convenience of description, only parts related to the fifth embodiment of the present invention are shown, where the parts include:
the voice acquiring unit 51 is configured to acquire a voice of a video call when it is detected that the wearable device and the terminal perform the video call;
a semantic recognition unit 52, configured to perform semantic recognition on the obtained speech to obtain a keyword in the speech;
a similarity calculation unit 43, configured to match the obtained keyword with a preset special effect name to obtain a matching similarity;
a special effect obtaining unit 54, configured to obtain a special effect corresponding to the keyword when the matching similarity is greater than a preset similarity threshold;
a special effect display unit 55, configured to display the obtained special effect in an alternative area of the video call interface; and
and a first special effect loading unit 56, configured to, when a special effect loading request input by the wearable device user through the candidate area is received, load the obtained special effect into the video call according to a preset loading parameter.
In the embodiment of the present invention, each unit of the video special effect interaction apparatus based on the wearable device may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein. For specific implementation of each unit of the video special effect interaction apparatus based on the wearable device, reference may be made to the description of the second method embodiment, and details are not repeated here.
Example six:
fig. 6 shows a structure of a wearable device-based video special effect interaction apparatus according to a sixth embodiment of the present invention, and for convenience of description, only the relevant portions of the embodiment of the present invention are shown, where the wearable device-based video special effect interaction apparatus includes:
the voice acquiring unit 61 is used for acquiring the voice of the video call when the wearable device is detected to perform the video call with the terminal;
a semantic recognition unit 62, configured to perform semantic recognition on the obtained speech to obtain a keyword in the speech;
the similarity calculation unit 63 is configured to match the obtained keyword with a preset special effect name to obtain matching similarity;
a special effect obtaining unit 64, configured to obtain a special effect corresponding to the keyword when the matching similarity is greater than a preset similarity threshold;
a parameter calculating unit 65, configured to acquire an image frame of the video call, perform image recognition on the acquired image frame, and calculate a loading parameter of the acquired special effect in the image frame; and
and a second special effect loading unit 66, configured to load the obtained special effect into the video call according to a preset loading condition and the calculated loading parameter.
In the embodiment of the present invention, each unit of the video special effect interaction apparatus based on the wearable device may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein. For specific implementation of each unit of the video special effect interaction apparatus based on the wearable device, reference may be made to the description of the third method embodiment, and details are not repeated here.
Example seven:
fig. 7 shows a structure of a wearable device provided in a fifth embodiment of the present invention, and for convenience of description, only a part related to the fifth embodiment of the present invention is shown.
The wearable device 7 of an embodiment of the present invention comprises a processor 70, a memory 71 and a computer program 72 stored in the memory 71 and executable on the processor 70. The processor 70, when executing the computer program 72, implements the steps in the above-described method embodiments, such as the steps S101 to S105 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of the units in the above-described device embodiments, such as the functions of the units 41 to 45 shown in fig. 4.
In the embodiment of the invention, when the fact that the wearable device and the terminal carry out video call is detected, voice of the video call is obtained, semantic recognition is carried out on the obtained voice to obtain a keyword in the voice, the obtained keyword is matched with a preset special effect name to obtain matching similarity, when the matching similarity is larger than a preset similarity threshold value, a special effect corresponding to the keyword is obtained, and the obtained special effect is loaded into the video call according to a preset loading condition and a preset loading parameter, so that the operation complexity of the user for using the special effect in the video call process is reduced, the interaction obstacle of the user for using the special effect is reduced, and the user experience is further improved.
Example eight:
in an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps in the above-described method embodiment, for example, steps S101 to S105 shown in fig. 1. Alternatively, the computer program realizes the functions of the units in the above-described device embodiments, such as the functions of the units 41 to 45 shown in fig. 4, when executed by the processor.
In the embodiment of the invention, when the fact that the wearable device and the terminal carry out video call is detected, voice of the video call is obtained, semantic recognition is carried out on the obtained voice to obtain a keyword in the voice, the obtained keyword is matched with a preset special effect name to obtain matching similarity, when the matching similarity is larger than a preset similarity threshold value, a special effect corresponding to the keyword is obtained, and the obtained special effect is loaded into the video call according to a preset loading condition and a preset loading parameter, so that the operation complexity of the user for using the special effect in the video call process is reduced, the interaction obstacle of the user for using the special effect is reduced, and the user experience is further improved.
The computer readable storage medium of the embodiments of the present invention may include any entity or device capable of carrying computer program code, a recording medium, such as a ROM/RAM, a magnetic disk, an optical disk, a flash memory, or the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A video special effect interaction method based on wearable equipment is characterized by comprising the following steps:
when the fact that the wearable device carries out video call with a terminal is detected, obtaining voice of the video call;
performing semantic recognition on the acquired voice to acquire key words in the voice;
matching the acquired keywords with a preset special effect name to obtain matching similarity;
when the matching similarity is larger than a preset similarity threshold, obtaining a special effect corresponding to the keyword;
loading the obtained special effect into the video call according to a preset loading condition and a preset loading parameter;
performing semantic recognition on the acquired voice to acquire a keyword in the voice, including:
carrying out grade division on the obtained keywords, wherein the keyword grade comprises a first keyword and a second keyword;
matching the acquired keywords with a preset special effect name to obtain matching similarity, wherein the matching similarity comprises the following steps:
and matching the first keyword with the special effect name to obtain a second matching similarity, acquiring a classification to which the special effect name corresponding to the first keyword belongs when the second matching similarity is greater than a preset second similarity threshold, matching the second keyword with the special effect name under the classification based on the first keyword to obtain a first matching similarity, and taking the first matching similarity as the matching similarity.
2. The method of claim 1, wherein the step of obtaining the special effect corresponding to the keyword is preceded by:
acquiring scene parameters of the video call;
and acquiring a special effect corresponding to the keyword according to the scene parameters.
3. The method according to claim 1, wherein after the step of matching the obtained keyword with a preset special effect name to obtain a matching similarity, the method comprises:
when the matching similarity is equal to 100%, obtaining a special effect corresponding to the keyword;
and loading the obtained special effect into the video call according to a preset loading parameter.
4. The method of claim 1, wherein the step of obtaining the special effect corresponding to the keyword is followed by:
displaying the obtained special effect in an alternative area of a video call interface;
and when a special effect loading request input by a wearable device user through the alternative area is received, loading the obtained special effect into the video call according to preset loading parameters.
5. The method of claim 1, wherein the step of obtaining the special effect corresponding to the keyword is followed by further comprising:
acquiring an image frame of the video call, performing image recognition on the acquired image frame, and calculating a loading parameter of the acquired special effect in the image frame;
and loading the obtained special effect into the video call according to a preset loading condition and the calculated loading parameter.
6. A video special effect interaction device based on wearable equipment is characterized in that the device comprises:
the voice acquisition unit is used for acquiring voice of the video call when the wearable device is detected to carry out the video call with the terminal;
the semantic recognition unit is used for performing semantic recognition on the acquired voice to acquire keywords in the voice;
the similarity calculation unit is used for matching the acquired keywords with a preset special effect name to obtain matching similarity;
a special effect obtaining unit, configured to obtain a special effect corresponding to the keyword when the matching similarity is greater than a preset similarity threshold; and
the special effect loading unit is used for loading the obtained special effect into the video call according to a preset loading condition and a preset loading parameter;
the semantic recognition unit is also used for carrying out grade division on the acquired keywords, and the keyword grade comprises a first keyword and a second keyword;
the similarity calculation unit is further configured to match the first keyword with the special effect name to obtain a second matching similarity, obtain a classification to which the special effect name corresponding to the first keyword belongs when the second matching similarity is greater than a preset second similarity threshold, match the second keyword with the special effect name under the classification based on the first keyword to obtain a first matching similarity, and use the first matching similarity as the matching similarity.
7. The apparatus of claim 6, wherein the apparatus further comprises:
the special effect display unit is used for displaying the obtained special effect in an alternative area of a video call interface; and
and the first special effect loading unit is used for loading the obtained special effect into the video call according to preset loading parameters when a special effect loading request input by a wearable device user through the standby area is received.
8. The apparatus of claim 6, wherein the apparatus further comprises:
the parameter calculation unit is used for acquiring image frames of the video call, performing image recognition on the acquired image frames, and calculating loading parameters of the acquired special effects in the image frames; and
and the second special effect loading unit is used for loading the obtained special effect into the video call according to a preset loading condition and the calculated loading parameter.
9. Wearable device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor realizes the steps of the method according to any of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910327776.7A CN109996026B (en) | 2019-04-23 | 2019-04-23 | Video special effect interaction method, device, equipment and medium based on wearable equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910327776.7A CN109996026B (en) | 2019-04-23 | 2019-04-23 | Video special effect interaction method, device, equipment and medium based on wearable equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109996026A CN109996026A (en) | 2019-07-09 |
| CN109996026B true CN109996026B (en) | 2021-01-19 |
Family
ID=67135081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910327776.7A Active CN109996026B (en) | 2019-04-23 | 2019-04-23 | Video special effect interaction method, device, equipment and medium based on wearable equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109996026B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117908677A (en) * | 2019-11-22 | 2024-04-19 | 广东小天才科技有限公司 | Video call method and wearable device |
| CN111416955B (en) * | 2020-03-16 | 2022-03-04 | 维沃移动通信有限公司 | Video call method and electronic equipment |
| CN111770375B (en) * | 2020-06-05 | 2022-08-23 | 百度在线网络技术（北京）有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN112702625B (en) * | 2020-12-23 | 2024-01-02 | Oppo广东移动通信有限公司 | Video processing method, device, electronic equipment and storage medium |
| CN113450804A (en) * | 2021-06-23 | 2021-09-28 | 深圳市火乐科技发展有限公司 | Voice visualization method and device, projection equipment and computer readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7681213B2 (en) * | 2001-05-16 | 2010-03-16 | Sony Corporation | Content distribution system, content distribution control apparatus, content distribution control method, content distribution control program and content distribution control program storage medium |
| CN103354522A (en) * | 2013-06-28 | 2013-10-16 | 华为技术有限公司 | Method and device for searching multistage flow table |
| CN104428766A (en) * | 2012-07-03 | 2015-03-18 | 三菱电机株式会社 | Voice recognition device |
| CN104618875A (en) * | 2015-02-06 | 2015-05-13 | 掌赢信息科技（上海）有限公司 | Message sending method and electronic device |
| US20160358629A1 (en) * | 2013-05-02 | 2016-12-08 | FreshTake Media, Inc. | Interactive real-time video editor and recorder |
| CN108986790A (en) * | 2018-09-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | The method and apparatus of voice recognition of contact |
| CN109062986A (en) * | 2018-06-29 | 2018-12-21 | 深圳市彬讯科技有限公司 | A kind of classification processing method and device of label |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004266746A (en) * | 2003-03-04 | 2004-09-24 | Megachips System Solutions Inc | Image and voice communication system |
| CN104780459A (en) * | 2015-04-16 | 2015-07-15 | 美国掌赢信息科技有限公司 | Method and electronic equipment for loading effects in instant video |
| CN105653142A (en) * | 2016-01-07 | 2016-06-08 | 厦门美图之家科技有限公司 | Image special effect ordering method and system based on areas and user attributes |
| CN109391792B (en) * | 2017-08-03 | 2021-10-29 | 腾讯科技（深圳）有限公司 | Video communication method, device, terminal and computer readable storage medium |
| CN109474844B (en) * | 2017-09-08 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Video information processing method and device and computer equipment |
| CN107864357A (en) * | 2017-09-28 | 2018-03-30 | 努比亚技术有限公司 | Video calling special effect controlling method, terminal and computer-readable recording medium |
| CN108401129A (en) * | 2018-03-22 | 2018-08-14 | 广东小天才科技有限公司 | Video call method, device, terminal based on Wearable and storage medium |
| CN109040615A (en) * | 2018-08-10 | 2018-12-18 | 北京微播视界科技有限公司 | Special video effect adding method, device, terminal device and computer storage medium |
-
2019
- 2019-04-23 CN CN201910327776.7A patent/CN109996026B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7681213B2 (en) * | 2001-05-16 | 2010-03-16 | Sony Corporation | Content distribution system, content distribution control apparatus, content distribution control method, content distribution control program and content distribution control program storage medium |
| CN104428766A (en) * | 2012-07-03 | 2015-03-18 | 三菱电机株式会社 | Voice recognition device |
| US20160358629A1 (en) * | 2013-05-02 | 2016-12-08 | FreshTake Media, Inc. | Interactive real-time video editor and recorder |
| CN103354522A (en) * | 2013-06-28 | 2013-10-16 | 华为技术有限公司 | Method and device for searching multistage flow table |
| CN104618875A (en) * | 2015-02-06 | 2015-05-13 | 掌赢信息科技（上海）有限公司 | Message sending method and electronic device |
| CN109062986A (en) * | 2018-06-29 | 2018-12-21 | 深圳市彬讯科技有限公司 | A kind of classification processing method and device of label |
| CN108986790A (en) * | 2018-09-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | The method and apparatus of voice recognition of contact |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109996026A (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109996026B (en) | Video special effect interaction method, device, equipment and medium based on wearable equipment | |
| CN109308357B (en) | Method, device and equipment for obtaining answer information | |
| CN109145123B (en) | Knowledge graph model construction method, intelligent interaction method and system and electronic equipment | |
| CN106205615B (en) | Control method and system based on voice interaction | |
| CN109145204B (en) | Portrait label generation and use method and system | |
| US20170277993A1 (en) | Virtual assistant escalation | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| US11264021B2 (en) | Method for intent-based interactive response and electronic device thereof | |
| CN110992989B (en) | Voice acquisition method and device and computer readable storage medium | |
| CN105468161A (en) | Instruction execution method and device | |
| CN111813910A (en) | Method, system, terminal device and computer storage medium for updating customer service problem | |
| CN113806503A (en) | Dialog fusion method, device and equipment | |
| CN106572131B (en) | The method and system that media data is shared in Internet of Things | |
| CN107831994A (en) | Input method enables method and device, computer installation and readable storage medium storing program for executing | |
| CN106844734B (en) | Method for automatically generating session reply content | |
| CN105869631B (en) | The method and apparatus of voice prediction | |
| CN108509442B (en) | Search method and apparatus, server, and computer-readable storage medium | |
| CN107357444A (en) | A kind of input pattern intelligent switch method and device based on usage scenario | |
| CN112966964A (en) | Product matching method, device, equipment and storage medium based on design requirements | |
| CN113656523B (en) | Destination arrival prompting method and device, electronic equipment and storage medium | |
| CN112261321B (en) | Subtitle processing method and device and electronic equipment | |
| CN108256957A (en) | Vehicle source search result based on user's history behavior shows method and device | |
| CN111367942B (en) | Address book retrieval method and device | |
| CN112732379A (en) | Operation method of application program on intelligent terminal, terminal and storage medium | |
| CN112052325A (en) | Voice interaction method and device based on dynamic perception |
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 |